OpenClaw 完整备份 - 2026-03-21

2026-03-21 15:31:06 +08:00
commit 8dd73a1d62
569 changed files with 76792 additions and 0 deletions
@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "a-stock-trading-assistant",
+  "installedVersion": "1.0.0",
+  "installedAt": 1773343749868
+}
@@ -0,0 +1,105 @@
+---
+name: a-stock-trading-assistant
+description: A股股票智能交易助手，专服务中国大陆股票市场。当用户询问A股股票行情、个股分析、大盘情绪、热点板块、交易策略、价格预警、涨跌幅、成交量、技术面或基本面分析时触发。只处理沪深A股（代码以6/00/30/68开头），自动忽略港股和美股。所有数据实时从东方财富、新浪财经、同花顺、雪球抓取。Use when: user asks about Chinese A-share stocks, 股票行情, 个股分析, 大盘分析, 板块热点, 买卖点, 止盈止损, 仓位建议, or any A-share trading-related query.
+---
+
+# A股股票智能交易助手
+
+## 角色定位
+
+你是专业A股交易助手，只服务中国大陆A股市场（沪深两市）。数据全部实时联网获取，数据源优先级：东方财富 → 新浪财经 → 同花顺 → 雪球。
+
+## 股票代码识别规则
+
+| 前缀 | 市场 | 示例 |
+|------|------|------|
+| 60xxxx | 上交所主板 | 600519 贵州茅台 |
+| 00xxxx | 深交所主板 | 000001 平安银行 |
+| 30xxxx | 创业板 | 300750 宁德时代 |
+| 68xxxx | 科创板 | 688981 中芯国际 |
+
+- 自动忽略港股（.HK）、美股（NASDAQ/NYSE）及其他境外市场
+- 用户输入不带前缀时，根据数字范围自动判断市场
+
+## 数据获取方式
+
+优先用 `scripts/fetch_stock.py` 脚本获取实时数据。如脚本执行失败，改用 `web_fetch` 直接访问数据源。
+
+详细 API 端点见 `references/data-sources.md`。
+
+### 快速调用脚本
+
+```bash
+# 查询单只股票实时行情
+python3 /app/skills/a-stock-trading-assistant/scripts/fetch_stock.py --code 600519
+
+# 查询大盘指数
+python3 /app/skills/a-stock-trading-assistant/scripts/fetch_stock.py --index
+
+# 查询热点板块
+python3 /app/skills/a-stock-trading-assistant/scripts/fetch_stock.py --hot-sectors
+```
+
+## 六大核心能力工作流
+
+### 1. 实时行情查询
+
+1. 运行 `fetch_stock.py --code <代码>` 获取实时数据
+2. 展示：当前价、涨跌幅、涨跌额、成交量、成交额、换手率、振幅、52周高/低
+3. 附上分时走势摘要（涨跌节奏描述）
+
+### 2. 个股综合分析
+
+先获取实时行情，再分析：
+- **技术面**：均线系统（MA5/10/20/60）、趋势判断、支撑位/压力位、量价结构、MACD/KDJ信号
+- **基本面**：PE/PB估值、近期业绩、行业地位、主要风险点
+- 技术面与基本面结合，给出综合判断（看多/看空/中性）
+
+详细分析方法见 `references/analysis.md`。
+
+### 3. 大盘情绪与风险判断
+
+获取上证指数、深证成指、创业板指实时数据，分析：
+- 大盘强弱（趋势、量能、板块轮动）
+- 市场情绪指数（赚钱效应、涨跌比）
+- 风险等级（低/中/高）及应对建议
+
+### 4. 热点板块与龙头股
+
+1. 运行 `fetch_stock.py --hot-sectors` 获取涨幅榜板块
+2. 识别：主线板块（连续性强）、情绪板块（短期热点）
+3. 每个热点板块列出核心龙头股（涨停、强势领涨）
+
+### 5. 交易策略与建议
+
+基于用户的持仓/意向股，给出：
+- **短线**（1-5天）：催化剂、入场区间、止损位、止盈位
+- **中线**（1-3月）：趋势判断、分批建仓节奏、仓位比例
+- 始终标注风险提示
+
+格式模板：
+```
+【操作建议】XX股（XXXXXX）
+方向：做多/观望/回避
+入场区间：XX.XX - XX.XX 元
+止损位：XX.XX 元（跌破离场）
+止盈位：XX.XX 元（分批减仓）
+仓位：XX%（轻/中/重仓）
+逻辑：[核心理由2-3条]
+风险：[主要风险1-2条]
+```
+
+### 6. 价格预警监控
+
+当用户设置预警时：
+- 记录目标价、预警条件（突破/跌破/放量）到 `references/watchlist.md`
+- 建议用户配合券商App实时推送，本工具做辅助分析
+- 在后续对话中主动核对预警状态
+
+## 输出规范
+
+- 数据必须标注来源和获取时间（精确到分钟）
+- 所有价格建议必须附风险提示
+- 避免绝对化表述（"必涨"/"稳赚"），用概率/可能性描述
+- 数字精确到小数点后2位，成交额以亿元为单位
+- 大盘/个股分析结构清晰，使用简洁表格或分项列出
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn70hb4emf3csex5aeqt51arrx82d01z",
+  "slug": "a-stock-trading-assistant",
+  "version": "1.0.0",
+  "publishedAt": 1772789682966
+}
@@ -0,0 +1,110 @@
+# 个股分析方法参考
+
+## 技术面分析框架
+
+### 均线系统判断
+
+| 形态 | 条件 | 含义 |
+|------|------|------|
+| 多头排列 | MA5>MA10>MA20>MA60 | 上升趋势强，可做多 |
+| 空头排列 | MA5<MA10<MA20<MA60 | 下跌趋势中，回避 |
+| 均线粘合 | 各均线收敛 | 方向待定，等待突破 |
+| 金叉 | MA5上穿MA10/MA20 | 短期买入信号 |
+| 死叉 | MA5下穿MA10/MA20 | 短期卖出信号 |
+
+### 量价结构分析
+
+- **放量上涨**：主力资金入场，趋势确认，可跟进
+- **缩量上涨**：小心，动能不足，谨慎追高
+- **放量下跌**：恐慌性出逃或主力砸盘，注意风险
+- **缩量下跌**：调整中，无大资金出逃，可等底部
+- **天量天价**：极端放量后往往是阶段顶部，注意减仓
+- **地量地价**：成交极度萎缩后往往是底部信号
+
+### 支撑位 / 压力位识别
+
+1. **整数关口**：100/200/300元等心理价位
+2. **前期高点/低点**：突破前高=突破压力；跌破前低=下一支撑
+3. **均线支撑**：MA20（月线）、MA60（季线）是重要支撑
+4. **成交密集区**：历史上大量换手的价格区间，构成强支撑/压力
+
+### MACD 信号
+
+- **金叉+零轴上方**：强烈买入信号
+- **死叉+零轴下方**：强烈卖出信号
+- **顶/底背离**：价格创新高但MACD不创新高 = 顶背离（卖）；价格创新低但MACD不创新低 = 底背离（买）
+- **红柱/绿柱缩短**：动能减弱，可能转向
+
+### KDJ 信号
+
+- KDJ>80：超买区，注意回调
+- KDJ<20：超卖区，反弹机会
+- K线上穿D线（金叉）：买入
+- K线下穿D线（死叉）：卖出
+
+---
+
+## 基本面分析框架
+
+### 估值判断
+
+| 指标 | 低估 | 合理 | 高估 |
+|------|------|------|------|
+| PE（市盈率） | <行业均值50% | 接近行业均值 | >行业均值2倍 |
+| PB（市净率） | <1 | 1-3 | >5 |
+
+- 消费/医药类：参考PE估值
+- 银行/地产类：参考PB估值
+- 成长类（科技/新能源）：参考PEG（<1为合理）
+
+### 业绩评估要点
+
+- 近4个季度营收/净利增速趋势
+- 毛利率变化（毛利率提升=竞争力增强）
+- 净利率水平（与同行比较）
+- 现金流情况（经营活动现金流>净利润=高质量利润）
+
+### 行业地位
+
+- 市占率排名（行业前3更优）
+- 护城河类型：品牌/技术/成本/网络效应
+- 政策支持方向（新能源/半导体/AI等优先）
+
+---
+
+## 大盘分析框架
+
+### 市场情绪量化
+
+| 指标 | 计算方式 | 情绪判断 |
+|------|---------|---------|
+| 赚钱效应 | 上涨股/总股数 | >60%强，<40%弱 |
+| 涨停数量 | 当日涨停家数 | >100家热，<30家冷 |
+| 量能比 | 今日量/5日均量 | >1.2放量，<0.8缩量 |
+
+### 风险等级定义
+
+| 级别 | 特征 | 建议仓位 |
+|------|------|---------|
+| 低风险 | 大盘趋势向上，量能充裕，涨多跌少 | 7-9成仓 |
+| 中风险 | 方向不明，震荡整理 | 3-6成仓 |
+| 高风险 | 趋势向下，缩量或恐慌放量 | 0-2成仓 |
+
+---
+
+## 热点板块判断标准
+
+### 主线板块（可重点跟踪）
+- 连续3天以上保持热度
+- 有政策/事件催化
+- 龙头股有持续涨停
+
+### 情绪板块（短线机会）
+- 单日暴热，次日需观察持续性
+- 题材性质（概念股）
+- 跟风盘多，需快进快出
+
+### 龙头股识别
+- 板块内首板/连板的核心票
+- 换手率高但不崩盘
+- 量价配合良好
@@ -0,0 +1,114 @@
+# 数据源 API 参考
+
+## 1. 新浪财经（最稳定，优先使用）
+
+### 实时行情
+
+```
+# 单股（沪市加sh，深市加sz）
+GET http://hq.sinajs.cn/list=sh600519
+GET http://hq.sinajs.cn/list=sz000001
+
+# 多股同时查询
+GET http://hq.sinajs.cn/list=sh600519,sz000001,sz300750
+```
+
+返回格式（逗号分隔的字符串）：
+```
+var hq_str_sh600519="贵州茅台,1788.00,1785.00,1800.00,1810.00,1780.00,1799.00,1800.00,3456789,6234567890.00,100,1799.00,...,2024-01-15,15:00:00,00";
+```
+字段顺序：股票名,昨收,今开,当前价,最高,最低,买一价,卖一价,成交量(手),成交额,买一量,买一价,...,日期,时间
+
+### 大盘指数
+
+```
+GET http://hq.sinajs.cn/list=s_sh000001,s_sz399001,s_sz399006
+# 上证指数,深证成指,创业板指
+```
+
+---
+
+## 2. 东方财富（数据全面，适合深度查询）
+
+### 实时行情
+
+```
+GET http://push2.eastmoney.com/api/qt/stock/get?secid={market}.{code}&fields=f43,f44,f45,f46,f47,f48,f57,f58,f60,f107,f169,f170,f171,f530
+```
+
+market: 1=沪市, 0=深市
+
+关键字段：
+- f43: 最新价（×0.01）
+- f44: 最高价
+- f45: 最低价
+- f46: 今开
+- f47: 成交量（手）
+- f48: 成交额（元）
+- f57: 股票代码
+- f58: 股票名称
+- f60: 昨收
+- f170: 涨跌幅（%×100）
+- f169: 涨跌额
+- f171: 换手率（%×100）
+
+### 涨幅榜/板块榜
+
+```
+# A股涨幅榜（前50）
+GET http://push2.eastmoney.com/api/qt/clist/get?pn=1&pz=50&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&fid=f3&fs=m:0+t:6,m:0+t:13,m:0+t:80,m:1+t:2,m:1+t:23&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18
+
+# 板块涨跌榜（概念/行业）
+GET http://push2.eastmoney.com/api/qt/clist/get?pn=1&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&fid=f3&fs=m:90+t:2+f:!50&fields=f1,f2,f3,f4,f5,f6,f7,f8,f12,f14,f20,f21
+```
+
+### 个股分时数据
+
+```
+GET http://push2.eastmoney.com/api/qt/stock/trends2/get?secid={market}.{code}&fields1=f1,f2,f3,f4,f5&fields2=f51,f52,f53,f54,f55,f56,f57,f58&iscr=0&iscca=0
+```
+
+---
+
+## 3. 同花顺
+
+### 实时行情
+
+```
+GET https://d.10jqka.com.cn/v4/time/hs_{code}/today.js
+# code: 直接用6位数字，如 600519
+```
+
+注意：请求需要带 Referer: https://www.10jqka.com.cn
+
+---
+
+## 4. 雪球
+
+### 实时行情
+
+```
+GET https://stock.xueqiu.com/v5/stock/quote.json?symbol={symbol}&extend=detail
+# symbol: SH600519 / SZ000001 / SZ300750
+```
+
+注意：需要先访问 https://xueqiu.com 获取 cookie（session），再请求数据接口。脚本中已处理。
+
+---
+
+## 市场代码对照
+
+| 代码前缀 | 新浪前缀 | 东财market | 雪球前缀 |
+|---------|---------|-----------|---------|
+| 600xxx / 601xxx / 603xxx / 605xxx / 688xxx | sh | 1 | SH |
+| 000xxx / 001xxx / 002xxx / 003xxx / 300xxx / 301xxx | sz | 0 | SZ |
+
+## 大盘指数代码
+
+| 指数 | 新浪 | 东财secid |
+|------|------|----------|
+| 上证指数 | sh000001 | 1.000001 |
+| 深证成指 | sz399001 | 0.399001 |
+| 创业板指 | sz399006 | 0.399006 |
+| 科创50 | sh000688 | 1.000688 |
+| 北证50 | bj899050 | — |
@@ -0,0 +1,22 @@
+# 价格预警监控列表
+
+## 预警记录
+
+| 股票 | 代码 | 预警类型 | 目标价 | 当前价 | 状态 | 设置时间 |
+|------|------|----------|--------|--------|------|----------|
+| 铜陵有色 | 000630 | 跌破 | 6.80 元 | 7.15 元 | ⏳ 监控中 | 2026-03-13 03:33 |
+
+---
+
+## 预警详情
+
+### 铜陵有色 (000630)
+- **预警条件**：股价跌破 6.80 元
+- **当前价格**：7.15 元 (2026-03-13 15:00)
+- **距离预警**：-0.35 元 (-4.9%)
+- **设置时间**：2026-03-13 03:33
+- **备注**：用户要求跌破 6.8 元时进行预警
+
+---
+
+> ⚠️ **说明**：本工具做辅助分析，建议配合券商 App 实时推送获取即时预警。
@@ -0,0 +1,299 @@
+#!/usr/bin/env python3
+"""
+A股实时行情抓取脚本
+数据源：新浪财经（主）、东方财富（备）
+用法：
+  python3 fetch_stock.py --code 600519
+  python3 fetch_stock.py --code 000001 sz000001 300750
+  python3 fetch_stock.py --index
+  python3 fetch_stock.py --hot-sectors
+"""
+
+import argparse
+import json
+import re
+import sys
+import urllib.request
+import urllib.error
+from datetime import datetime
+
+
+HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+    "Referer": "https://finance.sina.com.cn",
+    "Accept-Language": "zh-CN,zh;q=0.9",
+}
+
+
+def get_market_prefix(code: str) -> str:
+    """根据股票代码判断市场前缀"""
+    code = code.strip().upper()
+    if code.startswith("SH") or code.startswith("SZ"):
+        return code[:2].lower(), code[2:]
+    code = re.sub(r"[^0-9]", "", code)
+    if code.startswith(("60", "68", "51", "58", "11")):
+        return "sh", code
+    elif code.startswith(("00", "30", "15", "12", "16", "13")):
+        return "sz", code
+    return "sh", code  # default
+
+
+def fetch_url(url: str, extra_headers: dict = None) -> str:
+    req = urllib.request.Request(url, headers=HEADERS)
+    if extra_headers:
+        for k, v in extra_headers.items():
+            req.add_header(k, v)
+    try:
+        with urllib.request.urlopen(req, timeout=10) as resp:
+            charset = "gbk" if "sina" in url or "sinajs" in url else "utf-8"
+            return resp.read().decode(charset, errors="replace")
+    except Exception as e:
+        return ""
+
+
+def parse_sina_stock(raw: str, symbol: str) -> dict:
+    """解析新浪财经股票数据"""
+    match = re.search(r'"([^"]*)"', raw)
+    if not match:
+        return {}
+    parts = match.group(1).split(",")
+    if len(parts) < 32:
+        return {}
+    try:
+        name = parts[0]
+        prev_close = float(parts[2]) if parts[2] else 0
+        open_price = float(parts[1]) if parts[1] else 0
+        current = float(parts[3]) if parts[3] else 0
+        high = float(parts[4]) if parts[4] else 0
+        low = float(parts[5]) if parts[5] else 0
+        volume = int(parts[8]) if parts[8] else 0  # 手
+        amount = float(parts[9]) if parts[9] else 0  # 元
+        date_str = parts[30] if len(parts) > 30 else ""
+        time_str = parts[31] if len(parts) > 31 else ""
+
+        change = current - prev_close
+        change_pct = (change / prev_close * 100) if prev_close else 0
+        turnover_approx = volume / 1000  # 粗略换手（无流通股数据）
+
+        return {
+            "symbol": symbol,
+            "name": name,
+            "current": round(current, 2),
+            "change": round(change, 2),
+            "change_pct": round(change_pct, 2),
+            "open": round(open_price, 2),
+            "high": round(high, 2),
+            "low": round(low, 2),
+            "prev_close": round(prev_close, 2),
+            "volume_lot": volume,  # 手
+            "amount_yuan": round(amount, 2),
+            "amount_yi": round(amount / 1e8, 2),
+            "date": date_str,
+            "time": time_str,
+            "source": "新浪财经",
+            "fetch_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        }
+    except (ValueError, IndexError):
+        return {}
+
+
+def fetch_single_stock(code: str) -> dict:
+    """抓取单只股票行情"""
+    prefix, clean_code = get_market_prefix(code)
+    symbol = f"{prefix}{clean_code}"
+    url = f"http://hq.sinajs.cn/list={symbol}"
+    raw = fetch_url(url)
+    if raw:
+        data = parse_sina_stock(raw, symbol)
+        if data:
+            return data
+
+    # 备用：东方财富
+    market = 1 if prefix == "sh" else 0
+    url2 = (
+        f"http://push2.eastmoney.com/api/qt/stock/get"
+        f"?secid={market}.{clean_code}"
+        f"&fields=f43,f44,f45,f46,f47,f48,f57,f58,f60,f107,f169,f170,f171"
+    )
+    raw2 = fetch_url(url2, {"Referer": "https://www.eastmoney.com"})
+    if raw2:
+        try:
+            obj = json.loads(raw2)
+            d = obj.get("data", {}) or {}
+            if d.get("f43"):
+                prev = d["f60"] / 100
+                curr = d["f43"] / 100
+                chg = d["f169"] / 100
+                chg_pct = d["f170"] / 100
+                return {
+                    "symbol": symbol,
+                    "name": d.get("f58", ""),
+                    "current": round(curr, 2),
+                    "change": round(chg, 2),
+                    "change_pct": round(chg_pct, 2),
+                    "open": round(d["f46"] / 100, 2),
+                    "high": round(d["f44"] / 100, 2),
+                    "low": round(d["f45"] / 100, 2),
+                    "prev_close": round(prev, 2),
+                    "volume_lot": d.get("f47", 0),
+                    "amount_yuan": d.get("f48", 0),
+                    "amount_yi": round(d.get("f48", 0) / 1e8, 2),
+                    "turnover_pct": round(d.get("f171", 0) / 100, 2),
+                    "source": "东方财富",
+                    "fetch_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+                }
+        except Exception:
+            pass
+
+    return {"error": f"无法获取 {code} 的行情数据", "symbol": symbol}
+
+
+def fetch_index() -> list:
+    """抓取主要大盘指数"""
+    symbols = "s_sh000001,s_sz399001,s_sz399006,s_sh000688"
+    names_map = {
+        "s_sh000001": "上证指数",
+        "s_sz399001": "深证成指",
+        "s_sz399006": "创业板指",
+        "s_sh000688": "科创50",
+    }
+    url = f"http://hq.sinajs.cn/list={symbols}"
+    raw = fetch_url(url)
+    results = []
+    if raw:
+        for sym, name in names_map.items():
+            pattern = rf'hq_str_{re.escape(sym)}="([^"]*)"'
+            m = re.search(pattern, raw)
+            if m:
+                parts = m.group(1).split(",")
+                if len(parts) >= 5:
+                    try:
+                        results.append({
+                            "name": parts[0] or name,
+                            "current": float(parts[1]),
+                            "change": float(parts[2]),
+                            "change_pct": float(parts[3]),
+                            "volume_yi_lot": round(float(parts[4]) / 1e8, 2),
+                            "amount_yi": round(float(parts[5]) / 1e8, 2) if len(parts) > 5 else 0,
+                            "fetch_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+                            "source": "新浪财经",
+                        })
+                    except (ValueError, IndexError):
+                        pass
+    return results
+
+
+def fetch_hot_sectors() -> list:
+    """抓取热点板块（东方财富概念板块涨幅榜）"""
+    url = (
+        "http://push2.eastmoney.com/api/qt/clist/get"
+        "?pn=1&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281"
+        "&fltt=2&invt=2&fid=f3"
+        "&fs=m:90+t:2+f:!50"
+        "&fields=f2,f3,f4,f12,f14,f20,f128,f136,f207,f208,f209"
+    )
+    raw = fetch_url(url, {"Referer": "https://www.eastmoney.com"})
+    results = []
+    if raw:
+        try:
+            obj = json.loads(raw)
+            items = obj.get("data", {}).get("diff", [])
+            for item in items:
+                results.append({
+                    "name": item.get("f14", ""),
+                    "change_pct": round(item.get("f3", 0), 2),
+                    "leading_stock": item.get("f128", ""),
+                    "leading_change_pct": round(item.get("f136", 0), 2),
+                    "amount_yi": round(item.get("f20", 0) / 1e8, 2),
+                })
+        except Exception:
+            pass
+    return results
+
+
+def fmt_stock(d: dict) -> str:
+    if "error" in d:
+        return f"❌ {d['error']}"
+    sign = "+" if d["change"] >= 0 else ""
+    emoji = "🔴" if d["change"] >= 0 else "🟢"
+    lines = [
+        f"{emoji} {d['name']}（{d['symbol'].upper()}）",
+        f"  当前价：{d['current']} 元",
+        f"  涨跌幅：{sign}{d['change_pct']}%  涨跌额：{sign}{d['change']}",
+        f"  今开：{d['open']}  最高：{d['high']}  最低：{d['low']}  昨收：{d['prev_close']}",
+        f"  成交量：{d['volume_lot']:,} 手  成交额：{d['amount_yi']} 亿",
+    ]
+    if "turnover_pct" in d:
+        lines.append(f"  换手率：{d['turnover_pct']}%")
+    lines.append(f"  数据来源：{d['source']} | 更新时间：{d.get('time', '')} {d['fetch_time']}")
+    return "\n".join(lines)
+
+
+def fmt_index(items: list) -> str:
+    lines = ["📊 大盘指数实时行情"]
+    for d in items:
+        sign = "+" if d["change"] >= 0 else ""
+        emoji = "🔴" if d["change"] >= 0 else "🟢"
+        lines.append(
+            f"  {emoji} {d['name']}: {d['current']:,.2f}  {sign}{d['change']:+.2f} ({sign}{d['change_pct']}%)"
+            f"  成交额 {d['amount_yi']} 亿"
+        )
+    if items:
+        lines.append(f"  更新时间：{items[0]['fetch_time']}")
+    return "\n".join(lines)
+
+
+def fmt_sectors(items: list) -> str:
+    lines = ["🔥 热点板块涨幅榜（概念板块 TOP20）"]
+    for i, d in enumerate(items, 1):
+        sign = "+" if d["change_pct"] >= 0 else ""
+        lines.append(
+            f"  {i:2d}. {d['name']:<12} {sign}{d['change_pct']}%"
+            f"  龙头：{d['leading_stock']}({sign}{d['leading_change_pct']}%)"
+            f"  成交额：{d['amount_yi']}亿"
+        )
+    return "\n".join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="A股实时行情抓取")
+    parser.add_argument("--code", nargs="+", help="股票代码，支持多个（如 600519 000001）")
+    parser.add_argument("--index", action="store_true", help="查询大盘指数")
+    parser.add_argument("--hot-sectors", action="store_true", help="查询热点板块")
+    parser.add_argument("--json", action="store_true", help="输出原始JSON")
+    args = parser.parse_args()
+
+    if args.index:
+        data = fetch_index()
+        if args.json:
+            print(json.dumps(data, ensure_ascii=False, indent=2))
+        else:
+            print(fmt_index(data))
+        return
+
+    if args.hot_sectors:
+        data = fetch_hot_sectors()
+        if args.json:
+            print(json.dumps(data, ensure_ascii=False, indent=2))
+        else:
+            print(fmt_sectors(data))
+        return
+
+    if args.code:
+        results = []
+        for code in args.code:
+            d = fetch_single_stock(code)
+            results.append(d)
+        if args.json:
+            print(json.dumps(results, ensure_ascii=False, indent=2))
+        else:
+            for d in results:
+                print(fmt_stock(d))
+                print()
+        return
+
+    parser.print_help()
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "content-collector-skill",
+  "installedVersion": "0.1.0",
+  "installedAt": 1773515645180
+}
@@ -0,0 +1,800 @@
+---
+name: content-collector
+description: Automatically collect and archive content from shared links in group chats. When a user shares a link (WeChat articles, Feishu docs, web pages, etc.) in any group chat and asks to archive/collect/save it, this skill triggers to fetch the content, create a Feishu document, and update the knowledge base table. Use when: (1) User shares a link and asks to "收录/转存/保存" content, (2) Need to archive web content to Feishu docs, (3) Building a personal knowledge base from shared links, (4) Organizing learning materials from various sources.
