Skills for Real Engineers. Straight from my .agents directory.
uzi
Agent skill fromwbh604/UZI-Skill
A-share, Hong Kong, and US stock analysis skill for deep research, quick scans, investor panel review, hot-money/LHB analysis, trap detection, valuation, IC memos, and Bloomberg-style HTML reports.
How to install uzi
npx skills add wbh604/UZI-Skill1# UZI Skill Root23This root file is the top-level entry for agents that expect a `SKILL.md` at the repository root.45Use the narrowest matching workflow:67- Full stock research, valuation, IC memo, initiation, catalysts, earnings review, or HTML report:8 read `skills/deep-analysis/SKILL.md`.9- Investor jury, "which investors would buy", panel-only voting, or persona review:10 read `skills/investor-panel/SKILL.md`.11- Hot-money, LHB, seat recognition, or A-share short-term trader analysis:12 read `skills/lhb-analyzer/SKILL.md`.13- Trap detection, pump-and-dump checks, "teacher/group/friend recommended this stock", or safety review:14 read `skills/trap-detector/SKILL.md`.15- Daily market-event briefs, scheduled macro releases, central-bank speeches, or event-aware alerts:16 read [Official macro calendar verification](references/macro-calendar.md),17 alongside the relevant stock workflow when stock analysis is also requested.18- Command-specific requests:19 read the matching file under `commands/`.2021## Default Execution2223From the repository root:2425```bash26python3 run.py <ticker> --no-browser27```2829For remote/mobile reports:3031```bash32python3 run.py <ticker> --remote33```3435For a single investor school, such as A-share hot-money:3637```bash38python3 run.py <ticker> --school F --no-browser39```4041## Agent Rules42431. Treat scripts as data and scoring tools, not as final analyst judgment.442. Do not invent numbers. Use script outputs, cached JSON, or current public evidence.45…
Excerpt shown under the repository's MIT license.
More skills in UZI-Skill
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
