CLAUDE.mdA

CLAUDE.md from wbh604/uzi-skill is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.

Install it, pinned

mdr add wbh604/uzi-skill/CLAUDE.md@git:20260807.22e65f2

Pins git:20260807.22e65f2 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 14 of 14 checks passed
Kind: CLAUDE.md file
Repository: wbh604/uzi-skill
Path: CLAUDE.md
Versions recorded: 5
Latest version: git:20260807.22e65f2, committed Aug 7, 2026
First version recorded: Apr 18, 2026
Size: 2,125 bytes
Repository stars: 7,536
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# UZI-Skill · Claude Code Context

> 本文件供 Claude Code 自动读取，提供项目上下文。

## 这是什么

一个股票深度分析 plugin。用户说"分析 XXX"时，你应该自动触发 `deep-analysis` skill。

## 核心技能

| Skill | 触发条件 | 说明 |
|---|---|---|
| `deep-analysis` | 用户提到"分析/研究/估值/DCF/值不值得买"等 | 22维数据 + 66评委 + Bloomberg报告 |
| `investor-panel` | 用户要求"只看评委/大佬怎么看" | 单独跑投资者面板 |
| `lhb-analyzer` | 用户提到"龙虎榜/游资/营业部" | 龙虎榜专项分析 |
| `trap-detector` | 用户提到"杀猪盘/有没有问题/安全吗" | 杀猪盘检测 |

## 工作流 · 深浅两档（v2.10.6 · v3.9.4 强化）

**快速路径（默认）**：用户说"分析/看看"、或 lite/medium 档时，走 CLI 直跑。
```
python3 run.py <ticker> --depth lite --no-browser   # 30-60s
# 或
python3 run.py <ticker> --depth medium --no-browser # 2-4min，默认完整度
```
lite/medium 档 `agent_analysis.json` 缺失自动降级 warning，照样出 HTML。**不需要 role-play 66 评委**。

**深度路径（deep 档必须走）**：当用户要 `--depth deep`、DCF / IC memo / 首次覆盖 / 投委会备忘录等深度产物时，**你必须介入 role-play，不能只跑 CLI**：
1. `stage1()` — 脚本采集数据 + 规则引擎骨架分
2. **你介入（必走）** — 读 `panel.json` + `personas/*.yaml`，以 66 评委身份逐个分析当前股票，写 `agent_analysis.json`（含 `per_investor_override`）
3. `stage2()` — 自动合并你的 role-play 成果，生成报告

> ⚠️ **deep 档不要直接 `python run.py <ticker> --depth deep` 一把梭**——那是纯规则输出。deep 的意义就在于你代入角色做判断。见 AGENTS.md 路径判断表。

详细流程见 `AGENTS.md` / `skills/deep-analysis/SKILL.md`。

## 重要文件
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add wbh604/uzi-skill/CLAUDE.md@sha256:d414b699fd753368

The line at the top of this page pins the label git:20260807.22e65f2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_dlbznmiimrro4fr6.svg)](https://markdownregistry.com/a/art_dlbznmiimrro4fr6)

8 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Apr 18, 2026 and Aug 7, 2026, about one every 28 days.

version	committed	commit	size	audit
git:20260807.22e65f2 latest	2026-08-07	22e65f2	2,125 B	A	view · diff
git:20260611.4d6c595	2026-06-11	4d6c595	1,741 B	A	view · diff
git:20260604.4980b6a	2026-06-04	4980b6a	1,741 B	A	view · diff
git:20260603.6e3af6d	2026-06-03	6e3af6d	1,741 B	A	view · diff
git:20260418.d2537d5	2026-04-18	d2537d5	1,741 B	A	view

Audit of the latest version

A 14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Size between 200 bytes and 200 KB (2125 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

wbh604/uzi-skill · 7,536 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dlbznmiimrro4fr6
GET https://markdownregistry.com/api/v1/resolve?ref=wbh604/uzi-skill/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/d414b699fd753368d4db163a1c8461af0eff0b29937a38bc2bca4d1a5b4a4ff5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.

More from wbh604/uzi-skill

AGENTS.md AGENTS.md file

wbh604/uzi-skill · AGENTS.md

git:20261105.cd2eefd · audit A · 7,536 stars

uzi SKILL.md skill

wbh604/uzi-skill · SKILL.md · A-share, Hong Kong, and US stock analysis skill for deep research, quick scans, investor panel review, hot-money/LHB…