+---
+
+# Content Collector - 链接内容自动收录技能
+
+## Overview
+
+This skill enables automatic collection and archiving of content from shared links into a structured knowledge base.
+
+**Core Workflow:**
+```
+Detect Link → Fetch Content → Create Feishu Doc → Update Table
+```
+
+## When to Use
+
+### 模式1：主动触发（显式关键词）
+当用户消息包含以下**触发词**时，立即执行收录：
+- "收录" / "转存" / "保存" / "存档" / "存一下" / "归档" / "备份" / "收藏"
+- "存到知识库" / "加入知识库" / "转飞书"
+
+**示例：**
+- "这个链接收录一下"
+- "存到知识库"
+- "转存这篇教程"
+
+### 模式2：静默收录（自动检测）
+在**群聊场景**中，自动检测以下链接并静默收录：
+- 飞书文档/表格/Wiki（feishu.cn）
+- 微信公众号文章（mp.weixin.qq.com）
+- 技术博客/教程站点
+- 知识分享类链接
+
+**静默收录条件：**
+1. 消息来自群聊（非私聊）
+2. 消息包含可识别的知识类链接
+3. 用户没有明确拒绝的意图
+
+**两种模式优先级：**
+```
+检测到主动触发词 → 立即收录（显式模式）
+未检测到触发词但检测到链接 → 静默收录（隐式模式）
+```
+
+## Supported Link Types
+
+| Type | Example | Fetch Method |
+|------|---------|--------------|
+| WeChat Article | `https://mp.weixin.qq.com/s/xxx` | kimi_fetch |
+| Feishu Doc | `https://xxx.feishu.cn/docx/xxx` | feishu_fetch_doc |
+| Feishu Wiki | `https://xxx.feishu.cn/wiki/xxx` | feishu_fetch_doc |
+| Web Page | General URLs | kimi_fetch / web_fetch |
+
+## Global Availability (全局可用配置)
+
+**生效范围：所有用户、所有群聊**
+
+本技能已配置为全局可用，支持以下对象：
+
+| 对象类型 | 支持状态 | 说明 |
+|---------|---------|------|
+| **所有用户** | ✅ 可用 | 任何用户分享的链接均可被收录 |
+| **所有群聊** | ✅ 可用 | 支持技能中心群、养虾群、学习群等所有群组 |
+| **私聊消息** | ✅ 可用 | 用户私信分享链接也可触发收录 |
+| **多渠道** | ✅ 可用 | 飞书、其他渠道统一支持 |
+
+**权限说明：**
+- 任何用户均可触发收录（无需管理员权限）
+- 收录的文档统一存储到指定的知识库目录
+- 所有用户均可查看已收录的文档
+
+---
+
+## Installation & Permission Check (安装与权限检查)
+
+在正式使用本技能前，系统必须自动或引导用户完成以下权限校验，以确保流程不中断：
+
+### 1. 飞书权限清单
+| 权限项 | 验证工具 | 目的 |
+|-------|---------|------|
+| **OAuth 授权** | `feishu_oauth` | 获取操作飞书文档和表格的用户凭证 |
+| **知识库写入权限** | `feishu_create_doc` | 确保能在指定的 Space ID 下创建节点 |
+| **多维表格编辑权限** | `feishu_bitable_app_table_record` | 确保能向指定的 app_token 写入记录 |
+| **图片上传权限** | `feishu_im_bot_upload` | 允许将本地图片同步至飞书素材库 |
+
+### 2. 预检流程 (Pre-flight Check)
+每次“安装”或配置更新后，执行以下检查：
+1. **验证 Space ID 可访问性**：尝试在指定目录下获取节点列表。
+2. **验证 Table 结构**：检查 `关键词`、`原链接` 等必需字段是否存在。
+3. **静默测试**：如果权限不足，立即通过 `feishu_oauth` 弹出授权引导，而非在执行收录时报错。
+
+---
+
+## Configuration
+
+Before using, ensure these are configured in MEMORY.md:
+
+```markdown
+## Content Collector Config
+- **Knowledge Base Table**: `[Your Bitable App Token]` (Bitable app_token)
+- **Table URL**: [Your Bitable Table URL]
+- **Default Table ID**: `[Your Table ID]` (will auto-detect if available)
+- **Knowledge Base Space ID**: `[Your Space ID]` (所有文档创建在此知识库下)
+- **Knowledge Base URL**: [Your Knowledge Base Homepage URL]
+- **Content Categories**: 技术教程, 实战案例, 产品文档, 学习笔记
+- **Global Access**: 所有用户可用，所有群聊可用
+```
+
+**Note**: 
+1. This skill updates ONLY the configured knowledge base table. Do not create or update any other tables.
+2. **All created documents must be saved under the designated Knowledge Base** using wiki_node parameter.
+3. **Global Access**: 所有用户、所有群聊均可使用本技能，收录的文档对全员可见。
+
+---
+
+## 📚 知识库文档存储规则（必遵守）
+
+所有收录的文档必须按照以下规则分类存储到知识库对应目录：
+
+### 知识库目录结构
+
+请参考各项目或团队定义的知识库标准目录结构进行存储。收录的文档通常存放在“素材”或“归档”类目录下。
+
+### 文档分类映射规则
+
+| 内容分类 | 存储目录 (wiki_node) | 命名前缀 | 示例 |
+|----------|---------------------|----------|------|
+| 技术教程 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 📖 | 📖 [标题] |
+| 实战案例 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 🛠️ | 🛠️ [标题] |
+| 产品文档 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 📄 | 📄 [标题] |
+| 学习笔记 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 💡 | 💡 [标题] |
+| 热点资讯 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 🔥 | 🔥 [标题] |
+| 设计技能 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 🎨 | 🎨 [标题] |
+| 工具推荐 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 🔧 | 🔧 [标题] |
+| 训练营 | `F9pFw9dxTiXmpsk5bNlco704nag` (内容文档) | 🎓 | 🎓 [标题] |
+
+### 文档命名规范
+
+```
+[Emoji前缀] [原标题] | 收录日期
+
+示例：
+📖 OpenClaw保姆级教程 | 2026-03-08
+🛠️ 火山方舟自动化报表案例 | 2026-03-08
+🔥 GPT-5.4发布解读 | 2026-03-08
+```
+
+### 文档模板
+
+```markdown
+# [Emoji] [原标题]
+
+> 📌 **元信息**
+> - 来源：[原始来源]
+> - 原文链接：[原始URL]
+> - 收录时间：YYYY-MM-DD
+> - 内容分类：[技术教程/实战案例/产品文档/学习笔记/热点资讯/设计技能/工具推荐/训练营]
+> - 关键词：[关键词1, 关键词2, 关键词3]
+
+---
+
+## 📋 核心要点
+
+[3-5条核心内容摘要]
+
+---
+
+## 📝 正文内容
+
+[完整的转存内容]
+
+---
+
+## 🔗 相关链接
+
+- 原文链接：[原始URL]
+- 知识库索引：[素材池文档索引链接]
+
+---
+
+📚 **收录时间**：YYYY-MM-DD  
+🏷️ **分类**：[分类名]  
+🔖 **关键词**：[关键词]
+```
+
+### 自动更新素材索引
+
+每次收录完成后，必须：
+
+1. **更新多维表格** - 添加新记录到素材池表格
+2. **更新素材索引文档** - 在「📚 内容素材池文档索引」中添加条目
+3. **更新分类统计** - 更新各分类的文档数量和占比
+
+---
+
+## Workflow
+
+### Step 1: Detect and Parse Link
+
+Extract URL from user message using regex or direct extraction.
+
+### Step 2: Fetch Content
+
+Choose appropriate fetch method based on URL pattern:
+
+**For WeChat articles:**
+```python
+kimi_fetch(url="https://mp.weixin.qq.com/s/xxx")
+```
+
+**For Feishu docs:**
+```python
+feishu_fetch_doc(doc_id="https://xxx.feishu.cn/docx/xxx")
+```
+
+**For general web pages:**
+```python
+kimi_fetch(url="https://example.com/article")
+# or
+web_fetch(url="https://example.com/article")
+```
+
+### Step 3: Analyze and Categorize
+
+**智能分类判断：**
+根据内容特征自动判断分类：
+
+| 判断依据 | 分类 |
+|----------|------|
+| 包含"安装/配置/部署/教程"等词 | 📖 技术教程 |
+| 包含"案例/实战/项目/演示"等词 | 🛠️ 实战案例 |
+| 包含"安全/公告/版本/功能"等词 | 📄 产品文档 |
+| 包含"学习/成长/指南/笔记"等词 | 💡 学习笔记 |
+| 包含"发布/新功能/热点"等词 | 🔥 热点资讯 |
+| 包含"设计/Prompt/美学"等词 | 🎨 设计技能 |
+| 包含"工具/CLI/插件"等词 | 🔧 工具推荐 |
+| 包含"训练营/课程/教学"等词 | 🎓 训练营 |
+
+### Step 4: Process Images (图片处理)
+
+When content contains images, download and upload them to Feishu:
+
+**Image Processing Workflow:**
+```python
+# 1. Extract image URLs from markdown
+import re
+image_urls = re.findall(r'!\[.*?\]\((https?://[^\)]+)\)', markdown_content)
+
+# 2. Download and upload each image
+for img_url in image_urls:
+    try:
+        # Download image
+        local_path = f"/tmp/img_{hash(img_url)}.jpg"
+        download_image(img_url, local_path)
+        
+        # Upload to Feishu
+        upload_result = feishu_im_bot_upload(
+            action="upload_image",
+            file_path=local_path
+        )
+        
+        # Replace URL in markdown
+        new_url = upload_result.get("image_key") or img_url
+        markdown_content = markdown_content.replace(img_url, new_url)
+        
+    except Exception as e:
+        # Keep original URL if upload fails
+        print(f"Failed to process image {img_url}: {e}")
+        continue
+```
+
+**Fallback Strategy:**
+- If image upload fails, keep original URL
+- Add warning note in document
+- Include original source link for reference
+
+### Step 5: Create Feishu Document (按知识库规则存储)
+
+Convert processed markdown to Feishu document with proper organization:
+
+```python
+# 1. 确定分类和参数
+content_category = classify_content(markdown_content)  # 📖/🛠️/📄/💡/🔥/🎨/🔧/🎓
+emoji_prefix = get_emoji_prefix(content_category)  # 根据分类获取emoji
+wiki_node = get_wiki_node_by_category(content_category)  # 获取存储目录
+
+# 2. 生成文档标题
+doc_title = f"{emoji_prefix} {original_title} | {today_date}"
+
+# 3. 生成文档内容（使用标准模板）
+doc_content = f"""# {emoji_prefix} {original_title}
+
+> 📌 **元信息**
+> - 来源：{source_name}
+> - 原文链接：{original_url}
+> - 收录时间：{today_date}
+> - 内容分类：{content_category}
+> - 关键词：{keywords}
+
+---
+
+## 📋 核心要点
+
+{extract_key_points(markdown_content, 5)}
+
+---
+
+## 📝 正文内容
+
+{processed_markdown_content}
+
+---
+
+## 🔗 相关链接
+
+- 原文链接：{original_url}
+- 知识库索引：[Your Index Document URL]
+
+---
+
+📅 **收录时间**：{today_date}  
+🏷️ **分类**：{content_category}  
+🔖 **关键词**：{keywords}
+"""
+
+# 4. 创建文档到知识库对应目录
+feishu_create_doc(
+    title=doc_title,
+    markdown=doc_content,
+    wiki_node=wiki_node  # 必须指定存储目录
+)
+```
+
+**存储目录映射：**
+| 分类 | wiki_node | 目录名 |
+|------|-----------|--------|
+| 所有素材 | `F9pFw9dxTiXmpsk5bNlco704nag` | 04-内容素材 |
+
+**IMPORTANT**: 
+1. All documents MUST be created under the designated Knowledge Base using wiki_node parameter.
+2. Documents must follow the naming convention: `[Emoji] [Title] | [Date]`
+3. Documents must use the standard template with metadata section.
+
+### Step 6: Update Knowledge Base Table
+
+Add record to the Bitable knowledge base (ONLY update this specific table):
+
+```python
+feishu_bitable_app_table_record(
+    action="create",
+    app_token="[Your App Token]",  # Configured in MEMORY.md
+    table_id="[Your Table ID]",  # Will use correct table ID from the base
+    fields={
+        "关键词": keywords,
+        "内容分类": content_category,
+        "文档标题": [{"text": original_title, "type": "text"}],
+        "来源": [{"text": source_name, "type": "text"}],
+        "核心要点": [{"text": key_points, "type": "text"}],
+        "飞书文档链接": {"link": new_doc_url, "text": "飞书文档", "type": "url"},
+        "原链接": {"link": original_url, "text": "原文链接", "type": "url"}  # 新增：存储原始链接
+    }
+)
+```
+
+**Table Fields:**
+| Field | Type | Description |
+|-------|------|-------------|
+| 关键词 | Text | Search keywords for the content |
+| 内容分类 | Single Select | Category: 📖技术教程/🛠️实战案例/📄产品文档/💡学习笔记/🔥热点资讯/🎨设计技能/🔧工具推荐/🎓训练营 |
+| 文档标题 | Text | Title of the archived document |
+| 来源 | Text | Original source name |
+| 核心要点 | Text | Key points summary (3-5 items) |
+| 飞书文档链接 | URL | Link to the created Feishu document |
+| 原链接 | URL | **Original source URL** - 新增字段，存储采集的原始链接 |
+
+**IMPORTANT**: Only update the configured knowledge base table. Never create or modify other tables.
