# Trade Journal

> 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**。

- **Type:** Skill
- **Install:** `agentstack add skill-zicxr-a-stock-skills-trade-journal`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ZICXR](https://agentstack.voostack.com/s/zicxr)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ZICXR](https://github.com/ZICXR)
- **Source:** https://github.com/ZICXR/A-Stock-Skills/tree/main/skills/02-data-collection/trade-journal
- **Website:** https://github.com/ZICXR/A-Stock-Skills#readme

## Install

```sh
agentstack add skill-zicxr-a-stock-skills-trade-journal
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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

```bash
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`:

```markdown
## 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

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

### 3. 30 天后比对

```bash
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

```bash
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。

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ZICXR](https://github.com/ZICXR)
- **Source:** [ZICXR/A-Stock-Skills](https://github.com/ZICXR/A-Stock-Skills)
- **License:** MIT
- **Homepage:** https://github.com/ZICXR/A-Stock-Skills#readme

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-zicxr-a-stock-skills-trade-journal
- Seller: https://agentstack.voostack.com/s/zicxr
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.