Luopan skill
Router skill for researching an industry or company: first the goal, investment or career, then a report with source grades
- 392 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Investment attractiveness reports can be mistaken for advice, although the skill places no trades.
- Data goes to the Tencent Securities provider and the chosen model.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/luopanDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Investment attractiveness reports can be mistaken for advice, although the skill places no trades.
- Data goes to the Tencent Securities provider and the chosen model.
This is third-party code. Review the repository files before installing.
What it does
Luopan consists of a root `SKILL.md` and two modes in `modes/`. The root file decides what is being researched, an industry or a company, and loads the matching mode. For a company the agent first asks about the goal: investment, job search or both together. The report rests on A, B, C source grading, cross-checking and a mandatory section on the weak points of the conclusion. Financial data comes from the official Tencent Securities (腾讯自选股) interface. For US companies `modes/company/scripts` holds `sec_fetch.py`, and `render_report.py` builds the report.
Who it is for. Analysts, investors and job seekers who need a structured map of an industry or company in Chinese or English.
Good fit when
- You need to see quickly who holds profit and power along an industry chain.
- You are deciding whether to join a specific company.
- You want a stock review with scenario valuation and a margin of safety.
- An industry and a company are studied in sequence, the second inside the first.
Not a fit when
- You need personal financial advice or a trade signal.
- You require strictly audited reporting rather than a synthesis report.
- You care about depth on the Russian market: the focus is on A-shares, Hong Kong and US.
Example request
Study the AI agent industry, then show where NVIDIA sits in it and assess it from an investment angle.Limitations
The report is not investment advice: valuations rest on scenarios and data that can go stale. Structured data comes from a single provider, Tencent Securities, and coverage of A-shares and Hong Kong is noticeably stronger than the rest. The README and skills are written in Chinese. Tools where installation was verified are listed in the README; others must keep the directory structure. The last commit is from July 2026.
How to disable. Delete the `luopan` directory from your agent's skills directory.
FAQ
Which agents fit?
The README names Workbuddy, Codebuddy, KimiCode and Trae, and abroad Claude Code, Codex and OpenClaw.
Are there scripts?
Yes. `modes/company/scripts` holds `sec_fetch.py` for SEC data and `render_report.py` for building the report.
What if I do not state the goal for a company?
The skill asks once: investment, job or both. Until you answer it searches nothing and builds no report.
What must I keep when installing?
The full directory structure. The root `SKILL.md` only routes and loads subskills from `modes/industry` and `modes/company`.
Where does the data come from?
Structured quotes, financials, valuation and fund flows come from the official Tencent Securities interface. Industry and macro data are cross-checked against primary sources, and each claim carries a source grade.
Discussion
No questions or reviews yet.
Related
SkillsA skill that writes a nine-chapter report on a US, Hong Kong or China stock: reverse DCF, EPV, earnings-quality review and scripted valuation
An investment research skill: from a technology trend to supply-chain bottlenecks and a shortlist of companies worth researching first
A skill that finds bottlenecks in an industry's supply chain and shortlists A-share, Hong Kong and US stocks with data checks
A skill connects agents to FinLab data and its Python engine for stock research and local historical strategy backtesting.
A skill researches supply chains around an investment theme, collects company candidates and builds a dated, source-linked report.
Claude for Financial Services CN
claude-for-financial-services-cn
An unofficial set of 63 skills for Claude Code: DCF, comps, LBO, notes and decks for Chinese equities with Wind, iFind and AkShare data
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Luopan (this card) | no | 392 | |
| Hehe Industry Research Skill Pack | no | 326 | gives 14 skills with a main project skill for open data research; Luopan routes between industry and company and asks for the goal |
| Claude Equity Research | no | 759 | produces equity research reports for Claude Code; Luopan adds an industry mode and an employer evaluation mode |
README in short
The README explains routing, the two modes, three company research goals and the principles: source grading, a skeptic pass and honest caveats.