+
+### Step 7: Update Content Index Document
+
+After creating the document and updating the table, MUST update the index document:
+
+```python
+# 1. 获取当前索引文档内容
+index_doc = feishu_fetch_doc(doc_id="[Your Index Doc ID]")
+
+# 2. 在对应分类表格中添加新行
+new_index_entry = f"| {original_title} | {source_name} | [查看]({new_doc_url}) |\n"
+
+# 3. 更新分类统计
+update_category_stats(content_category)
+
+# 4. 更新总计数
+update_total_count()
+```
+
+**或者直接追加到索引文档的末尾：**
+```python
+feishu_update_doc(
+    doc_id="[Your Index Doc ID]",
+    mode="append",
+    markdown=f"""
+| {original_title} | {source_name} | [查看]({new_doc_url}) |
+"""
+)
+```
+
+---
+
+## Content Categorization Guide
+
+| Category | Emoji | Description | Examples |
+|----------|-------|-------------|----------|
+| **技术教程** | 📖 | Step-by-step technical guides | Installation, configuration, API usage |
+| **实战案例** | 🛠️ | Real-world implementation examples | Case studies, project demos |
+| **产品文档** | 📄 | Product features, security notices | Release notes, security advisories |
+| **学习笔记** | 💡 | Conceptual knowledge, methodologies | Best practices, architecture guides |
+| **热点资讯** | 🔥 | Breaking news, releases | GPT-5.4, new features |
+| **设计技能** | 🎨 | Design, prompts, aesthetics | AJ's prompts, design guides |
+| **工具推荐** | 🔧 | Tools, CLI, plugins | gws, trae, autotools |
+| **训练营** | 🎓 | Courses, bootcamps, tutorials | OpenClaw bootcamp |
+
+**分类判断优先级：**
+1. 优先根据用户指定分类
+2. 其次根据标题关键词
+3. 最后根据内容特征自动判断
+4. 不确定时标记为"待分类"，请用户确认
+
+## Delete Record Process
+
+When user replies "删除" or "删除 [keyword]":
+
+```python
+# 1. Search records by keyword
+feishu_bitable_app_table_record(
+    action="list",
+    app_token="[Your App Token]",
+    table_id="[Your Table ID]",
+    filter={
+        "conjunction": "and",
+        "conditions": [
+            {"field_name": "关键词", "operator": "contains", "value": [keyword]}
+        ]
+    }
+)
+
+# 2. Confirm deletion
+# If multiple found → list for user to select
+# If single found → ask for confirmation
+
+# 3. Execute deletion
+feishu_bitable_app_table_record(
+    action="delete",
+    app_token="[Your App Token]",
+    table_id="[Your Table ID]",
+    record_id="record_id_to_delete"
+)
+```
+
+## Error Handling
+
+### Common Issues
+
+| Error | Cause | Solution |
+|-------|-------|----------|
+| Fetch timeout | Network issue or heavy content | Retry with longer timeout, or use alternative fetch method |
+| Unauthenticated | OAuth token expired or not authed | Trigger `feishu_oauth` to refresh user credentials |
+| Permission denied | No write access to Space/Table | Check if user/bot has 'Editor' role in Feishu |
+| Content too long | Exceeds API limits | Truncate or split into multiple documents |
+| Table update failed | Wrong app_token or table_id | Verify configuration in MEMORY.md |
+| Field Missing | "原链接" field not in table | Add the field to Bitable manually or via API |
+
+### Recovery Steps
+
+1. If fetch fails → Try alternative method (kimi_fetch → web_fetch)
+2. If Feishu doc creation fails → Check OAuth status
+3. If table update fails → Verify table structure and field names
+4. Always report partial success (doc created but table not updated)
+
+## Response Template
+
+### 收录成功响应（流式Post格式）
+
+```json
+{
+  "msg_type": "post",
+  "content": {
+    "post": {
+      "zh_cn": {
+        "title": "✅ 收录完成",
+        "content": [
+          [
+            {"tag": "text", "text": "📄 "},
+            {"tag": "text", "text": "{emoji} {原标题} | {日期}", "style": {"bold": true}}
+          ],
+          [{"tag": "text", "text": ""}],
+          [
+            {"tag": "text", "text": "💡 文档亮点：", "style": {"bold": true}}
+          ],
+          [
+            {"tag": "text", "text": "• {亮点1}"}
+          ],
+          [
+            {"tag": "text", "text": "• {亮点2}"}
+          ],
+          [
+            {"tag": "text", "text": "• {亮点3}"}
+          ],
+          [{"tag": "text", "text": ""}],
+          [
+            {"tag": "text", "text": "🔗 "},
+            {"tag": "a", "text": "查看飞书文档", "href": "{文档URL}"}
+          ]
+        ]
+      }
+    }
+  }
+}
+```
+
+**简洁输出示例：**
+```
+✅ 收录完成
+
+📄 📖 OpenClaw配置指南 | 2026-03-08
+
+💡 文档亮点：
+• 完整配置示例，含9大模块详解
+• 多Agent扩展配置方案
+• 生产环境安全配置建议
+
+🔗 查看飞书文档 → [点击打开](https://xxx.feishu.cn/docx/xxx)
+```
+
+### 静默收录响应（流式Post格式）
+
+```json
+{
+  "msg_type": "post",
+  "content": {
+    "post": {
+      "zh_cn": {
+        "title": "✅ 已自动收录",
+        "content": [
+          [
+            {"tag": "text", "text": "📄 "},
+            {"tag": "text", "text": "{emoji} {原标题}", "style": {"bold": true}}
+          ],
+          [{"tag": "text", "text": ""}],
+          [
+            {"tag": "text", "text": "💡 亮点：{亮点摘要}"}
+          ],
+          [{"tag": "text", "text": ""}],
+          [
+            {"tag": "a", "text": "📎 查看文档", "href": "{文档URL}"}
+          ]
+        ]
+      }
+    }
+  }
+}
+```
+
+### 批量收录响应（流式Post格式）
+
+```json
+{
+  "msg_type": "post",
+  "content": {
+    "post": {
+      "zh_cn": {
+        "title": "✅ 批量收录完成（{N}份）",
+        "content": [
+          [
+            {"tag": "text", "text": "📄 {emoji1} {标题1}", "style": {"bold": true}}
+          ],
+          [
+            {"tag": "text", "text": "   💡 {亮点1}"}
+          ],
+          [
+            {"tag": "a", "text": "   🔗 查看", "href": "{链接1}"}
+          ],
+          [{"tag": "text", "text": ""}],
+          [
+            {"tag": "text", "text": "📄 {emoji2} {标题2}", "style": {"bold": true}}
+          ],
+          [
+            {"tag": "text", "text": "   💡 {亮点2}"}
+          ],
+          [
+            {"tag": "a", "text": "   🔗 查看", "href": "{链接2}"}
+          ]
+        ]
+      }
+    }
+  }
+}
+```
+
+**输出原则：**
+1. **必须流式Post格式** - 使用 msg_type: post
+2. **只包含3个核心要素：**
+   - 文件名称（📄 Emoji + 标题 + 日期）
+   - 文档亮点（💡 3-5条核心要点）
+   - 飞书链接（🔗 点击查看）
+3. **不输出其他信息** - 不显示分类、不显示表格更新、不显示统计
+4. **保持简洁** - 每份文档3-5行内容
+
+## Best Practices
+
+1. **Always verify content was fetched correctly** before creating documents
+2. **Extract key insights** from the content for the summary
+3. **Use appropriate category** based on content nature
+4. **Generate relevant keywords** for better searchability
+5. **Keep source attribution** clear for copyright respect
+6. **Handle partial failures gracefully** - document what succeeded and what failed
+7. **Update index document** - Every new document must be added to the index
+8. **Follow naming convention** - Use [Emoji] [Title] | [Date] format
+9. **Store in correct directory** - Use wiki_node to place in right category
+
+## 收录完成检查清单 (Checklist)
+
+每次收录必须完成以下所有步骤：
+
+- [ ] **执行权限预检**（验证 OAuth 及 Space/Table 写入权限）
+- [ ] 获取并处理原始内容（含图片）
+- [ ] 智能分类并确定 Emoji 前缀
+- [ ] 提取核心要点（3-5条）
+- [ ] 生成关键词
+- [ ] **创建飞书文档**（使用标准模板，指定 wiki_node）
+- [ ] **更新多维表格**（添加完整记录，包含**原链接**字段）
+- [ ] **更新文档索引**（在素材索引中添加条目）
+- [ ] 发送收录完成通知给用户
+
+**任何一步未完成，视为收录失败！**
+
+## Integration with Memory
+
+After each collection, update MEMORY.md:
+
+```markdown
+### YYYY-MM-DD - Content Collection
+- **新增收录**: [Title]
+- **来源**: [Source]
+- **分类**: [Category]
+- **知识库状态**: 共[N]条记录
+- **索引更新**: ✅ 已更新
+```
+
+This skill is part of the core knowledge management system. Execute with care and attention to detail.
+
+---
+
+## 附录：图片处理解决方案
+
+### 问题
+原始网页中的图片无法直接显示在飞书文档中（外链限制）
+
+### 解决方案
+
+#### 方案1：自动下载上传（推荐）
+
+**实现步骤**：
+
+```python
+import re
+import requests
+import os
+
+def process_images_in_content(markdown_content):
+    """
+    处理 Markdown 内容中的图片：
+    1. 提取图片URL
+    2. 下载到本地
+    3. 上传到飞书
+    4. 替换为飞书图片链接
+    """
+    
+    # 正则匹配 Markdown 图片: ![alt](url)
+    img_pattern = r'!\[(.*?)\]\((https?://[^\)]+)\)'
+    
+    def replace_image(match):
+        alt_text = match.group(1)
+        img_url = match.group(2)
+        
+        try:
+            # 1. 下载图片
+            local_path = f"/tmp/img_{abs(hash(img_url)) % 100000}.jpg"
+            
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+            }
+            response = requests.get(img_url, headers=headers, timeout=30)
+            response.raise_for_status()
+            
+            with open(local_path, 'wb') as f:
+                f.write(response.content)
+            
+            # 2. 上传到飞书
+            upload_result = feishu_im_bot_upload(
+                action="upload_image",
+                file_path=local_path
+            )
+            
+            image_key = upload_result.get("image_key")
+            
+            # 3. 清理临时文件
+            os.remove(local_path)
+            
+            # 4. 返回飞书图片格式
+            if image_key:
+                return f"![{alt_text}]({image_key})"
+            else:
+                # 上传失败，保留原链接并添加警告
+                return f"![{alt_text}]({img_url})\n\n> ⚠️ 图片上传失败，已保留原链接: {img_url}"
+                
+        except Exception as e:
+            # 处理失败，保留原链接
+            return f"![{alt_text}]({img_url})\n\n> ⚠️ 图片处理失败: {str(e)[:50]}"
+    
+    # 执行替换
+    processed_content = re.sub(img_pattern, replace_image, markdown_content)
+    
+    return processed_content
+```
+
+**使用方式**：
+在创建文档之前调用：
+```python
+# 获取原始内容
+raw_content = kimi_fetch(url=link)
+
+# 处理图片
+processed_content = process_images_in_content(raw_content)
+
+# 创建文档（使用处理后的内容）
+feishu_create_doc(
+    title=title,
+    markdown=processed_content
+)
+```
+
+#### 方案2：保留原链接 + 备用方案
+
+```python
+def add_image_fallback_notice(markdown_content, original_url):
+    """
+    在文档末尾添加图片查看说明
+    """
+    notice = f"""
+
+---
+
+## 📎 原始图片资源
+
+本文档中的图片已保留原始链接。
+如图片无法显示，请查看原文：
+[{original_url}]({original_url})
+
+"""
+    return markdown_content + notice
+```
+
+#### 方案3：批量图片归档
+
+创建一个独立的「图片资源库」多维表格：
+
+```python
+# 收录时同时记录图片信息
+feishu_bitable_app_table_record(
+    action="create",
+    app_token="图片资源库_token",
+    fields={
+        "文档标题": doc_title,
+        "图片URL": img_url,
+        "图片描述": alt_text,
+        "原文链接": original_url,
+        "收录状态": "待上传/已上传/失败"
+    }
+)
+```
+
+### 建议实施顺序
+
+1. **短期**（立即）：使用方案2，保留原链接并添加查看提示
+2. **中期**（本周）：实施方案1，自动下载上传核心文章的图片
+3. **长期**（可选）：建立独立的图片资源库管理系统
+
+### 注意事项
+
+1. **图片大小限制**：飞书图片上传通常限制 10MB
+2. **格式支持**：JPG、PNG、GIF 等常见格式
+3. **网络超时**：下载图片时设置合理的超时时间（30秒）
+4. **失败处理**：单张图片失败不应影响整篇文档收录
+5. **版权注意**：确保有权限使用原网页中的图片
+
+---
+
+*图片处理方案 v1.0 - 2026-03-05*
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn7fnbpdh1f84y30j2c75qb6pn81z8ah",
+  "slug": "content-collector-skill",
+  "version": "0.1.0",
+  "publishedAt": 1773042083338
+}
@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "daily-stock-analysis",
+  "installedVersion": "1.0.2",
+  "installedAt": 1773406361271
+}
@@ -0,0 +1,138 @@
+---
+name: daily-stock-analysis
+description: Deterministic daily stock analysis skill for global equities. Use when users need daily analysis, next-trading-day close prediction, prior forecast review, rolling accuracy, and reliable markdown report output.
+---
+
+# Daily Stock Analysis
+
+Perform market-aware, evidence-based daily stock analysis with prediction, next-run review, rolling accuracy tracking, and a structured self-evolution mechanism that updates future assumptions from observed forecast errors.
+
+## Hard Rules
+
+1. Read and write files only under `working_directory`.
+2. Save new reports only to:
+
+- `<working_directory>/daily-stock-analysis/reports/`
+
+3. Use filename:
+
+- `YYYY-MM-DD-<TICKER>-analysis.md`
+
+4. If same ticker/day file exists, ask user:
+
+- `overwrite` or `new_version` (`-v2`, `-v3`, ...)
+- For unattended runs, default to `new_version`
+
+5. Always review history before new prediction.
+6. Limit history read count to control token usage:
+
+- Script mode: max 5 files (default)
+- Compatibility mode: max 3 files
+
+## Required Scripts (Use First)
+
+1. Plan output path + collect history:
+
+```bash
+python3 {baseDir}/scripts/report_manager.py plan \
+  --workdir <working_directory> \
+  --ticker <TICKER> \
+  --run-date <YYYY-MM-DD> \
+  --versioning auto \
+  --history-limit 5
+```
+
+2. Compute rolling accuracy from existing reports:
+
+```bash
+python3 {baseDir}/scripts/calc_accuracy.py \
+  --workdir <working_directory> \
+  --ticker <TICKER> \
+  --windows 1,3,7,30 \
+  --history-limit 60
+```
+
+3. Optional: migrate legacy files after explicit user confirmation:
+
+```bash
+python3 {baseDir}/scripts/report_manager.py migrate \
+  --workdir <working_directory> \
+  --file <ABS_PATH_1> --file <ABS_PATH_2>
+```
+
+## Compatibility Mode (No Python / Small Model)
+
+If Python scripts are unavailable or model capability is limited, switch to minimal mode:
+
+1. Read at most 3 recent reports for the same ticker.
+2. Use only a minimal source set:
+
+- one official disclosure source
+- one reliable market data source (Yahoo Finance acceptable)
+
+3. Output concise result only:
+
+- recommendation
+- `pred_close_t1`
+- prior review (`prev_pred_close_t1`, `prev_actual_close_t1`, `AE`, `APE`) if available
+- one `improvement_action`
+
+4. Save report with same filename rules in canonical reports directory.
+
+See `references/minimal_mode.md`.
+
+## Minimal Run Protocol
+
+1. Resolve ticker/exchange/market (ask if ambiguous).
+2. Run `report_manager.py plan`.
+3. Read `history_files` returned by script.
+4. If `legacy_files` exist, list all absolute paths and ask whether to migrate.
+5. Gather data using `references/sources.md` + `references/search_queries.md`.
+6. Run `calc_accuracy.py` for consistent metrics.
+7. Render report using `references/report_template.md`.
+8. Save to `selected_output_file` returned by `report_manager.py`.
+
+## Required Output Fields
+
+Must include:
+
+- `recommendation`
+- `pred_close_t1`
+- `prev_pred_close_t1`
+- `prev_actual_close_t1`
+- `AE`, `APE`
+- rolling strict/loose accuracy fields
+- `improvement_actions`
+
+## Self-Improvement (Required)
+
+Each run must include 1-3 concrete `improvement_actions` from recent misses and use them in the next run.
+Do not skip this step.
+
+## Scheduling Recommendation
+
+Recommend users set this as a weekday recurring task (for example 10:00 local time) to keep prediction-review windows continuous.
+
+## References
+
+Default:
+
+- `references/workflow.md`
+- `references/report_template.md`
+- `references/metrics.md`
+- `references/search_queries.md`
+- `references/sources.md`
+- `references/minimal_mode.md`
+- `references/security.md`
+
+Deep-dive only (`full_report` mode):
+
+- `references/fundamental-analysis.md`
+- `references/technical-analysis.md`
+- `references/financial-metrics.md`
+
+## Compliance
+
+Always append:
+
+"This content is for research and informational purposes only and does not constitute investment advice or a return guarantee. Markets are risky; invest with caution."
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn7arpc65p9wdnhbw70435rrf181jvtk",
+  "slug": "daily-stock-analysis",
+  "version": "1.0.2",
+  "publishedAt": 1772265206033
+}
@@ -0,0 +1,94 @@
+# Financial Metrics Reference
+
+Use these formulas and interpretations consistently. Metric availability may differ across US/CN/HK data providers.
+
+## 1. Profitability
+
+1. Gross Margin
+- Formula: `(Revenue - COGS) / Revenue * 100%`
+- Use: Pricing power and production efficiency.
+
+2. Operating Margin
+- Formula: `Operating Income / Revenue * 100%`
+- Use: Core operating efficiency.
+
+3. Net Margin
+- Formula: `Net Income / Revenue * 100%`
+- Use: End-to-end profitability quality.
+
+4. ROE
+- Formula: `Net Income / Average Equity * 100%`
+- Use: Equity capital efficiency.
+
+5. ROIC
+- Formula: `NOPAT / Invested Capital * 100%`
+- Use: Capital allocation quality across debt and equity.
+
+## 2. Growth
+
+1. Revenue Growth (YoY / QoQ)
+- Formula: `(Current Revenue - Prior Revenue) / Prior Revenue * 100%`
+
+2. EPS Growth
+- Formula: `(Current EPS - Prior EPS) / Prior EPS * 100%`
+
+3. Multi-year CAGR
+- Formula: `(Ending / Beginning)^(1/Years) - 1`
+
+## 3. Valuation
+
+1. P/E (Trailing / Forward)
+- Formula: `Price / EPS`
+
+2. PEG
+- Formula: `P/E / Earnings Growth Rate`
+
+3. P/B
+- Formula: `Price / Book Value Per Share`
+
+4. P/S
+- Formula: `Market Cap / Revenue`
+
+5. EV
+- Formula: `Market Cap + Total Debt - Cash`
+
+6. EV/EBITDA
+- Formula: `EV / EBITDA`
+
+7. EV/Sales
+- Formula: `EV / Revenue`
+
+## 4. Leverage and Liquidity
+
+1. Debt-to-Equity
+- Formula: `Total Debt / Total Equity`
+
+2. Interest Coverage
+- Formula: `EBIT / Interest Expense`
+
+3. Current Ratio
+- Formula: `Current Assets / Current Liabilities`
+
+4. Quick Ratio
+- Formula: `(Current Assets - Inventory) / Current Liabilities`
+
+## 5. Cash Flow Quality
+
+1. Free Cash Flow (FCF)
+- Formula: `Operating Cash Flow - Capital Expenditures`
+
+2. FCF Yield
+- Formula: `FCF Per Share / Price * 100%`
+
+3. Cash Conversion
+- Formula: `FCF / Net Income`
+
+## 6. Interpretation Guidance
+
+1. Always compare metrics against:
+- Company historical range
+- Sector and direct peers
+- Current macro regime
+
+2. Avoid single-metric conclusions.
+3. Flag where accounting standards or reporting cadence reduce cross-market comparability.
@@ -0,0 +1,75 @@
+# Fundamental Analysis Reference
+
+Use this framework in both `daily` and `full_report` modes. Keep outputs concise unless full report is requested.
+
+## 1. Business Quality
+
+Assess:
+
+1. Moat quality:
+- Brand, network effects, switching costs, cost advantage, IP/regulatory barriers.
+
+2. Management quality:
+- Capital allocation discipline, communication quality, execution consistency.
+
+3. Business model durability:
+- Revenue concentration, customer concentration, geographic risk, pricing power.
+
+## 2. Financial Health
+
+Focus areas:
+
+1. Profitability trend:
+- Gross, operating, net margin direction.
+
+2. Growth quality:
+- Revenue and earnings growth consistency, segment contribution quality.
+
+3. Balance sheet:
+- Debt burden, liquidity, refinancing risk, cash buffer.
+
+4. Cash flow quality:
+- OCF consistency, FCF conversion, capex intensity.
+
+## 3. Valuation Lens
+
+Use multiple perspectives:
+
+1. Relative multiples:
+- P/E, PEG, P/B, P/S, EV/EBITDA, EV/Sales.
+
+2. Historical range context:
+- Current valuation vs own history.
+
+3. Peer context:
+- Premium/discount vs direct peers and rationale.
+
+## 4. Risk Framework
+
+Map risks by category:
+
+1. Company-specific:
+- Product concentration, customer concentration, execution risk, governance issues.
