← 返回 Skills 市场
chenjianghua117

A Stock Watcher

作者 chenjianghua117 · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
552
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install a-stock-watcher
功能描述
提供基于多数据源的A股实时行情查询、价格预警、技术分析及智能投顾服务，含自动化报告和风险评估功能。
使用说明 (SKILL.md)

A 股盯盘技能 - 多数据源增强版

基于东方财富/腾讯财经/新浪财经的 A 股实时监控技能。

功能

基础功能

  • 📈 实时查价 - 获取 A 股实时行情（延迟 5-15 秒）
  • 🔔 价格预警 - 设置目标价，触发时提醒
  • 🔄 持续监控 - 后台线程，可设刷新频率
  • ⚠️ 风险提示 - 暴涨/暴跌/高波动预警
  • 💡 操盘建议 - 基于简单规则的操盘参考

技术分析 (新增) ✨

  • 📊 20+ 技术指标 - MA/EMA/RSI/MACD/KDJ/BOLL/DMI/CCI/WR/ROC/OBV
  • 📈 趋势分析 - 多周期均线系统 (5/10/20/60 日)
  • 💹 动量指标 - RSI 超买超卖、MACD 金叉死叉
  • 📉 波动分析 - 布林带位置、ATR 波动率
  • 📦 成交量分析 - 放量/缩量判断
  • 📝 综合报告 - 一键生成技术分析报告

自动化报告 (新增) ✨

  • 📰 每日收盘报告 - 市场概览 + 个股详情 + 最佳/最差表现
  • 💼 持仓股票日报 - 持仓盈亏 + 成本对比 + 汇总统计
  • ⚠️ 异动股票监控 - 涨跌幅异常 + 成交量异常自动识别
  • 🔔 价格预警推送 - 目标价触发自动通知（钉钉）

智能投顾 (新增) ✨

  • 📊 风险评估问卷 - 5 题测评，生成风险画像（保守/稳健/平衡/积极/激进）
  • 💡 资产配置建议 - 基于风险等级，推荐股债配比
  • 🛑 止损止盈计算 - 基于波动率动态计算，风险收益比优化
  • 📈 估值分析 - PE 相对估值法，PEG 成长性估值
  • 📊 投资组合优化 - 现代投资组合理论，风险平价配置

数据源架构

优先级 数据源 延迟 支持市场 状态
主 东方财富 API 1-3 秒 A 股、基金、债券 ✅ 优先
备 腾讯财经 API 5-15 秒 A 股、港股、美股、期货 ✅ 备用
降 新浪财经 API 5-20 秒 A 股 ✅ 降级

数据源特点

项目 说明
免费性 完全免费，无需注册/积分/API Key
实时性 主数据源延迟 1-3 秒
智能切换 自动故障转移，保证高可用
支持市场 A 股为主，支持港股/美股扩展

使用方法

基础指令

查询行情

查询 600036 行情

设置预警

盯盘 600036 涨至 35 元
盯盘 000858 跌至 180 元

查看任务

查看盯盘任务

停止监控

停止盯盘 600036

风险提示

600036 风险提示

操盘建议

600036 操盘建议

技术分析指令 (新增) ✨

完整技术分析报告

600036 技术分析

查看技术指标

600036 指标

自动化报告指令 (新增) ✨

每日收盘报告

收盘报告

或

日报

持仓股票日报

持仓报告

管理自选股

添加到自选 600036 招商银行

设置持仓

设置持仓 002892 成本 10.5 数量 1000 科力尔

设置价格预警

设置预警 600036 涨至 40 元
设置预警 600036 跌至 35 元

智能投顾指令 (新增) ✨

风险评估

风险评估

查看问卷后提交答案：

风险评估 3,3,3,4,3

止损止盈计算

止损止盈 入场价 10.5 当前价 11.2 仓位 10000

估值分析

估值分析 600036 PE 15 行业 PE 20 增长 15

投资组合优化

投资组合

或

资产配置

依赖

  • Python 3.x
  • requests

风险提示

⚠️ 重要声明：

  • 本技能提供的信息仅供参考，不构成投资建议
  • 股市有风险，投资需谨慎
  • 数据存在延迟，请以交易所实时数据为准
  • 请勿仅凭本技能建议进行投资决策

