# wbh604/UZI-Skill

冰冷的钱就这样流进我温暖的口袋-游资（UZI）Skills — 让我们欢迎，股海贼王！66位投资大佬帮你看盘 · 22维数据 × 180条量化规则 × 17种机构分析方法 · A股/港股/美股

Repository: https://github.com/wbh604/UZI-Skill
Canonical: https://ross.abutalabs.com/products/uzi-skill
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-16T16:53:17+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 89, longevity 9
- inputs: {"age_days": 139, "days_push": 17, "days_rel": 72, "gap_med": 0.0, "n_releases_24m": 49}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6591, forks 929 (observed 2026-08-28T04:09:45.516281+00:00)

## What it is
UZI-Skill is a Python-based AI agent skill/plugin that performs deep stock analysis for A-share, Hong Kong, and US markets using 22 data dimensions, 242 quantitative rules, 22 institutional analysis methods, and a simulated panel of 66 famous investors. It installs into agents like Claude Code, Codex, Cursor, and Gemini CLI, or runs standalone via CLI.

## Use cases
- deep analysis of a single stock before buying
- quick 30-second scan of a stock ticker
- detect pump-and-dump / pig-butchering stock traps
- run DCF valuation on a specific company
- get investment-style opinions from famous investors like Buffett on a stock
- screen stocks with quantitative rules across A-shares, HK, and US markets

## When to choose
- you use an AI coding agent (Claude Code, Cursor, Codex) and want stock analysis as a skill
- you want multi-perspective institutional-style analysis of individual stocks in Chinese markets
- you need quick scam/trap screening for suspicious stocks

## When to avoid
- you need real-time trading execution or automated order placement
- you want passive fund or fund-manager analysis (use the companion jilao-skills instead)
- you require guaranteed financial accuracy - outputs are AI-generated analysis, not investment advice

## Facets
- artifact type: plugin
- maturity: active
- function: analytics, data-science, developer-tools, agent-framework, prompt-engineering
- domain: fintech, analytics, artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: stock-analysis, quantitative-rules, multi-agent-panel, a-shares, hong-kong-stocks, us-stocks, dcf-valuation, claude-code-plugin, investment-analysis, ai-skill

## Member repositories
- wbh604/UZI-Skill (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.516281+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:43:33.965531+00:00, confidence not recorded.
  - readme: https://github.com/wbh604/UZI-Skill (fetched 2026-08-28T04:09:45.516281+00:00, sha 3a171c0eacba)
- Data as of 2026-08-30T08:39:29.467469+00:00.