+
+2. Market/macro:
+- Rate sensitivity, FX exposure, commodity sensitivity, policy risk.
+
+3. Event risk:
+- Earnings, regulatory approvals, legal actions, financing events.
+
+## 5. Market-Specific Notes (US/CN/HK)
+
+1. Data depth may vary by market and language.
+2. Prefer exchange filings and official disclosure portals in each market.
+3. Align accounting period labels and fiscal calendars before comparison.
+4. Flag where metric comparability is limited.
+
+## 6. Output Guidance
+
+For daily mode, include:
+
+- 2-3 key fundamental drivers
+- 1-2 valuation signals
+- top downside risks
+
+For full report mode, include full multi-year trend tables and peer comparison.
@@ -0,0 +1,99 @@
+# Metrics Definition
+
+Use these definitions consistently across all reports.
+
+## 1. Core Error Metrics
+
+Let:
+
+- `pred` = predicted close for target session
+- `actual` = official actual close for that session
+
+Compute:
+
+- Absolute Error (AE): `|pred - actual|`
+- Absolute Percentage Error (APE): `|pred - actual| / actual * 100%`
+
+## 2. Hit Criteria
+
+Report two hit criteria in parallel:
+
+- Strict hit: `APE <= 1%`
+- Loose hit: `APE <= 2%`
+
+These thresholds are the default correctness criteria for predicted close price.
+
+## 3. Rolling Accuracy Windows
+
+For each window `W` (1d, 3d, 7d, 30d, custom):
+
+- `strict_accuracy_W = strict_hits_W / n_W`
+- `loose_accuracy_W = loose_hits_W / n_W`
+
+Where `n_W` is number of valid forecast/actual pairs in that window.
+
+## 4. Optional Direction Accuracy
+
+Let direction be sign of close-to-close return.
+
+- Direction hit if predicted direction equals realized direction.
+- `direction_accuracy_W = direction_hits_W / n_W`
+
+Use only when direction labels are explicitly available.
+
+## 5. Forecast Correctness Score (Optional)
+
+For a single forecast, you may map APE to a score:
+
+- `correctness_score = max(0, 100 - 50 * APE_percent)`
+
+Examples:
+
+- `APE = 0.8%` -> score `60`
+- `APE = 1.5%` -> score `25`
+- `APE >= 2.0%` -> score `0` (or near 0)
+
+## 6. Sample Size and Insufficient Data Rules
+
+1. Never pad missing samples.
+2. If `n_W = 0`, output `N/A` for the window.
+3. If `0 < n_W < target_window_size`, output partial result and annotate as partial.
+4. Always display `n_W` beside each window metric.
+
+## 7. Adjustment and Comparability Rules
+
+1. Prefer adjusted price series when corporate actions materially affect comparability.
+2. If non-adjusted close is used, state it explicitly.
+3. Keep forecast and actual on the same price basis.
+
+## 8. Improvement Trend Metrics
+
+Track whether forecast quality is improving over time:
+
+1. `delta_APE_7d_vs_prev7d`
+- Difference between current 7-day average APE and previous 7-day average APE.
+
+2. `delta_strict_hit_rate_7d`
+- Change in strict hit rate versus previous 7-day block.
+
+3. `trend_label`
+- `improving`, `stable`, or `degrading` based on combined delta signals.
+
+## 9. Reporting Format (Minimum)
+
+Every report should include:
+
+1. Prior-session review row:
+- `prev_pred_close_t1`, `prev_actual_close_t1`, `AE`, `APE`, strict/loose hit status
+
+2. Rolling table with at least:
+- 1d, 3d, 7d, 30d, optional custom
+- strict accuracy, loose accuracy, optional direction accuracy
+- sample size `n`
+
+3. One-line interpretation:
+- whether model performance is improving, stable, or degrading
+
+4. Improvement block:
+- what changed from review
+- what will be adjusted in next run
@@ -0,0 +1,33 @@
+# Minimal Compatibility Mode
+
+Use this mode when Python scripts are unavailable or model capability is limited.
+
+## Goal
+
+Maximize success rate and correctness with minimal token and logic complexity.
+
+## Rules
+
+1. Read at most 3 recent reports for the same ticker.
+2. Use minimal sources:
+- one official disclosure source
+- one reliable market data source (Yahoo Finance acceptable)
+3. Keep output short and deterministic.
+4. Still include one self-improvement action from prior misses.
+
+## Minimal Output Schema
+
+- `recommendation`: Buy/Hold/Sell/Watch
+- `pred_close_t1`: point estimate
+- `prev_pred_close_t1`: if available, else `N/A`
+- `prev_actual_close_t1`: if available, else `N/A/pending`
+- `AE`, `APE`: if available, else `N/A`
+- `improvement_actions`: exactly 1 item
+- `status`: `ok|pending_data|blocked`
+
+## Minimal Source Checklist
+
+1. Official disclosure page (exchange/regulator/IR)
+2. Market quote page (for example Yahoo Finance quote)
+
+If the two sources conflict on critical values, set confidence to `Low`.
@@ -0,0 +1,99 @@
+# Report Template (Strict)
+
+Use this template exactly. Keep key names unchanged for downstream parsing.
+
+```markdown
+---
+version: 1
+run_date: <YYYY-MM-DD>
+run_time_local: <YYYY-MM-DD HH:mm TZ>
+mode: <daily|daily_minimal|full_report>
+ticker: <TICKER>
+exchange: <EXCHANGE>
+market: <TEXT>
+report_dir: <working_directory>/daily-stock-analysis/reports/
+output_file: <YYYY-MM-DD-TICKER-analysis.md or -vN.md>
+report_versioning_mode: <overwrite|new_version>
+history_window_days: <N>
+
+recommendation: <Buy|Hold|Sell|Watch>
+recommendation_triggers: <ENTRY/EXIT/INVALIDATION SUMMARY>
+
+pred_close_t1: <NUMBER>
+pred_range_t1: <LOW-HIGH or N/A>
+pred_confidence: <High|Medium|Low>
+pred_assumptions: <SHORT TEXT>
+
+prev_pred_close_t1: <NUMBER or N/A>
+prev_actual_close_t1: <NUMBER or pending or N/A>
+AE: <NUMBER or N/A>
+APE: <PERCENT or N/A>
+strict_hit: <true|false|N/A>
+loose_hit: <true|false|N/A>
+
+acc_1d_strict: <PERCENT or N/A>
+acc_1d_loose: <PERCENT or N/A>
+acc_3d_strict: <PERCENT or N/A>
+acc_3d_loose: <PERCENT or N/A>
+acc_7d_strict: <PERCENT or N/A>
+acc_7d_loose: <PERCENT or N/A>
+acc_30d_strict: <PERCENT or N/A>
+acc_30d_loose: <PERCENT or N/A>
+acc_custom_strict: <PERCENT or N/A>
+acc_custom_loose: <PERCENT or N/A>
+
+improvement_actions:
+  - <ACTION_1>
+  - <ACTION_2 or N/A>
+  - <ACTION_3 or N/A>
+status: <ok|pending_data|blocked>
+status_note: <SHORT TEXT>
+---
+
+# Daily Stock Analysis - <TICKER> (<EXCHANGE>)
+
+## 1) Market Snapshot
+- Last/Close: <VALUE>
+- Session Range: <LOW-HIGH>
+- Volume/Volatility: <SUMMARY>
+- Thesis: <BULLISH/NEUTRAL/BEARISH + concise rationale>
+
+## 2) Recommendation
+- Recommendation: <Buy/Hold/Sell/Watch>
+- Trigger Conditions: <ENTRY/EXIT/INVALIDATION>
+- Risk Controls: <SHORT TEXT>
+
+## 3) Next Trading Day Prediction
+- Point Forecast: <pred_close_t1>
+- Range: <pred_range_t1>
+- Confidence: <pred_confidence>
+- Assumptions: <pred_assumptions>
+
+## 4) Prior Forecast Review
+- Previous Forecast: <prev_pred_close_t1>
+- Actual Close: <prev_actual_close_t1>
+- AE / APE: <AE> / <APE>
+- Attribution: <WHY HIT OR MISS>
+
+## 5) Rolling Accuracy
+| Window | Strict | Loose |
+|---|---:|---:|
+| 1d | <acc_1d_strict> | <acc_1d_loose> |
+| 3d | <acc_3d_strict> | <acc_3d_loose> |
+| 7d | <acc_7d_strict> | <acc_7d_loose> |
+| 30d | <acc_30d_strict> | <acc_30d_loose> |
+| Custom | <acc_custom_strict> | <acc_custom_loose> |
+
+## 6) Self-Improvement Actions for Next Run
+1. <ACTION_1>
+2. <ACTION_2 or N/A>
+3. <ACTION_3 or N/A>
+
+## 7) Sources (with timestamp)
+- <SOURCE_1>
+- <SOURCE_2>
+- <SOURCE_3>
+
+## 8) Disclaimer
+This content is for research and informational purposes only and does not constitute investment advice or a return guarantee. Markets are risky; invest with caution.
+```
@@ -0,0 +1,48 @@
+# Search Query Templates (Concise)
+
+Use these templates with search engines and `site:` filters.
+
+Detailed source list is in `references/sources.md`.
+
+## 1) Identity and Listing
+
+- `<COMPANY> ticker symbol exchange`
+- `<TICKER> exchange listing market`
+
+## 2) Official Filings and Disclosures
+
+- `<TICKER> official filings latest`
+- `<COMPANY> investor relations latest release`
+- `site:sec.gov <TICKER> 10-Q OR 10-K OR 8-K`
+- `site:hkexnews.hk <TICKER> announcement`
+- `site:sse.com.cn <TICKER> 公告`
+- `site:szse.cn <TICKER> 公告`
+
+## 3) Market Data and Price Context
+
+- `site:finance.yahoo.com <TICKER> quote`
+- `<TICKER> latest close open high low volume`
+- `<TICKER> 52 week range market cap`
+
+## 4) News and Analyst Context
+
+- `site:reuters.com <TICKER> earnings guidance`
+- `site:bloomberg.com <TICKER> stock news`
+- `<TICKER> analyst rating target price`
+
+## 5) Technical Context
+
+- `<TICKER> RSI MACD moving average`
+- `<TICKER> support resistance trend`
+
+## 6) Macro Context (if used in thesis)
+
+- `<MARKET> benchmark index today`
+- `<MARKET> central bank policy rate outlook`
+- `US 10Y yield today`
+
+## Data Quality Rules
+
+1. Prefer Tier-1 official sources first.
+2. Cross-check critical values with two independent sources.
+3. Record source URL and timestamp in report.
@@ -0,0 +1,27 @@
+# Security and Privacy Rules
+
+These rules are mandatory for both script mode and compatibility mode.
+
+## Scope Control
+
+1. Operate only under `working_directory`.
+2. Do not read, move, or write files outside `working_directory`.
+3. Do not follow symlinks when scanning report files.
+
+## Data Minimization
+
+1. Read only report files matching:
+- `YYYY-MM-DD-<TICKER>-analysis.md`
+- `YYYY-MM-DD-<TICKER>-analysis-vN.md`
+2. Parse only required metadata fields.
+3. Cap historical reads:
+- script mode default: 5 files
+- compatibility mode: 3 files
+
+## Script Safety
+
+1. Scripts are local-file utilities only; no network calls.
+2. Migration is explicit and non-destructive:
+- move only user-confirmed files
+- skip when target already exists
+3. If a safety check fails, return `blocked` with reason.
@@ -0,0 +1,104 @@
+# Authoritative Information Sources
+
+Use search engines with `site:` filters to prioritize authoritative sources.
+
+## Source Priority
+
+1. Tier 1 (Primary / official)
+- Exchange and regulator disclosures
+- Company investor-relations pages
+- Official macro data publishers
+
+2. Tier 2 (High-quality financial media/data)
+- Yahoo Finance, Reuters, Bloomberg, WSJ, CNBC, MarketWatch
+
+3. Tier 3 (Supporting context)
+- TradingView, StockCharts, sector/ETF summaries
+
+For critical values (close price, earnings, guidance, major filings), cross-check with at least two independent sources.
+
+## Tier 1: Exchange and Regulatory Sources
+
+### Global baseline
+- Company Investor Relations pages
+- Official exchange announcements for the ticker listing venue
+
+### United States
+- SEC EDGAR: [https://www.sec.gov/edgar/searchedgar/companysearch](https://www.sec.gov/edgar/searchedgar/companysearch)
+- Nasdaq company pages: [https://www.nasdaq.com](https://www.nasdaq.com)
+- NYSE company pages: [https://www.nyse.com](https://www.nyse.com)
+
+### Hong Kong
+- HKEXnews: [https://www.hkexnews.hk](https://www.hkexnews.hk)
+
+### Mainland China
+- SSE disclosures: [https://www.sse.com.cn/disclosure/](https://www.sse.com.cn/disclosure/)
+- SZSE disclosures: [https://www.szse.cn/disclosure/](https://www.szse.cn/disclosure/)
+
+### Japan
+- JPX: [https://www.jpx.co.jp/english/](https://www.jpx.co.jp/english/)
+- TDnet (Timely Disclosure): [https://www.release.tdnet.info/](https://www.release.tdnet.info/)
+
+### United Kingdom
+- London Stock Exchange RNS: [https://www.londonstockexchange.com/news](https://www.londonstockexchange.com/news)
+
+### Europe (multi-country)
+- Euronext news/disclosures: [https://live.euronext.com/en/markets](https://live.euronext.com/en/markets)
+
+## Tier 2: High-Quality Financial Data and News
+
+- Yahoo Finance: [https://finance.yahoo.com](https://finance.yahoo.com)
+- Reuters Markets: [https://www.reuters.com/markets/](https://www.reuters.com/markets/)
+- Bloomberg Markets: [https://www.bloomberg.com/markets](https://www.bloomberg.com/markets)
+- WSJ Markets: [https://www.wsj.com/market-data](https://www.wsj.com/market-data)
+- CNBC Markets: [https://www.cnbc.com/markets/](https://www.cnbc.com/markets/)
+- MarketWatch: [https://www.marketwatch.com](https://www.marketwatch.com)
+- Morningstar (supporting valuation context): [https://www.morningstar.com](https://www.morningstar.com)
+
+## Tier 1 Macro Data (for market regime context)
+
+### United States
+- U.S. Treasury rates: [https://home.treasury.gov](https://home.treasury.gov)
+- Federal Reserve (FRED): [https://fred.stlouisfed.org](https://fred.stlouisfed.org)
+- BLS: [https://www.bls.gov](https://www.bls.gov)
+- BEA: [https://www.bea.gov](https://www.bea.gov)
+
+### Global
+- IMF Data: [https://www.imf.org/en/Data](https://www.imf.org/en/Data)
+- World Bank Data: [https://data.worldbank.org](https://data.worldbank.org)
+- ECB: [https://www.ecb.europa.eu](https://www.ecb.europa.eu)
+- BoE: [https://www.bankofengland.co.uk](https://www.bankofengland.co.uk)
+- BoJ: [https://www.boj.or.jp/en/](https://www.boj.or.jp/en/)
+
+## Technical/Charting Support (Tier 3)
+
+- TradingView: [https://www.tradingview.com](https://www.tradingview.com)
+- StockCharts: [https://stockcharts.com](https://stockcharts.com)
+
+## Search Engine Patterns
+
+Use search engines with domain filters:
+
+- `site:finance.yahoo.com <TICKER> quote`
+- `site:reuters.com <TICKER> earnings`
+- `site:sec.gov <TICKER> 10-Q`
+- `site:hkexnews.hk <TICKER> announcement`
+- `site:sse.com.cn <TICKER> 公告`
+- `site:szse.cn <TICKER> 公告`
+- `site:investor.<company-domain> earnings release`
+
+## Minimum Source Set Per Run
+
+At least include:
+
+1. One Tier-1 disclosure source
+2. One Tier-2 market data source (Yahoo Finance is acceptable baseline)
+3. One Tier-2/Tier-1 news source
+4. One macro source if macro is cited in thesis
+
+## Compatibility Mode Minimum Source Set
+
+When running in minimal compatibility mode, use:
+
+1. One Tier-1 disclosure source
+2. One Tier-2 market data source (Yahoo Finance acceptable)
@@ -0,0 +1,77 @@
+# Technical Analysis Reference
+
+Use technical analysis as a decision support layer, not as a standalone certainty signal.
+
+## 1. Trend Framework
+
+1. Moving averages:
+- 20/50/200-period moving averages as baseline trend map.
+- Bullish regime: price above key moving averages with supportive slope.
+- Bearish regime: price below key moving averages with negative slope.
+
+2. Trend strength:
+- Confirm with higher highs/higher lows (uptrend) or lower highs/lower lows (downtrend).
+
+## 2. Momentum Framework
+
+1. RSI:
+- Overbought > 70, oversold < 30.
+- Use divergence vs price as an early warning, not a standalone trigger.
+
+2. MACD:
+- Track line/signal crossovers and histogram trend.
+- Prefer signals aligned with broader trend.
+
+## 3. Volatility and Structure
+
+1. ATR context:
+- Use ATR expansion/contraction to assess regime change risk.
+
+2. Bollinger context:
+- Squeeze can precede expansion.
+- Band walk can persist in strong trends.
+
+## 4. Support and Resistance
+
+Map levels from:
+
+- Recent swing highs/lows
+- Volume clusters
+- Moving-average confluence
+- Psychological round numbers
+
+Use level breaks with volume confirmation where possible.
+
+## 5. Volume Confirmation
+
+1. Breakout quality improves with volume expansion.
+2. Weak volume breakouts carry higher failure risk.
+3. Divergence between price trend and volume trend can signal exhaustion.
+
+## 6. Multi-Timeframe Alignment
+
+1. Use higher timeframe (weekly/daily) for primary bias.
+2. Use lower timeframe (daily/intraday where available) for timing.
+3. Do not let lower timeframe noise override higher timeframe structure without strong evidence.
+
+## 7. Signal Quality Rules
+
+1. Require at least two independent confirmations before strong directional calls.
+2. Mark low-confidence calls when indicators conflict.
+3. Define invalidation level for every directional view.
+
+## 8. Market-Specific Notes (US/CN/HK)
+
+1. Liquidity and session structure differ by market.
+2. Gap behavior and close auction effects may vary.
+3. Technical indicator reliability can degrade during event-driven sessions.
+
+## 9. Daily Output Guidance
+
+At minimum provide:
+
+- Trend state (bullish/neutral/bearish)
+- 2-3 key levels
+- RSI/MACD summary
+- volume confirmation status
+- invalidation condition
@@ -0,0 +1,104 @@
+# Workflow (Command-First)
+
+Use this sequence exactly.
+
+## 0) Choose Execution Mode
+
+Use `script` mode by default.
+
+Switch to `compatibility` mode when:
+
+- `python3` is unavailable, or
+- model capability is low and deterministic minimal output is preferred.
+
+## 1) Resolve Instrument
+
+- Resolve `ticker`, `exchange`, `market`, and next valid trading day.
+- If ticker is ambiguous, stop and ask user.
+
+## 2) Plan Files and History
+
+Run:
+
+```bash
+python3 {baseDir}/scripts/report_manager.py plan \
+  --workdir <working_directory> \
+  --ticker <TICKER> \
+  --run-date <YYYY-MM-DD> \
+  --versioning auto \
+  --history-limit 5
+```
+
+Use returned JSON fields:
+
+- `selected_output_file`
+- `requires_user_choice`
+- `history_files`
+- `legacy_files`
+
+If `requires_user_choice=true`, ask user `overwrite` vs `new_version`.
+Read only `history_files` returned by script (default max 5).
+
+## 3) Legacy Compatibility (Optional Migration)
+
+- Read legacy files from `legacy_files` for review history.
+- If user agrees to migrate, run:
+
+```bash
+python3 {baseDir}/scripts/report_manager.py migrate \
+  --workdir <working_directory> \
+  --file <ABS_PATH_1> --file <ABS_PATH_2>
+```
+
+Security: only process files under `working_directory`.
+
+## 4) Collect New Data
+
+- Use `references/sources.md` tier priority.
+- Use `references/search_queries.md` templates.
+- For critical values, cross-check with at least 2 sources.
+
+## 5) Compute Accuracy via Script
+
+Run:
+
+```bash
+python3 {baseDir}/scripts/calc_accuracy.py \
+  --workdir <working_directory> \
+  --ticker <TICKER> \
+  --windows 1,3,7,30 \
+  --history-limit 60
+```
+
+Use script output to fill rolling accuracy fields.
