llms.txt · git:20261020.587ceba · 2026-10-20 · sha256 34f812e67cd6e7e3
llms.txt git:20261020.587cebaA
Immutable. This exact content never changes and is served at /api/v1/blob/34f812e67cd6e7e3.
# 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).