Summary
66 位投资大佬评审团。给定一只股票的 dimensions.json 和 raw_data.json,让 66 位投资者各自按自己的方法论打分并输出 Pydantic Signal(signal/confidence/score/verdict/comment)。覆盖经典价值派、成长投资派、宏观对冲派、技术趋势派、中…
wbh604/uzi-skill
66 位投资大佬评审团。给定一只股票的 dimensions.json 和 raw_data.json,让 66 位投资?
npx skills add wbh604/uzi-skill --skill investor-panel
66 位投资大佬评审团。给定一只股票的 dimensions.json 和 raw_data.json,让 66 位投资者各自按自己的方法论打分并输出 Pydantic Signal(signal/confidence/score/verdict/comment)。覆盖经典价值派、成长投资派、宏观对冲派、技术趋势派、中…
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Board meeting preparation, investor updates, and executive communication.
1.6K installsCreate and update pitch decks, one-pagers, investor memos, accelerator applications, financial …
8.5K installsDraft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications fo…
8.3K installsSEC 13F fund-manager–centric view via Longbridge — top-50 active institutional investors by AUM…
509 installsRouter skill for LLMQuant investor-lens workflows. Use when the user wants an investor-style re…
412 installsManage investor communications, pitch materials, and fundraising processes
210 installsOther skills from wbh604/uzi-skill.
npx skills add wbh604/uzi-skill
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Parsed from SKILL.md frontmatter.
Files included with this skill beyond the listing page.
SKILL.md
4,431 B
SUMMARY.md
508 B
读取以下输入:
.cache/{ticker}/dimensions.json — 19 维评分.cache/{ticker}/raw_data.json — 原始数据scripts/lib/investor_db.py — 65 人元数据scripts/lib/seat_db.py — 22 位游资射程规则输出:
.cache/{ticker}/panel.json — 50 个 Signal + 投票统计每个投资者必须返回严格 JSON:
{
"investor_id": "buffett",
"name": "巴菲特",
"group": "A",
"avatar": "avatars/buffett.svg",
"signal": "bullish | neutral | bearish",
"confidence": 87,
"score": 82,
"verdict": "强烈买入 | 买入 | 关注 | 观望 | 等待 | 回避 | 不达标 | 不适合",
"reasoning": "1-3 句具体逻辑",
"comment": "用该投资者语言风格的金句 1-2 句",
"pass": ["..."],
"fail": ["..."],
"ideal_price": 16.20,
"period": "3-5 年"
}
Confidence 校准规则:
from lib.investor_db import INVESTORS, by_group
from lib.seat_db import SEATS, is_in_range
fields 白名单对 22 位游资,先用 isinrange(nickname, ticker_features) 判断是否在射程内:
signal: "neutral", verdict: "不适合", confidence: 90, comment: "{nick}的射程是{style},这只票不在风格内。"{
"panel_consensus": (bullish_count / 50) * 100,
"vote_distribution": Counter(verdict for i in investors),
"signal_distribution": Counter(signal for i in investors),
"investors": [...]
}
按需读取下列 references:
| 组 | 文件 | 人数 |
|---|---|---|
| A 经典价值 | references/group-a-classic-value.md |
6 |
| B 成长投资 | references/group-b-growth.md |
4 |
| C 宏观对冲 | references/group-c-macro-hedge.md |
5 |
| D 技术趋势 | references/group-d-technical.md |
4 |
| E 中国价投 | references/group-e-china-value.md |
6 |
| F 游资 | references/group-f-china-youzi.md |
22 |
| G 量化系统 | references/group-g-quant.md |
3 |
每次生成 comment 之前必须读 references/quotes-knowledge-base.md 查找该投资者的真实公开原话和"风格"字段。这是知识库 single source of truth。
每位投资者的 comment 字段必须像他本人:
每组 reference 文件末尾有 3-5 句真实公开语录作为 few-shot。