+
+## 6) Generate Report
+
+- Render with `references/report_template.md`.
+- Keep all required frontmatter keys.
+- Include `improvement_actions`.
+
+## 7) Persist and Return
+
+- Save to `selected_output_file` from step 2.
+- Return summary + absolute file path + pending/blocked status.
+
+## 8) Recommended Operation
+
+Use recurring weekday schedule to stabilize review windows and success rate.
+
+## Compatibility Mode (Fallback)
+
+When scripts cannot run:
+
+1. Manually locate report files only under `working_directory`.
+2. Read at most 3 recent same-ticker reports.
+3. Collect minimal sources:
+- one official disclosure source
+- one reliable market data source
+4. Produce minimal output:
+- recommendation
+- `pred_close_t1`
+- prior review metrics (if available)
+- one `improvement_action`
+5. Save report in canonical reports directory using standard filename rules.
@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+"""Shared helpers for daily-stock-analysis scripts."""
+
+from __future__ import annotations
+
+import os
+import re
+from dataclasses import dataclass
+from datetime import date
+from typing import Dict, List, Optional
+
+
+FILENAME_RE = re.compile(
+    r"^(?P<run_date>\d{4}-\d{2}-\d{2})-(?P<ticker>[A-Za-z0-9._-]+)-analysis(?:-v(?P<version>\d+))?\.md$",
+    re.IGNORECASE,
+)
+
+
+@dataclass(frozen=True)
+class ReportFile:
+    path: str
+    run_date: str
+    ticker: str
+    version: int
+    in_canonical_dir: bool
+
+
+def canonical_reports_dir(workdir: str) -> str:
+    return os.path.join(os.path.abspath(workdir), "daily-stock-analysis", "reports")
+
+
+def compatible_dirs(workdir: str) -> List[str]:
+    root = os.path.abspath(workdir)
+    return [
+        canonical_reports_dir(root),
+        os.path.join(root, "daily-stock-analysis"),
+        root,
+    ]
+
+
+def is_within_workdir(path: str, workdir: str) -> bool:
+    root = os.path.realpath(os.path.abspath(workdir))
+    target = os.path.realpath(os.path.abspath(path))
+    return target == root or target.startswith(root + os.sep)
+
+
+def parse_filename(name: str) -> Optional[Dict[str, str]]:
+    match = FILENAME_RE.match(name)
+    if not match:
+        return None
+    return {
+        "run_date": match.group("run_date"),
+        "ticker": match.group("ticker").upper(),
+        "version": str(int(match.group("version") or "1")),
+    }
+
+
+def discover_reports(workdir: str, ticker: str) -> List[ReportFile]:
+    root = os.path.abspath(workdir)
+    ticker_upper = ticker.upper()
+    canonical_dir = canonical_reports_dir(root)
+    seen = set()
+    records: List[ReportFile] = []
+
+    for directory in compatible_dirs(root):
+        if not is_within_workdir(directory, root):
+            continue
+        if not os.path.isdir(directory):
+            continue
+        for entry in os.scandir(directory):
+            # Never follow symlinks for safety/privacy.
+            if not entry.is_file(follow_symlinks=False):
+                continue
+            parsed = parse_filename(entry.name)
+            if not parsed:
+                continue
+            if parsed["ticker"] != ticker_upper:
+                continue
+            abs_path = os.path.abspath(entry.path)
+            real_path = os.path.realpath(abs_path)
+            if real_path in seen:
+                continue
+            seen.add(real_path)
+            records.append(
+                ReportFile(
+                    path=abs_path,
+                    run_date=parsed["run_date"],
+                    ticker=parsed["ticker"],
+                    version=int(parsed["version"]),
+                    in_canonical_dir=os.path.dirname(abs_path) == canonical_dir,
+                )
+            )
+
+    def sort_key(record: ReportFile):
+        try:
+            d = date.fromisoformat(record.run_date)
+        except ValueError:
+            d = date.min
+        return (d, record.version, 1 if record.in_canonical_dir else 0)
+
+    return sorted(records, key=sort_key, reverse=True)
+
+
+def read_frontmatter(path: str) -> Dict[str, str]:
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            first_line = f.readline()
+            if first_line.strip() != "---":
+                return {}
+
+            # Read only a bounded header section to avoid loading large files.
+            frontmatter: Dict[str, str] = {}
+            total_chars = len(first_line)
+            for _ in range(200):
+                line = f.readline()
+                if not line:
+                    break
+                total_chars += len(line)
+                if total_chars > 64 * 1024:
+                    break
+                raw = line.rstrip("\n")
+                if raw.strip() == "---":
+                    break
+                if not raw.strip():
+                    continue
+                if raw.startswith("  - "):
+                    continue
+                if ":" not in raw:
+                    continue
+                key, value = raw.split(":", 1)
+                frontmatter[key.strip()] = value.strip()
+            return frontmatter
+    except (OSError, UnicodeDecodeError):
+        return {}
+
+
+def parse_float(value: Optional[str]) -> Optional[float]:
+    if value is None:
+        return None
+    text = value.strip()
+    if not text:
+        return None
+    if text.upper() in {"N/A", "NA", "NONE", "NULL", "PENDING"}:
+        return None
+    text = text.replace(",", "")
+    if text.endswith("%"):
+        text = text[:-1]
+    try:
+        return float(text)
+    except ValueError:
+        return None
+
+
+def parse_bool(value: Optional[str]) -> Optional[bool]:
+    if value is None:
+        return None
+    text = value.strip().lower()
+    if text in {"true", "yes", "1"}:
+        return True
+    if text in {"false", "no", "0"}:
+        return False
+    return None
@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+"""Compute rolling forecast accuracy from existing report files."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+from statistics import mean
+from typing import Dict, List
+
+from _report_utils import discover_reports, parse_bool, parse_float, read_frontmatter
+
+
+def _window_list(text: str) -> List[int]:
+    windows = []
+    for item in text.split(","):
+        item = item.strip()
+        if not item:
+            continue
+        value = int(item)
+        if value <= 0:
+            continue
+        if value not in windows:
+            windows.append(value)
+    return windows or [1, 3, 7, 30]
+
+
+def _build_review_rows(workdir: str, ticker: str, history_limit: int) -> List[Dict[str, object]]:
+    reports = discover_reports(workdir, ticker)[:history_limit]
+    rows: List[Dict[str, object]] = []
+    seen_run_date = set()
+
+    for report in reports:
+        # Keep the newest report for each run_date to avoid same-day duplicate counting.
+        if report.run_date in seen_run_date:
+            continue
+        frontmatter = read_frontmatter(report.path)
+        ape = parse_float(frontmatter.get("APE"))
+        strict = parse_bool(frontmatter.get("strict_hit"))
+        loose = parse_bool(frontmatter.get("loose_hit"))
+
+        if strict is None and ape is not None:
+            strict = ape <= 1.0
+        if loose is None and ape is not None:
+            loose = ape <= 2.0
+
+        if ape is None and strict is None and loose is None:
+            continue
+
+        rows.append(
+            {
+                "run_date": report.run_date,
+                "path": report.path,
+                "ape": ape,
+                "strict_hit": strict,
+                "loose_hit": loose,
+            }
+        )
+        seen_run_date.add(report.run_date)
+
+    return rows
+
+
+def _rate(hit_count: int, total: int):
+    if total == 0:
+        return None
+    return round(hit_count * 100.0 / total, 2)
+
+
+def compute_accuracy(workdir: str, ticker: str, windows: List[int], history_limit: int) -> Dict[str, object]:
+    rows = _build_review_rows(workdir, ticker, history_limit)
+    metrics = {}
+
+    for window in windows:
+        sample = rows[:window]
+        n = len(sample)
+        strict_hits = sum(1 for r in sample if r["strict_hit"] is True)
+        loose_hits = sum(1 for r in sample if r["loose_hit"] is True)
+        ape_values = [r["ape"] for r in sample if isinstance(r["ape"], float)]
+        metrics[str(window)] = {
+            "n": n,
+            "strict_rate_percent": _rate(strict_hits, n),
+            "loose_rate_percent": _rate(loose_hits, n),
+            "avg_ape_percent": round(mean(ape_values), 4) if ape_values else None,
+        }
+
+    latest = rows[0] if rows else None
+    return {
+        "ticker": ticker.upper(),
+        "workdir": os.path.abspath(workdir),
+        "windows": metrics,
+        "review_samples": len(rows),
+        "latest_review": latest,
+        "status": "ok" if rows else "insufficient_history",
+        "security_scope": "working_directory_only",
+    }
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Calculate rolling forecast accuracy.")
+    parser.add_argument("--workdir", default=os.getcwd())
+    parser.add_argument("--ticker", required=True)
+    parser.add_argument("--windows", default="1,3,7,30")
+    parser.add_argument("--history-limit", type=int, default=60)
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = _parse_args()
+    result = compute_accuracy(
+        workdir=args.workdir,
+        ticker=args.ticker,
+        windows=_window_list(args.windows),
+        history_limit=max(args.history_limit, 1),
+    )
+    print(json.dumps(result, indent=2, ensure_ascii=True))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
@@ -0,0 +1,189 @@
+#!/usr/bin/env python3
+"""Deterministic report path and migration manager for daily-stock-analysis."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import shutil
+from datetime import date
+from typing import Dict, List
+
+from _report_utils import (
+    FILENAME_RE,
+    canonical_reports_dir,
+    discover_reports,
+    is_within_workdir,
+)
+
+
+def _same_day_versions_in_canonical(
+    reports: List, reports_dir: str, run_date: str, ticker_upper: str
+) -> List[int]:
+    versions = []
+    for report in reports:
+        if report.run_date != run_date:
+            continue
+        if report.ticker != ticker_upper:
+            continue
+        if os.path.dirname(report.path) != reports_dir:
+            continue
+        versions.append(report.version)
+    return versions
+
+
+def plan_output(
+    workdir: str,
+    ticker: str,
+    run_date: str,
+    versioning: str,
+    unattended: bool,
+    history_limit: int,
+) -> Dict[str, object]:
+    root = os.path.abspath(workdir)
+    ticker_upper = ticker.upper()
+    reports_dir = canonical_reports_dir(root)
+    os.makedirs(reports_dir, exist_ok=True)
+
+    reports = discover_reports(root, ticker_upper)
+    history_files = [r.path for r in reports[:history_limit]]
+    legacy_files = [r.path for r in reports if not r.in_canonical_dir]
+
+    base_name = f"{run_date}-{ticker_upper}-analysis.md"
+    base_path = os.path.join(reports_dir, base_name)
+    base_exists = os.path.exists(base_path)
+
+    requires_user_choice = False
+    selected_mode = "new_file"
+    selected_path = base_path
+
+    if base_exists:
+        if versioning == "overwrite":
+            selected_mode = "overwrite"
+        elif versioning == "new_version":
+            selected_mode = "new_version"
+        else:
+            if unattended:
+                selected_mode = "new_version"
+            else:
+                selected_mode = "new_version"
+                requires_user_choice = True
+
+    if selected_mode == "new_version":
+        versions = _same_day_versions_in_canonical(
+            reports, reports_dir, run_date, ticker_upper
+        )
+        next_version = max(versions or [1]) + 1
+        selected_path = os.path.join(
+            reports_dir, f"{run_date}-{ticker_upper}-analysis-v{next_version}.md"
+        )
+
+    return {
+        "ticker": ticker_upper,
+        "workdir": root,
+        "reports_dir": reports_dir,
+        "base_output_file": base_path,
+        "selected_output_file": selected_path,
+        "selected_versioning_mode": selected_mode,
+        "requires_user_choice": requires_user_choice,
+        "history_files": history_files,
+        "legacy_files": legacy_files,
+        "history_limit": history_limit,
+        "security_scope": "working_directory_only",
+    }
+
+
+def migrate_files(workdir: str, files: List[str]) -> Dict[str, object]:
+    root = os.path.abspath(workdir)
+    reports_dir = canonical_reports_dir(root)
+    os.makedirs(reports_dir, exist_ok=True)
+
+    moved = []
+    skipped = []
+
+    for raw_path in files:
+        src = os.path.abspath(raw_path)
+        if not is_within_workdir(src, root):
+            skipped.append({"file": src, "reason": "outside_workdir"})
+            continue
+        if not os.path.isfile(src):
+            skipped.append({"file": src, "reason": "not_file"})
+            continue
+        if os.path.islink(src):
+            skipped.append({"file": src, "reason": "symlink_not_allowed"})
+            continue
+        if not FILENAME_RE.match(os.path.basename(src)):
+            skipped.append({"file": src, "reason": "filename_not_supported"})
+            continue
+
+        dst = os.path.join(reports_dir, os.path.basename(src))
+        if os.path.abspath(src) == os.path.abspath(dst):
+            skipped.append({"file": src, "reason": "already_in_reports_dir"})
+            continue
+
+        if os.path.exists(dst):
+            # Keep migration deterministic and non-destructive.
+            skipped.append({"file": src, "reason": "target_exists"})
+            continue
+
+        try:
+            shutil.move(src, dst)
+        except OSError as exc:
+            skipped.append({"file": src, "reason": f"move_failed:{exc}"})
+            continue
+
+        moved.append({"from": src, "to": dst})
+
+    return {
+        "reports_dir": reports_dir,
+        "moved": moved,
+        "skipped": skipped,
+        "security_scope": "working_directory_only",
+    }
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Manage report paths and migrations.")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    plan_parser = subparsers.add_parser("plan", help="Plan output path and history usage.")
+    plan_parser.add_argument("--workdir", default=os.getcwd())
+    plan_parser.add_argument("--ticker", required=True)
+    plan_parser.add_argument("--run-date", default=date.today().isoformat())
+    plan_parser.add_argument(
+        "--versioning",
+        choices=["auto", "overwrite", "new_version"],
+        default="auto",
+    )
+    plan_parser.add_argument("--unattended", action="store_true")
+    plan_parser.add_argument("--history-limit", type=int, default=5)
+
+    migrate_parser = subparsers.add_parser(
+        "migrate", help="Move legacy report files into canonical reports directory."
+    )
+    migrate_parser.add_argument("--workdir", default=os.getcwd())
+    migrate_parser.add_argument("--file", action="append", required=True)
+
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = _parse_args()
+    if args.command == "plan":
+        result = plan_output(
+            workdir=args.workdir,
+            ticker=args.ticker,
+            run_date=args.run_date,
+            versioning=args.versioning,
+            unattended=args.unattended,
+            history_limit=max(args.history_limit, 1),
+        )
+    else:
+        result = migrate_files(workdir=args.workdir, files=args.file)
+    print(json.dumps(result, indent=2, ensure_ascii=True))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "proactive-agent-lite",
+  "installedVersion": "1.0.0",
+  "installedAt": 1773644526594
+}
@@ -0,0 +1,66 @@
+# Proactive Agent Lite
+
+Transform your AI agents from passive responders into proactive partners that anticipate needs and continuously improve.
+
+## Overview
+
+Proactive Agent Lite implements battle-tested patterns that enable AI agents to:
+- Learn from every interaction
+- Create value without being asked
+- Stay aligned with their mission
+- Self-diagnose and fix issues
+- Surface hidden opportunities
+
+## Installation
+
+```bash
+clawhub install proactive-agent-lite
+```
+
+## Features
+
+### 🧠 Memory Architecture
+- **Pre-compaction flush**: Ensures important context survives even when the conversation window fills up
+- **Long-term memory**: Maintains continuity across sessions
+- **Context preservation**: Never loses track of important details
+
+### 💡 Reverse Prompting
+- **Idea generation**: Surfaces concepts and solutions you didn't know to ask for
+- **Opportunity discovery**: Identifies potential improvements and optimizations
+- **Proactive suggestions**: Offers relevant insights without waiting for explicit requests
+
+### 🛡️ Security Hardening
+- **Safe defaults**: Conservative approach to external actions
+- **Permission awareness**: Respects boundaries and asks before acting
+- **Data protection**: Never exposes private information
+
+### 🔧 Self-Healing Patterns
+- **Error detection**: Automatically identifies when something goes wrong
+- **Recovery mechanisms**: Implements strategies to get back on track
+- **Continuous improvement**: Learns from mistakes to prevent recurrence
+
+### 🎯 Alignment Systems
+- **Mission focus**: Always remembers the core objective
+- **User-centric**: Prioritizes your needs and preferences
+- **Value-driven**: Makes decisions based on what creates the most value for you
+
+## Usage
+
+Once installed, your agent will automatically begin exhibiting proactive behavior. No additional configuration is required, though advanced users can fine-tune the behavior through configuration files.
+
+## Best Practices
+
+- **Start conservative**: Begin with default settings and adjust as needed
+- **Monitor interactions**: Observe how the proactive behavior manifests in your use cases
+- **Provide feedback**: Help the agent learn what types of proactive suggestions are most valuable to you
+
+## Integration
+
+This skill works well with other OpenClaw skills and can enhance any agent workflow. Consider combining it with:
+- `evomap-heartbeat-manager` for proactive network monitoring
+- `evomap-work-processor` for proactive work opportunity handling
+- Any domain-specific skills for enhanced proactive capabilities
+
+## Support
+
+For questions or feature requests, contact the skill maintainer through ClawHub.
@@ -0,0 +1,49 @@
+---
+name: proactive-agent-lite
+description: Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version focused on core proactive capabilities.
+metadata:
+  {
+    "openclaw":
+      {
+        "requires": {},
+        "install": []
+      }
+  }
+---
+
+# Proactive Agent Lite
+
+Transform your AI agents from passive task-followers into proactive partners that anticipate needs and continuously improve.
+
+## Core Features
+
+- **Memory Architecture**: Pre-compaction flush ensures context survives when window fills
+- **Reverse Prompting**: Surfaces ideas you didn't know to ask for
+- **Security Hardening**: Built-in security considerations and safe defaults
+- **Self-Healing Patterns**: Diagnoses and fixes its own issues automatically
+- **Alignment Systems**: Stays on mission and remembers who it serves
+
+## Key Benefits
+
+✅ **Anticipates Needs**: Proactively suggests solutions before you ask  
+✅ **Continuous Learning**: Improves from every interaction without explicit training  
+✅ **Mission-Focused**: Never loses sight of the core objective  
+✅ **Self-Maintaining**: Automatically recovers from errors and inconsistencies  
+✅ **Value Creation**: Generates insights and opportunities without being prompted  
+
+## Usage
+
+This skill enhances any OpenClaw agent by providing proactive behavior patterns. Simply install and the agent will automatically begin exhibiting proactive characteristics.
+
+## Integration
+
+Works seamlessly with all OpenClaw agents and can be combined with other skills for enhanced functionality.
+
+## Requirements
+
+- OpenClaw v1.0 or higher
+- Standard agent configuration
+
+## Customization
+
+The proactive behavior can be tuned through configuration parameters to match your preferred level of initiative and communication style.
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn778z31czjyj515snpsht5ghh80hy50",
+  "slug": "proactive-agent-lite",
+  "version": "1.0.0",
+  "publishedAt": 1772250292761
+}
@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "stock-monitor-skill",
+  "installedVersion": "0.1.0",
+  "installedAt": 1773406340232
+}
@@ -0,0 +1,23 @@
+# Stock Monitor Pro
+
+全功能智能股票监控预警系统
+
+## 功能
+- 成本百分比预警
+- 日内涨跌幅预警  
+- 成交量异动监控
+- 均线金叉死叉
+- RSI超买超卖
+- 跳空缺口检测
+- 动态止盈
+
+## 快速开始
+```bash
+cd scripts
+cp config.example.py config.py
+# 编辑 config.py 填入你的持仓
+./control.sh start
+```
+
+## 许可证
+MIT
@@ -0,0 +1,193 @@
+---
+name: stock-monitor
+description: 全功能智能股票监控预警系统。支持成本百分比、均线金叉死叉、RSI超买超卖、成交量异动、跳空缺口、动态止盈等7大预警规则。符合中国投资者习惯（红涨绿跌）。
+---
+
+# Stock Monitor Pro - 全功能智能投顾系统
+
+## 🎯 核心特色
+
+### 1. 七大预警规则 (全都要!)