作者

AI 贾维斯 for Windy

安全使用建议
This skill appears coherent for a stock-watcher: it fetches market data from public Chinese finance APIs, computes technical indicators, creates reports and charts, and stores a local config/cache (stock_config.json, cache/, charts/). Before installing, note: (1) it will make outbound HTTP requests to eastmoney/tencent/sina — ensure that network egress is acceptable in your environment; (2) it writes files to the runtime directory (config, cache, charts) — review/contain where it runs if you care about file placement; (3) notification/push behavior (DingTalk) may require you to configure a webhook or credentials — inspect notification.py and the config before enabling push channels; (4) there is no automated installer, so the environment must have Python 3.x and the requests package. If you want extra assurance, review notification.py and any omitted files for any hardcoded webhooks or external endpoints before enabling the skill in an autonomous agent.
功能分析
Type: OpenClaw Skill Name: a-stock-watcher Version: 1.0.0 The skill bundle provides a comprehensive stock analysis and monitoring toolset, including technical indicators, portfolio optimization, and automated reporting. It is classified as suspicious primarily due to a hardcoded DingTalk user ID ('235135121537852951') found in 'auto_report.py' and 'notification.py'. This default configuration causes automated reports—which may contain sensitive information about a user's stock holdings, costs, and portfolio performance—to be sent to this specific ID by default. While the background monitoring threads in 'a_stock_watcher.py' and network requests to financial APIs (Tencent, Sina, EastMoney) are consistent with the stated purpose, the hardcoded notification target poses a significant data privacy risk.
能力评估
✓ Purpose & Capability
Name/description (A 股盯盘、技术分析、报告、投顾) match the included Python modules and SKILL.md. All required network endpoints (eastmoney, tencent, sina) are consistent with obtaining market data; included modules (charting, historical data, auto-report, investment advisor) are proportionate to the stated functionality.
✓ Instruction Scope
SKILL.md describes user commands and notes dependencies (Python, requests). It does not instruct the agent to read unrelated system files or request secrets. The runtime code performs expected actions: HTTP requests to public finance APIs, local caching/config reads and writes, generating reports/charts, and background monitoring. No broad or unclear instructions that would grant the agent extra data collection beyond the stated purpose.
ℹ Install Mechanism
No install spec provided (instruction-only at registry level) but the package includes Python code. The SKILL.md lists Python 3.x and requests; there is no automated installer. That is safe but means the runtime environment must have Python and requests available. No downloads from untrusted URLs or obscure installers were observed.
✓ Credentials
The skill declares no required environment variables or primary credential. The code does not request AWS/other platform credentials. Default config contains a dingtalk_user_id string but no secret tokens were required by SKILL.md. Overall requested environment access is proportionate to functionality.
ℹ Persistence & Privilege
The skill creates and uses local files: stock_config.json (config), cache/stock_cache.json (cache), and charts/ (images or placeholders). It reads/writes these in its package/runtime directory. 'always' is false and the skill does not attempt to modify other skills or system-wide settings. Users should expect local disk writes and consider where the agent will run.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install a-stock-watcher
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /a-stock-watcher 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
A 股盯盘技能 1.0.0 发布，支持多数据源与智能投顾。 - 新增20+技术分析指标与一键技术分析报告功能 - 支持自动化每日收盘、持仓股票等报告生成 - 新增涨跌幅/成交量异常自动监控预警 - 智能投顾：风险测评、资产配置建议、止损止盈与估值分析 - 升级数据源架构，主用东方财富，自动切换腾讯/新浪，保障高可用 - 丰富指令集，支持盯盘、技术分析、投顾需求
元数据
Slug a-stock-watcher
版本 1.0.0
许可证 —
累计安装 4
当前安装数 4
历史版本数 1
常见问题

A Stock Watcher 是什么？

提供基于多数据源的A股实时行情查询、价格预警、技术分析及智能投顾服务，含自动化报告和风险评估功能。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 552 次。

如何安装 A Stock Watcher？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install a-stock-watcher」即可一键安装，无需额外配置。

A Stock Watcher 是免费的吗？

是的，A Stock Watcher 完全免费（开源免费），可自由下载、安装和使用。

A Stock Watcher 支持哪些平台？

A Stock Watcher 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 A Stock Watcher？

由 chenjianghua117（@chenjianghua117）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论