agentleFS
ZICXRZICXR/A-Stock-Skills/skills/02-data-collection/trade-journal/SKILL.md

trade-journal

Skill26 starsChanged 5 months agoMITView on GitHub

AI 建议 vs 实盘 复盘工具。当用户说"今天/本周/本月 复盘"、"AI 推荐的准不准"、"交易记录"、"实盘对比" 时使用。本 Skill 记录 AI 信号 + 实际成交 + 30 天后表现,跑 1 个月后能算出"AI 推荐胜率"。**核心价值:让 AI 对自己的建议负责**。

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

trade-journal: AI vs 实盘 复盘

何时使用

  • 用户做了交易,想记录"AI 当时怎么说"
  • 周/月复盘,看 AI 推荐准不准
  • 想积累历史数据,看"AI 推荐的 4 只,30 天后涨跌幅 vs 沪深 300"

核心理念

AI 信号 → 记录 → 30 天后比对 → 算胜率
                                    ↓
                          3 个月后知道 AI 准不准

快速使用

1. 记录 AI 建议

python main.py record --code 601991 --signal "MACD金叉+站上MA20" --action buy --target_price 3.50

输出 journal/2026-06-22.md:

## 2026-06-22 14:30
- 代码: 601991 大唐发电
- AI 信号: MACD金叉+站上MA20
- 建议操作: buy
- 目标价: 3.50 (+9%)
- 当前价: 3.20

2. 记录实盘

python main.py fill --code 601991 --price 3.21 --shares 6200

3. 30 天后比对

python main.py review

输出:

📊 30 天复盘
| 代码 | AI 建议 | 实盘买入 | 30 天后 | 盈亏 | AI 准? |
|------|---------|---------|--------|------|--------|
| 601991 | 3.20 | 3.21 | 3.85 | +19.9% | ✅ 准 |

4. AI 胜率统计

python main.py stats

输出:

🎯 AI 信号胜率 (近 90 天)
- 总推荐: 24 次
- 命中 (涨幅>5%): 14 次
- 胜率: 58.3%
- 平均收益: +4.2%
- vs 沪深 300: +1.8%

数据格式

journal/ 目录:

journal/
├── 2026-06-22.md      # 每日记录
├── 2026-06-23.md
└── _stats.json         # 自动统计

哲学

AI 不可信, 除非它愿意被复盘

这个 Skill 是 A-Stock-Skills 的"问责机制"。 不积跬步无以至千里, 跑 3 个月您就知道 AI 准不准。

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.