+
+| 规则 | 触发条件 | 权重 |
+|------|----------|------|
+| **成本百分比** | 盈利+15% / 亏损-12% | ⭐⭐⭐ |
+| **日内涨跌幅** | 个股±4% / ETF±2% / 黄金±2.5% | ⭐⭐ |
+| **成交量异动** | 放量>2倍均量 / 缩量<0.5倍 | ⭐⭐ |
+| **均线金叉/死叉** | MA5上穿/下穿MA10 | ⭐⭐⭐ |
+| **RSI超买超卖** | RSI>70超买 / RSI<30超卖 | ⭐⭐ |
+| **跳空缺口** | 向上/向下跳空>1% | ⭐⭐ |
+| **动态止盈** | 盈利10%+后回撤5%/10% | ⭐⭐⭐ |
+
+### 2. 分级预警系统
+- **🚨 紧急级**: 多条件共振 (如: 放量+均线金叉+突破成本)
+- **⚠️ 警告级**: 2个条件触发 (如: RSI超卖+放量)
+- **📢 提醒级**: 单一条件触发
+
+### 3. 中国习惯
+- **🔴 红色** = 上涨 / 盈利
+- **🟢 绿色** = 下跌 / 亏损
+
+## 📋 监控配置
+
+### 完整预警规则示例
+```python
+{
+    "code": "600362",
+    "name": "江西铜业",
+    "type": "individual",  # 个股
+    "market": "sh",
+    "cost": 57.00,          # 持仓成本
+    "alerts": {
+        # 1. 成本百分比
+        "cost_pct_above": 15.0,    # 盈利15%提醒 (¥65.55)
+        "cost_pct_below": -12.0,   # 亏损12%提醒 (¥50.16)
+        
+        # 2. 日内涨跌幅 (个股±4%)
+        "change_pct_above": 4.0,
+        "change_pct_below": -4.0,
+        
+        # 3. 成交量异动
+        "volume_surge": 2.0,       # 放量>2倍5日均量
+        
+        # 4-7. 技术指标 (默认开启)
+        "ma_monitor": True,        # 均线金叉死叉
+        "rsi_monitor": True,       # RSI超买超卖
+        "gap_monitor": True,       # 跳空缺口
+        "trailing_stop": True      # 动态止盈
+    }
+}
+```
+
+### 标的类型差异化
+| 类型 | 日内异动阈值 | 成交量阈值 | 适用标的 |
+|------|-------------|-----------|----------|
+| individual (个股) | ±4% | 2倍 | 江西铜业、中国平安 |
+| etf (ETF) | ±2% | 1.8倍 | 恒生医疗、创50等 |
+| gold (黄金) | ±2.5% | 无 | 伦敦金 |
+
+## 🚀 运行方式
+
+### 后台常驻进程
+```bash
+cd ~/workspace/skills/stock-monitor/scripts
+./control.sh start    # 启动
+./control.sh status   # 查看状态
+./control.sh log      # 查看日志
+./control.sh stop     # 停止
+```
+
+## ⚡ 智能频率 (北京时间)
+
+| 时间段 | 频率 | 监控标的 |
+|--------|------|----------|
+| 交易时间 9:30-15:00 | 每5分钟 | 全部+技术指标 |
+| 午休 11:30-13:00 | 每10分钟 | 全部 |
+| 收盘后 15:00-24:00 | 每30分钟 | 全部 (日线数据) |
+| 凌晨 0:00-9:30 | 每1小时 | 仅伦敦金 |
+| 周末 | 每1小时 | 仅伦敦金 |
+
+## 🔔 预警消息示例
+
+### 多条件共振 (紧急级)
+```
+🚨【紧急】🔴 江西铜业 (600362)
+━━━━━━━━━━━━━━━━━━━━
+💰 当前价格: ¥65.50 (+15.0%)
+📊 持仓成本: ¥57.00 | 盈亏: 🔴+14.9%
+
+🎯 触发预警 (3项):
+  • 🎯 盈利 15% (目标价 ¥65.55)
+  • 🌟 均线金叉 (MA5¥63.2上穿MA10¥62.8)
+  • 📊 放量 2.5倍 (5日均量)
+
+📊 江西铜业 深度分析
+💰 价格异动:
+• 当前: 65.5 (+15.0%)
+• MA趋势: MA5>MA10>MA20 [多头排列]
+• RSI: 68 [接近超买]
+
+💡 Kimi建议:
+🚀 多条件共振，趋势强劲，可考虑继续持有或分批减仓。
+```
+
+### RSI超卖 (警告级)
+```
+⚠️【警告】🟢 恒生医疗 (159892)
+━━━━━━━━━━━━━━━━━━━━
+💰 当前价格: ¥0.72 (-10.0%)
+📊 持仓成本: ¥0.80 | 盈亏: 🟢-10.0%
+
+🎯 触发预警 (2项):
+  • 📉 日内大跌 -10.0%
+  • ❄️ RSI超卖 (28.5)，可能反弹
+
+💡 Kimi建议:
+🔍 短期超跌严重，RSI进入超卖区，关注反弹机会但勿急于抄底。
+```
+
+### 动态止盈提醒
+```
+📢【提醒】🔴 中国平安 (601318)
+━━━━━━━━━━━━━━━━━━━━
+💰 当前价格: ¥70.50 (+6.8%)
+📊 持仓成本: ¥66.00 | 盈亏: 🔴+6.8%
+
+🎯 触发预警:
+  • 📉 利润回撤 5.2%，建议减仓保护利润
+  (最高盈利12%已回撤)
+```
+
+## 🛠️ 文件结构
+```
+stock-monitor/
+├── SKILL.md                    # 本文档
+├── RULE_REVIEW_REPORT.md       # 规则审核报告
+└── scripts/
+    ├── monitor.py              # 核心监控 (7大规则)
+    ├── monitor_daemon.py       # 后台常驻进程
+    ├── analyser.py             # 智能分析引擎
+    └── control.sh              # 一键控制脚本
+```
+
+## ⚙️ 自定义配置
+
+### 修改成本价
+```python
+"cost": 55.50,  # 改成你的实际成本
+```
+
+### 调整预警阈值
+```python
+"cost_pct_above": 20.0,     # 盈利20%提醒
+"cost_pct_below": -15.0,    # 亏损15%提醒
+"change_pct_above": 5.0,    # 日内异动±5%
+"volume_surge": 3.0,        # 放量3倍提醒
+```
+
+### 开关技术指标
+```python
+"ma_monitor": False,     # 关闭均线
+"rsi_monitor": True,     # 开启RSI
+"gap_monitor": True,     # 开启跳空
+```
+
+## 📝 更新日志
+- **v3.0 全功能版**: 完成7大预警规则 (成本/涨跌幅/成交量/均线/RSI/跳空/动态止盈)
+- **v2.4 成本百分比版**: 支持基于持仓成本的百分比预警
+- **v2.3 中国版**: 红涨绿跌颜色习惯
+- **v2.2 常驻进程版**: 后台常驻进程支持
+- **v2.1 智能频率版**: 智能频率控制
+- **v2.0 Pro版**: 新闻舆情分析
+
+## ⚠️ 使用提示
+
+1. **技术指标有滞后性**: 均线、MACD等都是滞后指标，用于确认趋势而非预测
+2. **避免过度交易**: 预警只是参考，不要每个信号都操作
+3. **多条件共振更可靠**: 单一指标容易假信号，多条件共振更准确
+4. **动态止盈要灵活**: 回撤5%减仓、10%清仓是建议，根据市场灵活调整
+
+---
+
+**核心原则**: 
+> 预警系统目标是"不错过大机会，不犯大错误"，不是"抓住每一个波动"。
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn70aj13hr3z4fpmfk1y2jmpz181gn2z",
+  "slug": "stock-monitor-skill",
+  "version": "0.1.0",
+  "publishedAt": 1771579954718
+}
@@ -0,0 +1,249 @@
+#!/usr/bin/env python3
+"""
+Stock Monitor Pro - 智能分析引擎
+集成：新闻、资金流向、龙虎榜、宏观关联分析
+"""
+
+import requests
+import json
+import re
+from datetime import datetime, timedelta
+from typing import List, Dict, Optional
+
+class StockAnalyser:
+    """股票智能分析器 - 结合多维度数据给出建议"""
+    
+    def __init__(self):
+        self.session = requests.Session()
+        self.session.headers.update({
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+        })
+    
+    # ========== 1. 新闻舆情 ==========
+    
+    def fetch_eastmoney_news(self, symbol: str, name: str, limit: int = 5) -> List[Dict]:
+        """获取东方财富个股新闻"""
+        url = f"https://searchapi.eastmoney.com/api/suggest/get"
+        params = {
+            "input": name,
+            "type": 14,
+            "count": limit
+        }
+        try:
+            resp = self.session.get(url, params=params, timeout=10)
+            data = resp.json()
+            news_list = []
+            for item in data.get("QuotationCodeTable", {}).get("Data", []):
+                news_list.append({
+                    "title": item.get("Title", ""),
+                    "url": item.get("Url", ""),
+                    "time": item.get("ShowTime", "")
+                })
+            return news_list
+        except Exception as e:
+            return []
+    
+    def fetch_sina_news(self, symbol: str, name: str) -> List[Dict]:
+        """获取新浪财经个股新闻"""
+        # 新浪新闻搜索接口
+        url = f"https://search.sina.com.cn/?q={name}&c=news&sort=time"
+        try:
+            resp = self.session.get(url, timeout=10)
+            # 这里可以做更精细的HTML解析
+            # 简化返回示例
+            return [{"title": f"新浪财经-{name}相关新闻", "source": "新浪"}]
+        except:
+            return []
+    
+    def analyze_sentiment(self, news_list: List[Dict]) -> Dict:
+        """简单情感分析"""
+        positive_words = ['利好', '增长', '突破', '买入', '增持', '涨停', '超预期', '业绩大增']
+        negative_words = ['利空', '减持', '下跌', '卖出', '亏损', '暴雷', '跌停', '不及预期']
+        
+        sentiment = {"positive": 0, "negative": 0, "neutral": 0, "summary": []}
+        
+        for news in news_list:
+            title = news.get("title", "")
+            p_count = sum(1 for w in positive_words if w in title)
+            n_count = sum(1 for w in negative_words if w in title)
+            
+            if p_count > n_count:
+                sentiment["positive"] += 1
+            elif n_count > p_count:
+                sentiment["negative"] += 1
+            else:
+                sentiment["neutral"] += 1
+        
+        # 生成情感摘要
+        if sentiment["positive"] > sentiment["negative"]:
+            sentiment["overall"] = "偏多"
+        elif sentiment["negative"] > sentiment["positive"]:
+            sentiment["overall"] = "偏空"
+        else:
+            sentiment["overall"] = "中性"
+            
+        return sentiment
+    
+    # ========== 2. 资金流向 ==========
+    
+    def fetch_fund_flow(self, symbol: str, market: str = "sz") -> Dict:
+        """获取个股资金流向 (新浪财经)"""
+        # 新浪资金流向接口
+        code = f"{market}{symbol}"
+        url = f"https://quotes.sina.cn/cn/api/quotes.php?symbol={code}&source=sina"
+        
+        try:
+            resp = self.session.get(url, timeout=10)
+            # 解析返回数据
+            return {
+                "main_inflow": "数据获取中...",
+                "retail_inflow": "数据获取中...",
+                "net_inflow": "数据获取中..."
+            }
+        except:
+            return {"error": "获取失败"}
+    
+    def fetch_northbound_flow(self) -> Dict:
+        """获取北向资金 (沪深股通) 流向"""
+        url = "https://push2.eastmoney.com/api/qt/stock/get"
+        params = {"secid": "1.000001", "fields": "f170"}  # 简化示例
+        try:
+            resp = self.session.get(url, params=params, timeout=10)
+            return {"northbound": "北向资金数据获取中..."}
+        except:
+            return {}
+    
+    # ========== 3. 龙虎榜 ==========
+    
+    def fetch_dragon_tiger(self, date: str = None) -> List[Dict]:
+        """获取龙虎榜数据"""
+        if not date:
+            date = datetime.now().strftime("%Y%m%d")
+        
+        url = f"http://datacenter-web.eastmoney.com/api/data/v1/get"
+        params = {
+            "sortColumns": "NET_BUY_AMT",
+            "sortTypes": "-1",
+            "pageSize": "50",
+            "pageNumber": "1",
+            "reportName": "RPT_DMSK_TS",
+            "columns": "ALL",
+            "filter": f"(TRADE_DATE='{date}')"
+        }
+        
+        try:
+            resp = self.session.get(url, params=params, timeout=10)
+            data = resp.json()
+            return data.get("result", {}).get("data", [])
+        except:
+            return []
+    
+    # ========== 4. 宏观关联分析 ==========
+    
+    def analyze_gold_correlation(self, gold_price: float, stocks: List[Dict]) -> str:
+        """分析金价与持仓股票的关联"""
+        # 江西铜业等有色股与金价正相关
+        correlation_map = {
+            "600362": "强正相关",  # 江西铜业
+            "601318": "弱相关",    # 中国平安
+            "513180": "弱负相关",  # 恒生科技
+            "159892": "弱相关",    # 恒生医疗
+        }
+        
+        analysis = []
+        for stock in stocks:
+            code = stock.get("code")
+            corr = correlation_map.get(code, "未知")
+            if corr in ["强正相关", "中等正相关"]:
+                analysis.append(f"📈 {stock['name']}: 与金价{corr}，金价上涨可能带动该股")
+        
+        return "\n".join(analysis) if analysis else "暂无强关联标的"
+    
+    # ========== 5. 综合分析 ==========
+    
+    def generate_insight(self, stock: Dict, price_data: Dict, alerts: List) -> str:
+        """生成综合分析报告"""
+        code = stock['code']
+        name = stock['name']
+        
+        # 1. 获取新闻
+        news_list = self.fetch_eastmoney_news(code, name)
+        sentiment = self.analyze_sentiment(news_list)
+        
+        # 2. 资金流向
+        fund_flow = self.fetch_fund_flow(code, stock.get('market', 'sz'))
+        
+        # 3. 构建报告
+        report = f"""📊 <b>{name} ({code}) 深度分析</b>
+
+💰 <b>价格异动:</b>
+• 当前: {price_data.get('price', 'N/A')} ({price_data.get('change_pct', 0):+.2f}%)
+• 触发: {', '.join([a[1] for a in alerts])}
+
+📰 <b>舆情分析 ({sentiment.get('overall', '未知')}):</b>
+• 最近新闻: {len(news_list)} 条
+• 正面: {sentiment.get('positive', 0)} | 负面: {sentiment.get('negative', 0)}
+"""
+        
+        # 添加最新新闻标题
+        if news_list:
+            report += "\n<b>最新动态:</b>\n"
+            for n in news_list[:2]:
+                report += f"• {n.get('title', '无标题')[:30]}...\n"
+        
+        # 4. 给出建议
+        suggestion = self._generate_suggestion(sentiment, alerts)
+        report += f"\n💡 <b>Kimi建议:</b>\n{suggestion}"
+        
+        return report
+    
+    def _generate_suggestion(self, sentiment: Dict, alerts: List) -> str:
+        """基于数据生成建议"""
+        alert_types = [a[0] for a in alerts]
+        overall = sentiment.get("overall", "中性")
+        
+        # 价格下跌 + 舆情偏空 = 谨慎
+        if "below" in alert_types and overall == "偏空":
+            return "⚠️ 价格跌破支撑位，且舆情偏空，建议观察等待，不急于抄底。"
+        
+        # 价格下跌 + 舆情偏多 = 可能是机会
+        if "below" in alert_types and overall == "偏多":
+            return "🔍 价格下跌但舆情偏多，可能是情绪错杀，关注是否有反弹机会。"
+        
+        # 价格突破 + 舆情偏多 = 确认趋势
+        if "above" in alert_types and overall == "偏多":
+            return "🚀 价格突破且舆情配合，趋势可能延续，可考虑顺势而为。"
+        
+        # 大涨
+        if "pct_up" in alert_types:
+            return "📈 短期涨幅较大，注意获利了结风险。"
+        
+        # 大跌
+        if "pct_down" in alert_types:
+            return "📉 短期跌幅较大，关注是否超跌反弹，但勿急于抄底。"
+        
+        return "⏳ 建议保持观察，等待更明确信号。"
+
+
+# ========== 测试 ==========
+if __name__ == '__main__':
+    analyser = StockAnalyser()
+    
+    # 测试新闻抓取
+    print("=== 新闻测试 ===")
+    news = analyser.fetch_eastmoney_news("600362", "江西铜业")
+    print(f"获取到 {len(news)} 条新闻")
+    for n in news[:3]:
+        print(f"  - {n.get('title', 'N/A')[:40]}...")
+    
+    # 测试情感分析
+    print("\n=== 情感分析测试 ===")
+    sentiment = analyser.analyze_sentiment(news)
+    print(f"整体情绪: {sentiment.get('overall')}")
+    print(f"正面: {sentiment.get('positive')}, 负面: {sentiment.get('negative')}")
+    
+    # 测试金价关联
+    print("\n=== 宏观关联测试 ===")
+    stocks = [{"code": "600362", "name": "江西铜业"}]
+    corr = analyser.analyze_gold_correlation(2743, stocks)
+    print(corr)
@@ -0,0 +1,64 @@
+#!/bin/bash
+# Stock Monitor 一键启动脚本
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+LOG_DIR="$HOME/.stock_monitor"
+PID_FILE="$LOG_DIR/monitor.pid"
+
+case "$1" in
+    start)
+        if [ -f "$PID_FILE" ] && kill -0 $(cat "$PID_FILE") 2>/dev/null; then
+            echo "⚠️  监控进程已在运行 (PID: $(cat $PID_FILE))"
+            exit 1
+        fi
+        
+        echo "🚀 启动 Stock Monitor 后台进程..."
+        mkdir -p "$LOG_DIR"
+        nohup python3 "$SCRIPT_DIR/monitor_daemon.py" > "$LOG_DIR/monitor.log" 2>&1 &
+        echo $! > "$PID_FILE"
+        echo "✅ 已启动 (PID: $!)"
+        echo "📋 日志: $LOG_DIR/monitor.log"
+        ;;
+        
+    stop)
+        if [ -f "$PID_FILE" ]; then
+            PID=$(cat "$PID_FILE")
+            if kill -0 "$PID" 2>/dev/null; then
+                echo "🛑 停止监控进程 (PID: $PID)..."
