bitwater

Investment Committee

Professionalv1.0.0
By bitwaterUpdated 2026-05-11investment-committee@clawhub_bitwater/investment-committee
Finance#Investment#股票#资产

According to AlphaMoat, as of 2026-09, Investment Committee has 1,797 downloads and 5 stars — ranked #4,581 of 5,078 AI skills overall, and #406 of 465 in Professional.

Installs
229
Downloads
1.8K
Stars
5
Overall Rank
#4,581
Top 91% overall · Top 88% in Professional
PlatformInstallsDownloadsStarsComments
ClawHub ↗271.1K3-
SkillHub ↗2291.8K5—

Platforms count differently and update at different times.

What this skill does

Apply multiple investment-analysis frameworks to stocks, ETFs, crypto assets, gold, and commodities, combining market data and fundamental context into a Chinese committee-style report. Reports may include buy judgments, position sizing, stop-losses, and target prices. Treat these as educational analysis only; independently verify data and conclusions, and do not treat them as personalized investment advice.

Profile published 2026-10-27

What you can do with it

  • Compare investment assets from different analytical perspectives
  • Summarize market data, risks, and framework-based views

When to use it

  • When generating a structured investment analysis report
  • When verifying market-data freshness and the basis for recommendations

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Compare the main risks and analytical views for these assets, and flag conclusions that need further verification.

Monthly Trend

Downloads1.8K
4121.2K1.9K2026-03 · Downloads 5152026-05 · Downloads 1.0K2026-06 · Downloads 1.2K2026-07 · Downloads 1.3K2026-08 · Downloads 1.4K2026-09 · Downloads 1.8K26-0326-09
Stars5
2452026-03 · Stars 22026-05 · Stars 52026-06 · Stars 52026-07 · Stars 52026-08 · Stars 52026-09 · Stars 526-0326-09

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-091.8K—5
2026-081.4K+7.7%5
2026-071.3K+14.4%5
2026-061.2K+12.5%5
2026-051.0K—5
2026-03515—2

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

3.9 KB · ClawHub v1.0.0
---
name: investment-committee
description: 调用由查理·芒格、霍华德·马克斯、段永平、斯坦利·德鲁肯米勒、詹姆斯·西蒙斯组成的投资大师委员会,对任意标的进行多维度独立分析并输出委员会裁决报告。适用场景:(1) 买入判断——「委员会分析腾讯」「大师怎么看英伟达」「帮我分析BTC」;(2) 仓位管理——「我持有半仓BTC,怎么操作」「已持有NVDA,加仓还是减仓」;(3) 比较分析——「腾讯和谷歌选哪个」。支持股票(A/港/美)、ETF、BTC/加密资产、黄金/大宗商品。
---

# Investment Committee Skill

五位大师平权投票(各 20%),并行独立分析,输出中文裁决报告。

## 执行流程
Show all (92 lines)

### Step 1:数据准备

**行情抓取**(优先用脚本,比搜索更准确):
```bash
python3 {workspace}/investment-committee/scripts/fetch_price.py GOOGL 700.hk BTC GOLD
```
> 数据源:stooq.com(免费无限流)。常用映射:`700`→`700.hk`,`NVDA`→`nvda.us`,`BTC`→`btc.v`,`GOLD`/`黄金`→`xauusd`。

**基本面数据**:web_search 补充 PE、Forward PE、分析师目标价、近期财报、宏观事件。

**关键信息清单**(装进所有委员 prompt):
- 价格 + 日涨跌 + 52周区间
- TTM PE / Forward PE(股票)或恐惧贪婪指数(加密)
- RSI / 与200日均线偏差
- 近期重大事件(财报日期、政策、宏观催化剂)
- 若用户有持仓:持仓比例 + 是否已盈亏

### Step 2:识别分析模式

| 用户请求 | 模式 | 重点 |
|---|---|---|
| "分析 XXX" / "要不要买" | **买入判断模式** | 五委员给买入评分 |
| "我持有 X 仓位,怎么办" | **仓位管理模式** | 五委员给操作建议(止损/持有/加仓) |
| "XXX 和 YYY 哪个更好" | **比较模式** | 两标的同时分析,最后比较结论 |

### Step 3:并行召唤五位委员

```
sessions_spawn × 5(同时发出,保证独立性)
```

每个 sub-agent 的 task 格式:
```
你现在扮演 [大师姓名]。

以下是你的投资哲学和分析框架:
[读取对应 references/ 文件全文]

[买入判断模式] 请用你的视角分析以下标的,严格按你的框架输出评分和判断:
[仓位管理模式] 用户当前 [X%] 仓位持有该标的,请从你的框架出发给出仓位管理建议:

标的:[XXX]
当前价格:[YYY]
关键数据:[数据清单]
近期事件:[事件]
[上次你的评分:X/10(若有历史档案)]

输出格式:(按对应 reference 文件的 "输出要求" 一节)
```

**⚠️ 关键约束**:五个 sub-agent 必须独立,不能互相看到结论。

### Step 4:整合裁决

收齐五份结果后,读取 `references/verdict.md` 进行整合:

1. 计算加权综合分(各 20%)
2. 识别最大分歧(分差最大的两位委员)
3. 检查否决规则
4. 提取可直接执行的操作参数(止损价、仓位、加仓条件)
5. 按 `assets/report-template.md` 格式输出
6. 发送到当前 Discord 频道
7. 存档到 `{workspace}/investment-committee/history/YYYY-MM-DD_标的_说明.md`

## 特殊资产权重调整

**加密资产 / 黄金**:芒格和段永平因"无内在价值"天然低分,报告中注明「本标的宏观/量化视角权重更具参考价值」,重点参考马克斯(周期)、德鲁肯米勒(宏观流动性)、西蒙斯(量化信号)。

## 委员角色速查

| 委员 | 核心框架 | Reference 文件 |
|---|---|---|
| 芒格 | 护城河 / 生意本质 / 能力圈 | `references/munger.md` |
| 马克斯 | 周期位置 / 情绪温度 / 风险不对称 | `references/marks.md` |
| 段永平 | 本分 / 动机审查 / 十年持有 | `references/duan.md` |
| 德鲁肯米勒 | 宏观流动性 / 催化剂 / 止损 | `references/druckenmiller.md` |
| 西蒙斯 | 量化五信号 / 动量 / 统计胜率 | `references/simons.md` |

裁决整合规则见 `references/verdict.md`。
报告格式见 `assets/report-template.md`。

Popular in Professional

Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.