UZI Skill Root
This root file is the top-level entry for agents that expect a SKILL.md at the repository root.
Use the narrowest matching workflow:
- Full stock research, valuation, IC memo, initiation, catalysts, earnings review, or HTML report:
read
skills/deep-analysis/SKILL.md.
- Investor jury, "which investors would buy", panel-only voting, or persona review:
read
skills/investor-panel/SKILL.md.
- Hot-money, LHB, seat recognition, or A-share short-term trader analysis:
read
skills/lhb-analyzer/SKILL.md.
- Trap detection, pump-and-dump checks, "teacher/group/friend recommended this stock", or safety review:
read
skills/trap-detector/SKILL.md.
- Command-specific requests:
read the matching file under
commands/.
Default Execution
From the repository root:
python3 run.py <ticker> --no-browser
For remote/mobile reports:
python3 run.py <ticker> --remote
For a single investor school, such as A-share hot-money:
python3 run.py <ticker> --school F --no-browser
Agent Rules
- Treat scripts as data and scoring tools, not as final analyst judgment.
- Do not invent numbers. Use script outputs, cached JSON, or current public evidence.
- For serious deep-analysis requests, complete the agent review loop described in
skills/deep-analysis/SKILL.md before final report assembly.
- For hot-money analysis, apply LHB seat matching and
is_in_range() before making a short-term judgment.
- For trap detection, scan all eight signals and include concrete evidence when risk is non-trivial.
- For report template or UI changes, update tests, version metadata, and release notes together.
1---2name: uzi3description: UZI stock-research suite root. Use when the user mentions UZI, UZI-Skill, deep stock research, valuation, investor panel, hot-money/LHB analysis, trap detection, IC memo, Bloomberg-style equity research, A-share, HK, or US stock analysis.4license: MIT5---678# UZI Skill Root910This root file is the top-level entry for agents that expect a `SKILL.md` at the repository root.1112Use the narrowest matching workflow:1314- Full stock research, valuation, IC memo, initiation, catalysts, earnings review, or HTML report:15 read `skills/deep-analysis/SKILL.md`.16- Investor jury, "which investors would buy", panel-only voting, or persona review:17 read `skills/investor-panel/SKILL.md`.18- Hot-money, LHB, seat recognition, or A-share short-term trader analysis:19 read `skills/lhb-analyzer/SKILL.md`.20- Trap detection, pump-and-dump checks, "teacher/group/friend recommended this stock", or safety review:21 read `skills/trap-detector/SKILL.md`.22- Command-specific requests:23 read the matching file under `commands/`.2425## Default Execution2627From the repository root:2829```bash30python3 run.py <ticker> --no-browser31```3233For remote/mobile reports:3435```bash36python3 run.py <ticker> --remote37```3839For a single investor school, such as A-share hot-money:4041```bash42python3 run.py <ticker> --school F --no-browser43```4445## Agent Rules46471. Treat scripts as data and scoring tools, not as final analyst judgment.482. Do not invent numbers. Use script outputs, cached JSON, or current public evidence.493. For serious deep-analysis requests, complete the agent review loop described in `skills/deep-analysis/SKILL.md` before final report assembly.504. For hot-money analysis, apply LHB seat matching and `is_in_range()` before making a short-term judgment.515. For trap detection, scan all eight signals and include concrete evidence when risk is non-trivial.526. For report template or UI changes, update tests, version metadata, and release notes together.
liujiayi3703