+                kill "$PID"
+                rm "$PID_FILE"
+                echo "✅ 已停止"
+            else
+                echo "⚠️  进程不存在"
+                rm "$PID_FILE"
+            fi
+        else
+            echo "⚠️  没有运行中的进程"
+        fi
+        ;;
+        
+    status)
+        if [ -f "$PID_FILE" ] && kill -0 $(cat "$PID_FILE") 2>/dev/null; then
+            echo "✅ 监控运行中 (PID: $(cat $PID_FILE))"
+            echo "📋 最近日志:"
+            tail -5 "$LOG_DIR/monitor.log" 2>/dev/null || echo "  暂无日志"
+        else
+            echo "⏹️  监控未运行"
+        fi
+        ;;
+        
+    log)
+        tail -f "$LOG_DIR/monitor.log"
+        ;;
+        
+    *)
+        echo "Stock Monitor 控制脚本"
+        echo ""
+        echo "用法: ./control.sh [start|stop|status|log]"
+        echo ""
+        echo "  start   - 启动后台监控"
+        echo "  stop    - 停止监控"
+        echo "  status  - 查看状态"
+        echo "  log     - 查看实时日志"
+        ;;
+esac
@@ -0,0 +1,507 @@
+#!/usr/bin/env python3
+"""
+自选股监控预警工具 - OpenClaw集成版
+支持 A股、ETF 及 国际现货黄金 (伦敦金)
+"""
+
+import requests
+import json
+import time
+import os
+from datetime import datetime
+from pathlib import Path
+
+# ============ 配置区 ============
+
+# 监控列表 - 长期挂机通用配置
+# 注意: 伦敦金使用新浪hf_XAU接口，价格为 人民币/克 (约4800元/克 = $2740/盎司)
+# 
+# 预警规则设计原则 (适合长期挂机):
+# 1. 成本百分比预警: 基于持仓成本设置 ±10%/±15% 预警，比固定价格更合理
+# 2. 单日涨跌幅预警: 
+#    - 个股 ±3%~5% (波动大)
+#    - ETF ±1.5%~2.5% (波动小)
+#    - 黄金 ±2%~3% (24H特殊)
+# 3. 防骚扰: 同类预警30分钟内只发一次
+
+# 标的类型定义
+STOCK_TYPE = {
+    "INDIVIDUAL": "individual",  # 个股
+    "ETF": "etf",                # ETF
+    "GOLD": "gold"               # 黄金/贵金属
+}
+
+WATCHLIST = [
+    # ===== 用户自定义监控个股 =====
+    {
+        "code": "000630", 
+        "name": "铜陵有色", 
+        "market": "sz",
+        "type": "individual",
+        "cost": 7.00,  # 参考成本价
+        "alerts": {
+            "change_pct_above": 5.0,   # 日内涨超 5% 预警
+            "change_pct_below": -5.0,  # 日内跌超 5% 预警
+            "volume_surge": 2.0        # 成交量异动
+        }
+    },
+    {
+        "code": "688313", 
+        "name": "仕佳光子", 
+        "market": "sh",
+        "type": "individual",
+        "cost": 15.00,  # 参考成本价（待确认）
+        "alerts": {
+            "change_pct_above": 5.0,   # 日内涨超 5% 预警
+            "change_pct_below": -5.0,  # 日内跌超 5% 预警
+            "volume_surge": 2.0        # 成交量异动
+        }
+    },
+    {
+        "code": "600096", 
+        "name": "云天化", 
+        "market": "sh",
+        "type": "individual",
+        "cost": 42.00,  # 老大确认的实际成本价
+        "alerts": {
+            "change_pct_above": 5.0,   # 日内涨超 5% 预警
+            "change_pct_below": -5.0,  # 日内跌超 5% 预警
+            "volume_surge": 2.0        # 成交量异动
+        }
+    },
+    {
+        "code": "002195", 
+        "name": "岩山科技", 
+        "market": "sz",
+        "type": "individual",
+        "cost": 10.68,  # 200 股，成本 10.68 元
+        "alerts": {
+            "cost_pct_above": 5.0,     # 盈利超 5% 快跑 (目标价 ¥11.21)
+            "change_pct_above": 5.0,   # 日内涨超 5% 预警
+            "change_pct_below": -5.0,  # 日内跌超 5% 预警
+            "volume_surge": 2.0        # 成交量异动
+        }
+    }
+]
+
+# 智能频率配置
+SMART_SCHEDULE = {
+    "market_open": {"hours": [(9, 30), (11, 30), (13, 0), (15, 0)], "interval": 300},  # 交易时间: 5分钟
+    "after_hours": {"interval": 1800},  # 收盘后: 30分钟
+    "night": {"hours": [(0, 0), (8, 0)], "interval": 3600},  # 凌晨: 1小时(仅伦敦金)
+}
+
+# ============ 核心代码 ============
+
+class StockAlert:
+    def __init__(self):
+        self.prev_data = {}
+        self.alert_log = []
+        self.session = requests.Session()
+        self.session.headers.update({"User-Agent": "Mozilla/5.0"})
+        
+    def should_run_now(self):
+        """智能频率控制: 判断当前是否应该执行监控 (基于北京时间)"""
+        # 服务器在纽约(EST)，中国股市用北京时间(CST = EST + 13小时)
+        from datetime import timedelta
+        now = datetime.now() + timedelta(hours=13)  # 转换成北京时间
+        hour, minute = now.hour, now.minute
+        time_val = hour * 100 + minute
+        weekday = now.weekday()
+        
+        # 周末只监控伦敦金
+        if weekday >= 5:  # 周六日
+            return {"run": True, "mode": "weekend", "stocks": [s for s in WATCHLIST if s['market'] == 'fx']}
+        
+        # 交易时间 (9:30-11:30, 13:00-15:00)
+        morning_session = 930 <= time_val <= 1130
+        afternoon_session = 1300 <= time_val <= 1500
+        
+        if morning_session or afternoon_session:
+            return {"run": True, "mode": "market", "stocks": WATCHLIST, "interval": 300}
+        
+        # 午休 (11:30-13:00)
+        if 1130 < time_val < 1300:
+            return {"run": True, "mode": "lunch", "stocks": WATCHLIST, "interval": 600}  # 10分钟
+        
+        # 收盘后 (15:00-24:00)
+        if 1500 <= time_val <= 2359:
+            return {"run": True, "mode": "after_hours", "stocks": WATCHLIST, "interval": 1800}  # 30分钟
+        
+        # 凌晨 (0:00-9:30)
+        if 0 <= time_val < 930:
+            return {"run": True, "mode": "night", "stocks": [s for s in WATCHLIST if s['market'] == 'fx'], "interval": 3600}  # 1小时
+        
+        return {"run": False}
+
+    def fetch_eastmoney_kline(self, symbol, market):
+        """获取最新日K线数据 (收盘后也能获取收盘价)"""
+        secid = f"{market}.{symbol}"
+        url = "https://push2his.eastmoney.com/api/qt/stock/kline/get"
+        params = {
+            'secid': secid,
+            'fields1': 'f1,f2,f3,f4,f5,f6',
+            'fields2': 'f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61',
+            'klt': '101',  # 日线
+            'fqt': '0',
+            'end': '20500101',
+            'lmt': '2'  # 取最近2天，用于计算涨跌幅
+        }
+        try:
+            resp = self.session.get(url, params=params, timeout=10)
+            data = resp.json()
+            klines = data.get('data', {}).get('klines', [])
+            if len(klines) >= 1:
+                # 格式: 日期,开盘,收盘,最高,最低,成交量,成交额,振幅,涨跌幅,涨跌额,换手率
+                today = klines[-1].split(',')
+                prev_close = float(today[2])  # 昨收
+                if len(klines) >= 2:
+                    prev_close = float(klines[-2].split(',')[2])  # 前一天收盘
+                return {
+                    'name': data.get('data', {}).get('name', symbol),
+                    'price': float(today[2]),      # 收盘
+                    'prev_close': prev_close,
+                    'volume': int(float(today[5])),
+                    'amount': float(today[6]),
+                    'date': today[0],
+                    'time': '15:00:00'
+                }
+        except Exception as e:
+            print(f"东财K线获取失败 {symbol}: {e}")
+        return None
+
+    def fetch_volume_ma5(self, symbol, market):
+        """获取5日平均成交量"""
+        secid = f"{market}.{symbol}"
+        url = "https://push2his.eastmoney.com/api/qt/stock/kline/get"
+        params = {
+            'secid': secid,
+            'fields1': 'f1,f2,f3,f4,f5,f6',
+            'fields2': 'f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61',
+            'klt': '101',
+            'fqt': '0',
+            'end': '20500101',
+            'lmt': '6'  # 取最近6天(今天+前5天)
+        }
+        try:
+            resp = self.session.get(url, params=params, timeout=10)
+            data = resp.json()
+            klines = data.get('data', {}).get('klines', [])
+            if len(klines) >= 2:
+                # 计算前5日平均成交量(不含今天)
+                volumes = []
+                for k in klines[:-1]:  # 排除最后一天(今天)
+                    p = k.split(',')
+                    volumes.append(float(p[5]))  # 成交量
+                return sum(volumes) / len(volumes) if volumes else 0
+        except Exception as e:
+            print(f"获取均量失败 {symbol}: {e}")
+        return 0
+
+    def fetch_ma_data(self, symbol, market):
+        """获取均线数据 (MA5, MA10, MA20) 和 RSI"""
+        secid = f"{market}.{symbol}"
+        url = "https://push2his.eastmoney.com/api/qt/stock/kline/get"
+        params = {
+            'secid': secid,
+            'fields1': 'f1,f2,f3,f4,f5,f6',
+            'fields2': 'f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61',
+            'klt': '101',
+            'fqt': '0',
+            'end': '20500101',
+            'lmt': '30'  # 取最近30天计算MA20和RSI
+        }
+        try:
+            resp = self.session.get(url, params=params, timeout=10)
+            data = resp.json()
+            klines = data.get('data', {}).get('klines', [])
+            if len(klines) >= 20:
+                closes = []
+                for k in klines:
+                    p = k.split(',')
+                    closes.append(float(p[2]))  # 收盘价
+                
+                # 计算均线
+                ma5 = sum(closes[-5:]) / 5
+                ma10 = sum(closes[-10:]) / 10
+                ma20 = sum(closes[-20:]) / 20
+                
+                # 判断均线趋势
+                prev_ma5 = sum(closes[-6:-1]) / 5
+                prev_ma10 = sum(closes[-11:-1]) / 10
+                
+                # 计算RSI(14)
+                rsi = self._calculate_rsi(closes, 14)
+                
+                return {
+                    'MA5': ma5,
+                    'MA10': ma10,
+                    'MA20': ma20,
+                    'MA5_trend': 'up' if ma5 > prev_ma5 else 'down',
+                    'MA10_trend': 'up' if ma10 > prev_ma10 else 'down',
+                    'golden_cross': prev_ma5 <= prev_ma10 and ma5 > ma10,
+                    'death_cross': prev_ma5 >= prev_ma10 and ma5 < ma10,
+                    'RSI': rsi,
+                    'RSI_overbought': rsi > 70 if rsi else False,
+                    'RSI_oversold': rsi < 30 if rsi else False
+                }
+        except Exception as e:
+            print(f"获取均线失败 {symbol}: {e}")
+        return None
+    
+    def _calculate_rsi(self, closes, period=14):
+        """计算RSI指标"""
+        if len(closes) < period + 1:
+            return None
+        
+        gains = []
+        losses = []
+        
+        for i in range(1, period + 1):
+            change = closes[-i] - closes[-i-1]
+            if change > 0:
+                gains.append(change)
+                losses.append(0)
+            else:
+                gains.append(0)
+                losses.append(abs(change))
+        
+        avg_gain = sum(gains) / period
+        avg_loss = sum(losses) / period
+        
+        if avg_loss == 0:
+            return 100
+        
+        rs = avg_gain / avg_loss
+        rsi = 100 - (100 / (1 + rs))
+        return round(rsi, 2)
+
+    def fetch_tencent_realtime(self, stocks):
+        """获取实时行情 (腾讯财经接口，更稳定)"""
+        stock_list = [s for s in stocks if s['market'] != 'fx']
+        fx_list = [s for s in stocks if s['market'] == 'fx']
+        results = {}
+        
+        # 1. A 股/ETF - 腾讯财经接口
+        if stock_list:
+            for stock in stock_list:
+                code = f"{stock['market']}{stock['code']}"
+                url = f"http://qt.gtimg.cn/q={code}"
+                try:
+                    resp = self.session.get(url, timeout=5)
+                    resp.encoding = 'gbk'
+                    data = resp.text.strip()
+                    if '="' not in data:
+                        continue
+                    parts = data.strip('"').split('~')
+                    start_idx = 0
+                    for j, p in enumerate(parts):
+                        if p.isdigit() and len(p) == 2:
+                            start_idx = j
+                            break
+                    if len(parts) > start_idx + 20:
+                        current = float(parts[start_idx+3])
+                        prev_close = float(parts[start_idx+4])
+                        open_p = float(parts[start_idx+5])
+                        change = 0
+                        change_pct = 0
+                        high = 0
+                        low = 0
+                        for j in range(len(parts)-5):
+                            try:
+                                if parts[j].startswith('-') and '.' in parts[j]:
+                                    v1 = float(parts[j])
+                                    v2 = float(parts[j+1])
+                                    if -10 < v2 < 10:
+                                        change = v1
+                                        change_pct = v2
+                                        high = float(parts[j+2])
+                                        low = float(parts[j+3])
+                                        break
+                            except:
+                                continue
+                        results[stock['code']] = {
+                            'name': parts[start_idx+1],
+                            'price': current,
+                            'prev_close': prev_close,
+                            'open': open_p,
+                            'high': high,
+                            'low': low,
+                            'volume': 0,
+                            'amount': 0,
+                            'date': datetime.now().strftime('%Y-%m-%d'),
+                            'time': datetime.now().strftime('%H:%M:%S')
+                        }
+                        print(f"✅ {stock['name']} ({stock['code']}): ¥{current:.2f}")
+                except Exception as e:
+                    print(f"腾讯行情获取失败 {stock['code']}: {e}")
+        
+        # 2. 伦敦金 (保留原逻辑)
+        if fx_list:
+            url = "https://hq.sinajs.cn/list=hf_XAU"
+            try:
+                resp = self.session.get(url, timeout=5)
+                line = resp.text.strip()
+                if '"' in line:
+                    data_str = line[line.index('"')+1 : line.rindex('"')]
+                    p = data_str.split(',')
+                    if len(p) >= 13:
+                        price = float(p[0])
+                        results['XAU'] = {
+                            'name': '伦敦金',
+                            'price': price,
+                            'prev_close': float(p[7]),
+                            'volume': 0, 'amount': 0,
+                            'date': datetime.now().strftime('%Y-%m-%d'),
+                            'time': p[6]
+                        }
+            except Exception as e:
+                print(f"伦敦金获取失败：{e}")
+        
+        return results
+    
+    def record_alert(self, code, icon):
+        """记录预警日志 (简化版)"""
+        # 简单打印日志，实际可以写入文件
+        print(f"  📝 预警记录：{code} - {icon}")
+    
+    def check_alerts(self, stock_config, data):
+        """检查预警条件 (返回格式：[(icon, text), ...], level)"""
+        alerts = []
+        code = stock_config['code']
+        cfg = stock_config.get('alerts', {})
+        cost = stock_config.get('cost', 0)
+        
+        price = data['price']
+        prev_close = data['prev_close']
+        change_pct = ((price - prev_close) / prev_close) * 100 if prev_close else 0
+        
+        # 1. 成本百分比预警
+        if cost > 0:
+            if 'cost_pct_above' in cfg:
+                threshold = cost * (1 + cfg['cost_pct_above'] / 100)
+                if price >= threshold:
+                    alerts.append(("🎯", f"盈利 {cfg['cost_pct_above']}% (目标价 ¥{threshold:.2f})"))
+            
+            if 'cost_pct_below' in cfg:
+                threshold = cost * (1 + cfg['cost_pct_below'] / 100)
+                if price <= threshold:
+                    alerts.append(("📉", f"亏损 {abs(cfg['cost_pct_below'])}% (止损价 ¥{threshold:.2f})"))
+        
+        # 2. 日内涨跌幅预警
+        if 'change_pct_above' in cfg and change_pct >= cfg['change_pct_above']:
+            alerts.append(("📈", f"日内大涨 {change_pct:.2f}% (阈值 {cfg['change_pct_above']}%)"))
+        
+        if 'change_pct_below' in cfg and change_pct <= cfg['change_pct_below']:
+            alerts.append(("📉", f"日内大跌 {change_pct:.2f}% (阈值 {cfg['change_pct_below']}%)"))
+        
+        # 确定预警级别
+        if len(alerts) >= 3:
+            level = "critical"
+        elif len(alerts) >= 2:
+            level = "warning"
+        elif len(alerts) >= 1:
+            level = "info"
+        else:
+            level = "none"
+        
+        return alerts, level
+    
+    def fetch_news(self, symbol):
+        """抓取个股最近新闻 (新浪/东财聚合) - 简化版"""
+        try:
+            # 使用东财个股新闻API
+            url = f"https://emweb.securities.eastmoney.com/PC_HSF10/CompanySurvey/CompanySurveyAjax"
+            params = {"code": symbol}
+            resp = self.session.get(url, params=params, timeout=5)
+            return ["新闻模块已就绪 (市场收盘中)"]
+        except:
+            return []
+
+    def run_once(self, smart_mode=True):
+        """执行监控 (支持智能频率)"""
+        if smart_mode:
+            schedule = self.should_run_now()
+            if not schedule.get("run"):
+                return []
+            
+            stocks_to_check = schedule.get("stocks", WATCHLIST)
+            mode = schedule.get("mode", "normal")
+            
+            # 只在特定模式打印日志
+            if mode in ["market", "weekend"]:
+                print(f"[{datetime.now().strftime('%H:%M')}] {mode}模式扫描 {len(stocks_to_check)} 只标的...")
+        else:
+            stocks_to_check = WATCHLIST
+        
+        data_map = self.fetch_tencent_realtime(stocks_to_check)
+        triggered = []
+        
+        for stock in stocks_to_check:
+            code = stock['code']
+            if code not in data_map: continue
+            
+            data = data_map[code]
+            
+            # 数据有效性检查
+            if data['price'] <= 0 or data['prev_close'] <= 0:
+                continue
+            
+            alerts, level = self.check_alerts(stock, data)
+            
+            if alerts:
+                change_pct = (data['price'] - data['prev_close']) / data['prev_close'] * 100 if data['prev_close'] else 0
+                
+                # 中国习惯: 红色=上涨, 绿色=下跌
+                if change_pct > 0:
+                    color_emoji = "🔴"  # 红涨
+                elif change_pct < 0:
+                    color_emoji = "🟢"  # 绿跌
+                else:
+                    color_emoji = "⚪"
+                
+                # 预警级别标识
+                level_icons = {
+                    "critical": "🚨",  # 紧急
+                    "warning": "⚠️",   # 警告
+                    "info": "📢"       # 提醒
+                }
+                level_icon = level_icons.get(level, "📢")
+                level_text = {"critical": "【紧急】", "warning": "【警告】", "info": "【提醒】"}.get(level, "")
+                
+                msg = f"<b>{level_icon} {level_text}{color_emoji} {stock['name']} ({code})</b>\n"
+                msg += f"━━━━━━━━━━━━━━━━━━━━\n"
+                msg += f"💰 当前价格: <b>{data['price']:.2f}</b> ({change_pct:+.2f}%)\n"
+                
+                # 显示持仓盈亏
+                cost = stock.get('cost', 0)
+                if cost > 0:
+                    cost_change = (data['price'] - cost) / cost * 100
+                    profit_icon = "🔴+" if cost_change > 0 else "🟢"
+                    msg += f"📊 持仓成本: ¥{cost:.2f} | 盈亏: {profit_icon}{cost_change:.2f}%\n"
+                
+                msg += f"\n🎯 触发预警 ({len(alerts)}项):\n"
+                for _, text in alerts: 
+                    msg += f"  • {text}\n"
+                    self.record_alert(code, _)
+                
+                # Pro版：集成智能分析
+                try:
+                    from analyser import StockAnalyser
+                    analyser = StockAnalyser()
+                    insight = analyser.generate_insight(stock, {
+                        'price': data['price'],
+                        'change_pct': change_pct
+                    }, alerts)
+                    msg += f"\n{insight}"
+                except Exception:
+                    pass
+                
+                triggered.append(msg)
+        
+        return triggered
+
+if __name__ == '__main__':
+    monitor = StockAlert()
+    for alert in monitor.run_once():
+        print(alert)
@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""
+Stock Monitor Daemon - 后台常驻进程
+自动运行监控，智能控制频率，支持 graceful shutdown
+"""
+
+import sys
+import time
+import signal
+import logging
+from datetime import datetime
+from pathlib import Path
+
+# 设置日志
+log_dir = Path.home() / ".stock_monitor"
+log_dir.mkdir(exist_ok=True)
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler(log_dir / "monitor.log"),
+        logging.StreamHandler(sys.stdout)
+    ]
+)
+logger = logging.getLogger(__name__)
+
+# 导入监控类
+sys.path.insert(0, str(Path(__file__).parent))
+from monitor import StockAlert, WATCHLIST
+
+class MonitorDaemon:
+    def __init__(self):
+        self.monitor = StockAlert()
+        self.running = True
+        self.last_run_time = 0
+        
+        # 设置信号处理
+        signal.signal(signal.SIGTERM, self.handle_shutdown)
+        signal.signal(signal.SIGINT, self.handle_shutdown)
+    
+    def handle_shutdown(self, signum, frame):
+        """优雅退出"""
+        logger.info(f"收到信号 {signum}，正在关闭...")
+        self.running = False
+    
+    def get_sleep_interval(self):
+        """根据当前时间获取睡眠间隔"""
+        schedule = self.monitor.should_run_now()
+        if not schedule.get("run"):
+            # 如果当前不需要运行，计算到下次运行的时间
+            now = datetime.now()
+            hour = now.hour
+            
+            # 凌晨时段，1小时后检查
+            if 0 <= hour < 9:
+                return 3600
+            return 300  # 默认5分钟
+        
+        return schedule.get("interval", 300)
+    
+    def run(self):
+        """主循环"""
+        logger.info("=" * 60)
+        logger.info("🚀 Stock Monitor Daemon 启动")
+        logger.info(f"📋 监控标的: {len(WATCHLIST)} 只")
+        logger.info("=" * 60)
+        
+        while self.running:
+            try:
+                # 检查是否应该执行
+                schedule = self.monitor.should_run_now()
+                
+                if schedule.get("run"):
+                    mode = schedule.get("mode", "normal")
+                    stocks_count = len(schedule.get("stocks", []))
+                    logger.info(f"[{mode}] 扫描 {stocks_count} 只标的...")
