agentleFS
JerryLiu369JerryLiu369/awesome-quant-skills/llms.txt

awesome-quant-skills

llms.txt3 starsChanged 32 days agoMITView on GitHub

A curated directory of agent skills, quant MCP servers, and skill-native systems for quantitative finance, systematic research, and algorithmic trading. For humans and AI agents. Research/education only — not investment advice; default to paper trading and human approval (see SECURITY.md). - skills/<category>/<name>/SKILL.md — 33 mirrored skills, SKILL.md-only excerpts; each file has an Imported from header with its upstream source. Frontmatter always has name + description. - Categories: alpha-factors, backtesting-audit, china-markets, crypto-web3, global-equities, portfolio-risk. - README directory sections (link-only upstream repos,…

The file

Files
llms.txt
# Awesome Quant Skills

> A curated directory of agent skills, quant MCP servers, and skill-native
> systems for quantitative finance, systematic research, and algorithmic
> trading. For humans and AI agents. Research/education only — not investment
> advice; default to paper trading and human approval (see SECURITY.md).

- Repo: https://github.com/JerryLiu369/awesome-quant-skills
- Full guide: README.md (start at Quickstart). License details: NOTICE.md.
- Own curation: MIT. Mirrored skills under `skills/` keep upstream licenses.

## Layout (stable contract)

- `skills/<category>/<name>/SKILL.md` — 33 mirrored skills, `SKILL.md`-only
  excerpts; each file has an `Imported from` header with its upstream source.
  Frontmatter always has `name` + `description`.
- Categories: `alpha-factors`, `backtesting-audit`, `china-markets`,
  `crypto-web3`, `global-equities`, `portfolio-risk`.
- README directory sections (link-only upstream repos, no local copy):
  Vertical Market Stacks (China A-Shares & Futures, Crypto & Web3, US &
  Global Equities), Universal Quant Pipeline (Data Ingestion, Alpha
  Generation, Portfolio & Risk, Backtesting & Safety, Execution & Routing),
  Quant MCP Servers (Market Feeds, Broker Gateways), Skill-Native Frameworks,
  Agent Evaluation & Benchmarks, Miscellaneous. Entries without a `mirrored at`
  note are link-only.
- `NOTICE.md` — the mirror-to-upstream index table (local path, upstream,
  license status). `SECURITY.md` — safe defaults for money-moving tools.

## Compatibility

Skills follow the open `SKILL.md` convention and load in Claude Code,
OpenCode, Codex, Cursor, OpenClaw, Hermes, and other compatible harnesses;
only the install path differs (e.g. `~/.claude/skills/` for Claude Code).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.