Stock Data Assistant

What it does

When your agent uses it

• Looking up daily K-line or financial data for A-share, Hong Kong, ETF or index tickers
• Subscribing to live quote pushes for a watchlist
• Letting WeChat messages query a local stock database through picoclaw

Example prompts

• “Pull the recent daily K-line data for Kweichow Moutai (600519.SH).”
• “Start the WeChat bridge and show me the login QR code.”
• “Subscribe to live quotes for 600519.SH over the WebSocket service.”
• “Check the status of the picoclaw bridge.”

Requirements

• A running stock_datasource MCP server (port 8001 by default)
• LLM settings in `.env`, including `OPENAI_API_KEY`
• Internet access to download picoclaw from GitHub Releases
• A WeChat account to scan the login QR code

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1安装 picoclaw
2. 2生成 picoclaw 配置
3. 3启动 picoclaw
4. 4登录微信

What it can do on your machine

Read from SKILL.md and the folder at commit 3d4dbd2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Shell and Python), which the agent can run.

  Shell commands in SKILL.md call:

  • bash
  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.openai.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENAI_API_KEY
  • STOCK_MCP_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Stock Data Assistant loads about 1.2k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 252 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~60

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:48

  2. **生成配置** — 从 `.env` 读取 LLM 配置，生成 `picoclaw.yaml`

• NoteMentions a .env fileSKILL.md:115

  ### LLM 配置（自动从 .env 复用）

• NoteMentions a .env fileSKILL.md:192

  enerate_picoclaw_config.py           # 从 .env 生成配置

• NoteMentions a .env fileSKILL.md:203

  | `OPENAI_API_KEY not set` | 确保 `.env` 文件中有 `OPENAI_API_KEY` 字段 |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Yourdaylight/stock_datasource at commit 3d4dbd2, republished under its MIT licence (© Yourdaylight). 252 words, ~1,229 tokens.

name

stock-data-assistant

description

统一的股票数据助手 Skill，整合： (1) 数据查询 — 通过 MCP 协议查询历史 K 线、财务报表等（A 股/港股/ETF/指数）； (2) 实时搜索 — 通过 WebSocket 订阅实时行情推送（每 3~5 秒更新）； (3) 微信联动 — 通过 picoclaw + WeChat Channel 实现微信端操作数据库和订阅实时数据。 触发此 Skill 时会自动下载 picoclaw、复用项目 LLM 配置、启动微信登录。

┌─────────────┐     ┌──────────────┐     ┌─────────────────┐
│   微信用户    │────▶│  picoclaw     │────▶│ stock-mcp (8001) │
│  (WeChat)   │     │  (LLM Gateway)│     │  历史数据查询     │
└─────────────┘     │  port:18790  │     ├─────────────────┤
                    │  微信 Channel │     │  WS (8765)       │
┌─────────────┐     │              │────▶│  实时行情推送     │
│  Web 前端    │────▶│  MCP Client  │     └─────────────────┘
│  (18080)    │     └──────────────┘
└─────────────┘

bash skills/stock-data-assistant/start_wechat_bridge.sh

# 显示微信登录二维码（扫码后即绑定）
.local/bin/picoclaw auth weixin

# 或者使用完整路径
./.local/bin/picoclaw auth weixin

📱 你: 查一下贵州茅台最近的日K线
🤖 AI: 正在为您查询贵州茅台(600519.SH)的日线数据...

📱 你: 腾讯控股现在价格多少？
🤖 AI: 腾讯控股(00700.HK) 当前价 XXX.XX 港元，涨幅 X.XX%

📱 你: 监控 00700.HK 涨跌超过2%就通知我
🤖 AI: 已设置涨跌幅告警，触发条件：±2.00%

📱 你: 列出今天涨幅最大的10只A股
🤖 AI: 正在筛选今日涨幅榜 Top 10...

bash skills/stock-data-assistant/setup_picoclaw.sh
# 或指定版本
bash skills/stock-data-assistant/setup_picoclaw.sh v0.2.5

python3 skills/stock-data-assistant/generate_picoclaw_config.py
# 自定义参数
python3 skills/stock-data-assistant/generate_picoclaw_config.py \
    --mcp-token sk-your-token-here \
    --output ./my-config.yaml

export PATH=".local/bin:$PATH"
picoclaw run --config .local/picoclaw.yaml

picoclaw auth weixin

# 查看状态
bash skills/stock-data-assistant/start_wechat_bridge.sh --status

# 停止所有服务
bash skills/stock-data-assistant/start_wechat_bridge.sh --stop

# 仅启动（不启用实时订阅）
bash skills/stock-data-assistant/start_wechat_bridge.sh --no-rt

# 指定订阅股票
bash skills/stock-data-assistant/start_wechat_bridge.sh --symbols 00700.HK,600519.SH

skills/stock-data-assistant/
├── SKILL.md                              # 本文档
├── setup_picoclaw.sh                     # 自动下载 picoclaw
├── generate_picoclaw_config.py           # 从 .env 生成配置
├── start_wechat_bridge.sh                # 一键启动脚本
└── references/
    └── picoclaw_config_example.yaml     # 配置示例

© Yourdaylight, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/stock-data-assistant of Yourdaylight/stock_datasource.

• SKILL.md
• generate_picoclaw_config.py
• references/picoclaw_config_example.yaml
• setup_picoclaw.sh
• start_wechat_bridge.sh

Open the folder on GitHubat commit 3d4dbd2