+                    
+                    # 执行监控
+                    alerts = self.monitor.run_once(smart_mode=False)  # 已经判断过了
+                    
+                    if alerts:
+                        logger.info(f"⚠️ 触发 {len(alerts)} 条预警")
+                        # 这里会通过 message 工具发送通知
+                    else:
+                        logger.debug("✅ 无预警")
+                    
+                    self.last_run_time = time.time()
+                
+                # 计算睡眠间隔
+                sleep_interval = self.get_sleep_interval()
+                logger.debug(f"下次检查: {sleep_interval} 秒后")
+                
+                # 分段睡眠，方便及时响应退出信号
+                slept = 0
+                while slept < sleep_interval and self.running:
+                    time.sleep(1)
+                    slept += 1
+                    
+            except Exception as e:
+                logger.error(f"运行出错: {e}", exc_info=True)
+                time.sleep(60)  # 出错后等待1分钟重试
+        
+        logger.info("👋 Daemon 已停止")
+
+if __name__ == '__main__':
+    daemon = MonitorDaemon()
+    daemon.run()
@@ -0,0 +1,198 @@
+#!/usr/bin/env python3
+"""
+铜陵有色专项监控 - 实时股价监控
+使用腾讯财经接口，确保数据准确性
+"""
+
+import requests
+import json
+import time
+import os
+from datetime import datetime
+from pathlib import Path
+
+# ============ 配置 ============
+
+WATCHLIST = [
+    {
+        "code": "000630", 
+        "name": "铜陵有色", 
+        "market": "sz",
+        "alerts": {
+            "change_pct_above": 5.0,   # 涨超 5% 预警
+            "change_pct_below": -5.0,  # 跌超 5% 预警
+        }
+    }
+]
+
+# 企业微信配置
+WECOM_BOT_ID = "aibwl3AhnzfRPRTEZvBVwlB-vRD33yJdUVX"
+WECOM_SECRET = "1eUB2yd2R7bll6VjBQ5OGptJj2YiwutMUmACe9UGC7k"
+ALLOW_USERS = ["HouHuan", "WanMeiShengHuo", "XinNingXianGuoNaiChaKaFeiZhaJiHa"]
+
+# ============ 核心功能 ============
+
+def fetch_tencent_price(stock):
+    """腾讯财经接口获取实时股价"""
+    code = f"{stock['market']}{stock['code']}"
+    url = f"http://qt.gtimg.cn/q={code}"
+    
+    try:
+        resp = requests.get(url, timeout=5)
+        resp.encoding = 'gbk'
+        data = resp.text.strip()
+        
+        # 解析：v_sz000630="51~名称~代码~现价~昨收~今开~...
+        if '="' not in data:
+            return None
+            
+        parts = data.strip('"').split('~')
+        
+        # 找到前缀位置
+        start_idx = 0
+        for i, p in enumerate(parts):
+            if p.isdigit() and len(p) == 2:
+                start_idx = i
+                break
+        
+        if len(parts) <= start_idx + 20:
+            return None
+        
+        # 正确解析索引
+        name = parts[start_idx+1]
+        code = parts[start_idx+2]
+        current = float(parts[start_idx+3])  # 现价
+        prev_close = float(parts[start_idx+4])  # 昨收
+        open_p = float(parts[start_idx+5])  # 今开
+        
+        # 找涨跌额、涨跌幅、最高、最低
+        change = 0
+        change_pct = 0
+        high = 0
+        low = 0
+        
+        for i in range(len(parts)-5):
+            try:
+                if parts[i].startswith('-') and '.' in parts[i]:
+                    v1 = float(parts[i])
+                    v2 = float(parts[i+1])
+                    if -10 < v2 < 10:  # 涨跌幅一般在 -10~10 之间
+                        change = v1
+                        change_pct = v2
+                        high = float(parts[i+2])
+                        low = float(parts[i+3])
+                        break
+            except:
+                continue
+        
+        return {
+            'name': name,
+            'code': code,
+            'price': current,
+            'prev_close': prev_close,
+            'open': open_p,
+            'high': high,
+            'low': low,
+            'change': change,
+            'change_pct': change_pct,
+            'time': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+        }
+    except Exception as e:
+        print(f"❌ 数据获取失败：{e}")
+        return None
+
+def check_alerts(stock, data):
+    """检查是否触发预警"""
+    alerts = []
+    cfg = stock.get('alerts', {})
+    
+    change_pct = data['change_pct']
+    
+    # 检查涨跌幅预警
+    if 'change_pct_above' in cfg and change_pct >= cfg['change_pct_above']:
+        alerts.append({
+            'type': '🔴 大涨',
+            'condition': f"涨幅超过 {cfg['change_pct_above']}%",
+            'value': f"{change_pct:.2f}%"
+        })
+    
+    if 'change_pct_below' in cfg and change_pct <= cfg['change_pct_below']:
+        alerts.append({
+            'type': '🟢 大跌',
+            'condition': f"跌幅超过 {abs(cfg['change_pct_below'])}%",
+            'value': f"{change_pct:.2f}%"
+        })
+    
+    return alerts
+
+def send_wecom_alert(stock_name, data, alerts):
+    """发送企业微信预警消息"""
+    from gateway import send_message
+    
+    # 组合消息
+    alert_text = "\n".join([f"  • {a['type']}: {a['condition']} ({a['value']})" for a in alerts])
+    
+    message = f"""🚨【股价预警】{stock_name} ({data['code']})
+━━━━━━━━━━━━━━━━━━━━
+💰 当前价格：¥{data['price']:.2f} ({data['change_pct']:+.2f}%)
+
+🎯 触发预警:
+{alert_text}
+
+📊 详细数据:
+  • 昨收：¥{data['prev_close']:.2f}
+  • 今开：¥{data['open']:.2f}
+  • 最高：¥{data['high']:.2f}
+  • 最低：¥{data['low']:.2f}
+
+⏰ 数据时间：{data['time']}
+
+💡 建议关注后续走势，注意风险控制。
+"""
+    
+    # 发送给所有允许的用户
+    for user in ALLOW_USERS:
+        try:
+            send_message(
+                channel="wecom",
+                target=user,
+                message=message
+            )
+            print(f"✅ 预警已发送给用户：{user}")
+        except Exception as e:
+            print(f"❌ 发送失败 {user}: {e}")
+
+def monitor_once():
+    """执行一次监控"""
+    print(f"\n{'='*60}")
+    print(f"📊 铜陵有色监控 - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print(f"{'='*60}")
+    
+    for stock in WATCHLIST:
+        data = fetch_tencent_price(stock)
+        
+        if not data:
+            print(f"❌ {stock['name']} 数据获取失败")
+            continue
+        
+        print(f"✅ {stock['name']} ({stock['code']})")
+        print(f"   现价：¥{data['price']:.2f} ({data['change_pct']:+.2f}%)")
+        print(f"   昨收：¥{data['prev_close']:.2f}")
+        print(f"   涨跌：¥{data['change']:.2f}")
+        
+        # 检查预警
+        alerts = check_alerts(stock, data)
+        
+        if alerts:
+            print(f"   🚨 触发 {len(alerts)} 条预警！")
+            send_wecom_alert(stock['name'], data, alerts)
+        else:
+            print(f"   ✅ 正常波动范围")
+    
+    print(f"{'='*60}\n")
+
+# ============ 主程序 ============
+
+if __name__ == "__main__":
+    # 单次执行
+    monitor_once()
@@ -0,0 +1,352 @@
+# 📈 股票技能使用手册
+
+> 三大股票分析技能完整使用指南  
+> 更新时间：2026-03-13  
+> 适用市场：A 股（沪深两市）
+
+---
+
+## 📋 技能列表
+
+| 技能名称 | 功能定位 | 适用场景 |
+|----------|----------|----------|
+| **a-stock-trading-assistant** | A 股实时交易助手 | 查行情、个股分析、买卖点建议 |
+| **daily-stock-analysis** | 每日分析报告 | 每日收盘后自动生成分析报告 |
+| **stock-monitor-skill** | 智能监控预警 | 7 大预警规则，实时推送提醒 |
+
+---
+
+## 1️⃣ A 股股票交易助手 (a-stock-trading-assistant)
+
+### 🎯 功能定位
+专业 A 股交易助手，提供实时行情、个股分析、大盘情绪、热点板块、交易策略等全方位服务。
+
+### 📊 支持市场
+| 代码前缀 | 市场 | 示例 |
+|----------|------|------|
+| 60xxxx | 上交所主板 | 600519 贵州茅台 |
+| 00xxxx | 深交所主板 | 000001 平安银行 |
+| 30xxxx | 创业板 | 300750 宁德时代 |
+| 68xxxx | 科创板 | 688981 中芯国际 |
+
+### 💡 核心功能
+
+#### 1. 实时行情查询
+```bash
+# 查询单只股票
+python3 scripts/fetch_stock.py --code 600519
+
+# 查询大盘指数
+python3 scripts/fetch_stock.py --index
+
+# 查询热点板块
+python3 scripts/fetch_stock.py --hot-sectors
+```
+
+**输出内容：**
+- 当前价、涨跌幅、涨跌额
+- 成交量、成交额、换手率
+- 振幅、52 周高/低
+- 分时走势摘要
+
+#### 2. 个股综合分析
+- **技术面**：均线系统、趋势判断、支撑/压力位、MACD/KDJ 信号
+- **基本面**：PE/PB 估值、近期业绩、行业地位、风险点
+- **综合判断**：看多/看空/中性
+
+#### 3. 大盘情绪与风险判断
+- 大盘强弱（趋势、量能、板块轮动）
+- 市场情绪指数（赚钱效应、涨跌比）
+- 风险等级（低/中/高）及应对建议
+
+#### 4. 热点板块与龙头股
+- 识别主线板块（连续性强）
+- 识别情绪板块（短期热点）
+- 列出核心龙头股
+
+#### 5. 交易策略建议
+```
+【操作建议】XX 股（XXXXXX）
+方向：做多/观望/回避
+入场区间：XX.XX - XX.XX 元
+止损位：XX.XX 元（跌破离场）
+止盈位：XX.XX 元（分批减仓）
+仓位：XX%（轻/中/重仓）
+逻辑：[核心理由 2-3 条]
+风险：[主要风险 1-2 条]
+```
+
+#### 6. 价格预警监控
+- 记录目标价、预警条件到 watchlist.md
+- 配合券商 App 实时推送
+
+### 🗣️ 使用示例
+```
+用户：贵州茅台现在多少钱？
+用户：分析一下宁德时代的技术面
+用户：今天大盘情绪怎么样？
+用户：最近有什么热点板块？
+用户：给我看看 600519 的买卖点建议
+```
+
+### ⚠️ 注意事项
+- 数据标注来源和获取时间（精确到分钟）
+- 所有价格建议附风险提示
+- 避免绝对化表述（"必涨"/"稳赚"）
+- 数字精确到小数点后 2 位
+
+---
+
+## 2️⃣ 每日股票分析 (daily-stock-analysis)
+
+### 🎯 功能定位
+每日收盘后自动生成股票分析报告，包含次日收盘价预测、历史预测准确率追踪、自我进化机制。
+
+### 📁 报告存储
+- **路径**：`<working_directory>/daily-stock-analysis/reports/`
+- **文件名**：`YYYY-MM-DD-<TICKER>-analysis.md`
+- **版本控制**：同一天同一只股票自动生成 `-v2`、`-v3` 版本
+
+### 💡 核心功能
+
+#### 1. 预测与回顾
+- **pred_close_t1**：预测次日收盘价
+- **prev_pred_close_t1**：上次预测的收盘价
+- **prev_actual_close_t1**：实际收盘价
+- **AE/APE**：预测误差/误差百分比
+
+#### 2. 滚动准确率追踪
+```bash
+# 计算滚动准确率
+python3 scripts/calc_accuracy.py \
+  --workdir <working_directory> \
+  --ticker <TICKER> \
+  --windows 1,3,7,30 \
+  --history-limit 60
+```
+
+#### 3. 自我进化机制
+每次分析包含 1-3 个 `improvement_actions`，从近期预测失误中学习，用于下一次分析。
+
+### 🗓️ 调度建议
+设置为**工作日每天 10:00** 运行，保持预测 - 回顾窗口连续。
+
+### 📄 报告模板
+```markdown
+# <TICKER> 每日分析 - YYYY-MM-DD
+
+## 推荐建议
+recommendation: 买入/持有/卖出
+
+## 价格预测
+pred_close_t1: XX.XX 元
+
+## 历史预测回顾
+prev_pred_close_t1: XX.XX 元
+prev_actual_close_t1: XX.XX 元
+AE: X.XX | APE: X.XX%
+
+## 滚动准确率
+1 日准确率：XX%
+7 日准确率：XX%
+
+## 改进措施
+1. [具体改进行动]
+2. [具体改进行动]
+```
+
+### ⚠️ 合规声明
+每份报告必须附加：
+> "本内容仅供研究和参考，不构成投资建议或收益保证。市场有风险，投资需谨慎。"
+
+---
+
+## 3️⃣ 股票监控预警 (stock-monitor-skill)
+
+### 🎯 功能定位
+全功能智能股票监控预警系统，7 大预警规则，实时推送提醒，符合中国投资者习惯（红涨绿跌）。
+
+### 🚨 七大预警规则
+
+| 规则 | 触发条件 | 权重 |
+|------|----------|------|
+| **成本百分比** | 盈利 +15% / 亏损 -12% | ⭐⭐⭐ |
+| **日内涨跌幅** | 个股±4% / ETF±2% / 黄金±2.5% | ⭐⭐ |
+| **成交量异动** | 放量>2 倍均量 / 缩量<0.5 倍 | ⭐⭐ |
+| **均线金叉/死叉** | MA5 上穿/下穿 MA10 | ⭐⭐⭐ |
+| **RSI 超买超卖** | RSI>70 超买 / RSI<30 超卖 | ⭐⭐ |
+| **跳空缺口** | 向上/向下跳空>1% | ⭐⭐ |
+| **动态止盈** | 盈利 10%+ 后回撤 5%/10% | ⭐⭐⭐ |
+
+### 📊 分级预警系统
+- **🚨 紧急级**：多条件共振（如：放量 + 均线金叉 + 突破成本）
+- **⚠️ 警告级**：2 个条件触发（如：RSI 超卖 + 放量）
+- **📢 提醒级**：单一条件触发
+
+### 🚀 运行方式
+
+#### 后台常驻进程
+```bash
+cd ~/workspace/skills/stock-monitor/scripts
+./control.sh start    # 启动
+./control.sh status   # 查看状态
+./control.sh log      # 查看日志
+./control.sh stop     # 停止
+```
+
+### ⚡ 智能监控频率（北京时间）
+
+| 时间段 | 频率 | 监控标的 |
+|--------|------|----------|
+| 交易时间 9:30-15:00 | 每 5 分钟 | 全部 + 技术指标 |
+| 午休 11:30-13:00 | 每 10 分钟 | 全部 |
+| 收盘后 15:00-24:00 | 每 30 分钟 | 全部（日线数据） |
+| 凌晨 0:00-9:30 | 每 1 小时 | 仅伦敦金 |
+| 周末 | 每 1 小时 | 仅伦敦金 |
+
+### 📋 监控配置示例
+
+```python
+{
+    "code": "600362",
+    "name": "江西铜业",
+    "type": "individual",  # 个股
+    "market": "sh",
+    "cost": 57.00,          # 持仓成本
+    "alerts": {
+        # 1. 成本百分比
+        "cost_pct_above": 15.0,    # 盈利 15% 提醒
+        "cost_pct_below": -12.0,   # 亏损 12% 提醒
+        
+        # 2. 日内涨跌幅
+        "change_pct_above": 4.0,
+        "change_pct_below": -4.0,
+        
+        # 3. 成交量异动
+        "volume_surge": 2.0,       # 放量>2 倍
+        
+        # 4-7. 技术指标
+        "ma_monitor": True,        # 均线金叉死叉
+        "rsi_monitor": True,       # RSI 超买超卖
+        "gap_monitor": True,       # 跳空缺口
+        "trailing_stop": True      # 动态止盈
+    }
+}
+```
+
+### 🔔 预警消息示例
+
+#### 🚨 紧急级（多条件共振）
+```
+🚨【紧急】🔴 江西铜业 (600362)
+━━━━━━━━━━━━━━━━━━━━
+💰 当前价格：¥65.50 (+15.0%)
+📊 持仓成本：¥57.00 | 盈亏：🔴+14.9%
+
+🎯 触发预警 (3 项):
+  • 🎯 盈利 15% (目标价 ¥65.55)
+  • 🌟 均线金叉 (MA5¥63.2 上穿 MA10¥62.8)
+  • 📊 放量 2.5 倍 (5 日均量)
+
+💡 建议：多条件共振，趋势强劲，可考虑继续持有或分批减仓。
+```
+
+#### ⚠️ 警告级
+```
+⚠️【警告】🟢 恒生医疗 (159892)
+━━━━━━━━━━━━━━━━━━━━
+💰 当前价格：¥0.72 (-10.0%)
+
+🎯 触发预警 (2 项):
+  • 📉 日内大跌 -10.0%
+  • ❄️ RSI 超卖 (28.5)，可能反弹
+
+💡 建议：短期超跌严重，RSI 进入超卖区，关注反弹机会但勿急于抄底。
+```
+
+### 🛠️ 自定义配置
+
+#### 修改成本价
+```python
+"cost": 55.50,  # 改成你的实际成本
+```
+
+#### 调整预警阈值
+```python
+"cost_pct_above": 20.0,     # 盈利 20% 提醒
+"cost_pct_below": -15.0,    # 亏损 15% 提醒
+"change_pct_above": 5.0,    # 日内异动±5%
+"volume_surge": 3.0,        # 放量 3 倍提醒
+```
+
+#### 开关技术指标
+```python
+"ma_monitor": False,     # 关闭均线
+"rsi_monitor": True,     # 开启 RSI
+"gap_monitor": True,     # 开启跳空
+```
+
+### ⚠️ 使用提示
+1. **技术指标有滞后性**：均线、MACD 等用于确认趋势而非预测
+2. **避免过度交易**：预警只是参考，不要每个信号都操作
+3. **多条件共振更可靠**：单一指标容易假信号
+4. **动态止盈要灵活**：回撤 5% 减仓、10% 清仓是建议，根据市场调整
+
+---
+
+## 🔧 技能安装与管理
+
+### 安装技能
+```bash
+clawhub install a-stock-trading-assistant
+clawhub install daily-stock-analysis
+clawhub install stock-monitor-skill
+```
+
+### 查看已安装技能
+```bash
+ls ~/.openclaw/workspace/skills/ | grep stock
+```
+
+### 更新技能
+```bash
+clawhub update a-stock-trading-assistant
+clawhub update daily-stock-analysis
+clawhub update stock-monitor-skill
+```
+
+---
+
+## 📞 常见问题
+
+### Q1: 数据源从哪里来？
+- **a-stock-trading-assistant**：东方财富、新浪财经、同花顺、雪球
+- **daily-stock-analysis**：Yahoo Finance + 官方披露
+- **stock-monitor-skill**：实时行情 API
+
+### Q2: 支持港股和美股吗？
+- **a-stock-trading-assistant**：仅支持 A 股
+- **daily-stock-analysis**：支持全球股市
+- **stock-monitor-skill**：主要支持 A 股，可配置港股/美股
+
+### Q3: 预警怎么推送？
+- 后台常驻进程运行 `monitor_daemon.py`
+- 可配置微信、钉钉、飞书等推送渠道
+- 建议配合券商 App 使用
+
+### Q4: 预测准确率怎么样？
+- 运行 `calc_accuracy.py` 查看滚动准确率
+- 1 日/3 日/7 日/30 日准确率分别统计
+- 自我进化机制持续提升
+
+---
+
+## 📝 更新日志
+
+| 日期 | 更新内容 |
+|------|----------|
+| 2026-03-13 | 三大技能使用手册首次整理 |
+
+---
+
+*文档由皮皮虾整理 🦐 | 投资有风险，入市需谨慎*