agentleFS
ZICXRZICXR/A-Stock-Skills/skills/00-start-here/SKILL.md

start-here

Skill26 starsChanged 5 months agoMITView on GitHub

30 秒上手指南。A-Stock-Skills 入门必读,5 个实战场景覆盖 90% 的使用需求。当用户问"我该用哪个 skill"、"怎么开始"、"有什么例子" 时,Claude 应优先激活此 Skill。

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

🚀 start-here: 30 秒上手

A-Stock-Skills 只有 10 个 Skill

#Skill解决什么问题
1astock-data-source拿实时行情 / K 线 (多源 fallback)
2astock-cacheK 线 parquet 缓存 (5 秒 vs 30 分钟)
3astock-utils代码转换 / 交易日历 / 工具函数
4watchlist-monitor监控自选股 + 涨跌幅告警
5screener全市场筛选 (PE / 涨幅 / MACD 等)
6stock-technical-analysisMA / MACD / KDJ / RSI / BOLL
7report每日复盘 + 个股研报
8alerter钉钉 / 微信 / 飞书 推送
9trade-journal🆕 AI 建议 vs 实盘 复盘
10start-here🆕 本文档

🎯 5 个真实场景

场景 1: 拿一只股票的行情

python skills/01-infra/astock-data-source/main.py get-realtime --code 601991

场景 2: 拿 60 日 K 线 + 算 MACD

from skills.Stock_Analysis.stock_technical_analysis.main import calc_macd
from skills.Stock_Infrastructure.astock_data_source.main import get_kline

df = get_kline("601991", days=60)
macd = calc_macd(df)
print(macd.tail())

场景 3: 全市场筛选 PE<20 + 涨幅>5%

python skills/05-quant/screener/main.py screen --pe-max 20 --pct-change-min 5

场景 4: 监控自选股

# 1. 生成配置模板
python skills/02-data-collection/watchlist-monitor/main.py init

# 2. 编辑 watchlist.yaml
# 3. 启动监控
python skills/02-data-collection/watchlist-monitor/main.py monitor

场景 5: 复盘 AI 准不准

# 1. 记录今天的 AI 建议
python skills/02-data-collection/trade-journal/main.py record --code 601991 --signal "MACD金叉" --target_price 3.50

# 2. 30 天后比对
python skills/02-data-collection/trade-journal/main.py review

⚠️ 3 件必读

  1. 数据源问题: 住宅 IP 跑东财会被封, astock-data-source v2.0 已自动 fallback
  2. 缓存很重要: 第一次跑慢, 第二次快 100 倍 (用 astock-cache)
  3. AI 不可信, 除非复盘: 用 trade-journal 记录, 30 天后看胜率

🛡️ 免责声明

本项目所有数据来源于公开市场数据, 仅供学习研究使用, 不构成任何投资建议。投资有风险, 入市需谨慎。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.