
Lean 4 Skills
PluginLean 4 theorem-proving plugin with workflows to draft, formalize, prove, disprove, review and golf proofs, plus mathlib search, axiom checks and safety guardrails, helping mathematicians and teachers produce machine-checked proofs. Needs Lean 4 and mathlib; pairs well with lean-lsp-mcp.
Lean 4 Skills
Lean 4 workflow pack for AI coding agents. Gives your agent a structured prove/review/golf loop, mathlib search, axiom checking, and safety guardrails. The workflows are host-agnostic — Claude Code, Codex, Gemini CLI, Cursor, and others all use the same core skill; only the invocation surface differs.
Quick Start
| Host | Recommended installation | What you get | Details |
|---|---|---|---|
| Claude Code | Native plugin (Tier 3) | Skill + /lean4:* commands, hooks, guardrails, subagents, helper runtime | Claude Code |
| Codex | Native plugin (Tier 3) | Skill + trusted hooks + absolute-path helper runtime; no /lean4:* parity | Codex |
| Other Agent Skills hosts (Gemini, Antigravity, Copilot, Cursor, Windsurf, OpenCode, …) | Skill-only quick install | Instructions + references (documented, not CI-verified) | Installation guide |
| Any host, full runtime | Portable checkout (Tier 2) | Skill + wrappers + helper scripts | Portable |
Claude Code (run in chat):
/plugin marketplace add cameronfreer/lean4-skills
/plugin install lean4
Codex (in your shell):
codex plugin marketplace add cameronfreer/lean4-skills --ref main
codex plugin add lean4@lean4-skills
Host-native skill installers generally provide the instructions and references only. Use the portable runtime when you also need the bundled wrappers and scripts; Claude Code and Codex provide native full-plugin installations.
Workflows
| Workflow | Description |
|---|---|
| draft | Draft Lean declaration skeletons from informal claims |
| formalize | Interactive formalization — drafting plus guided proving |
| autoformalize | Autonomous end-to-end formalization from informal sources |
| prove | Guided cycle-by-cycle theorem proving |
| autoprove | Autonomous multi-cycle proving with explicit stop budgets |
| disprove | Guided counterexample search with certified refutation |
| checkpoint | Save point (per-file + project build, axiom check, commit) |
| review | Read-only quality review |
| refactor | Leverage mathlib, extract helpers, simplify proof strategies |
| golf | Improve proofs for directness, clarity, performance, and brevity |
| learn | Interactive teaching and mathlib exploration |
| diagnose | Diagnostics and migration help |
Claude Code: invoke as /lean4:<name>. Other hosts: follow the corresponding workflow in SKILL.md.
Typical session: draft (or formalize / autoformalize) → prove (or autoprove) → review → refactor → golf → checkpoint → git push. Use disprove instead of prove to refute a statement rather than prove it.
CLI-like inputs to the seven parameter-heavy commands are validated by a host-agnostic parser — see the Command Invocation Contract.
The Shared Proof Cycle
The proving workflows (prove, autoprove, formalize, and autoformalize) share one cycle — Plan → Work → Checkpoint → Review → Replan → Continue/Stop — where each sorry gets a mathlib search, tactic attempts, and validation, and being stuck forces a review + replan. Statement and header changes belong to the synthesis workflows (formalize / autoformalize); prove and autoprove keep declaration headers immutable. Editing .lean files without a command runs one bounded pass — fix the immediate issue, then hand off to the right workflow — with the Blocked-Goal Triage loop for a goal that resists it. Details: cycle-engine.md.
Verification
CI gates every PR: full documentation lint, semantic contract suites, hook and wrapper runtime tests on Linux and macOS Bash 3.2, and pinned shellcheck/ruff/mypy/actionlint. Hosts marked "documented" in the Quick Start table follow verified setup patterns but are not CI-tested.
Lean LSP MCP (Optional, Recommended)
The skill works standalone, but pairs best with lean-lsp-mcp: live goal inspection, mathlib search, and typically much faster feedback than repeated full builds. See INSTALLATION.md → MCP Server for registration on any host, including the Claude Code scope trade-off for subagent visibility.
Documentation
- INSTALLATION.md — installation tiers, host sections, MCP setup
- SKILL.md — core skill reference
- Commands — command documentation
- References — cycle engine, mathlib style, proof golfing, tactic patterns, grind, metaprogramming, and more
- lean4-contribute — opt-in helper for filing bug reports, feature requests, and insights from your editor
- CHANGELOG.md — version history
- MIGRATION.md — migrating from v3 (Claude Code)
Contributing
Issues and PRs welcome at https://github.com/cameronfreer/lean4-skills. With the lean4-contribute plugin installed, your agent may suggest filing bug reports, feature requests, or insights at natural stopping points — drafting starts only after you opt in, and every draft is shown in full before anything is sent.
License & Citation
MIT licensed. See LICENSE for more information.
Citing this repository is highly appreciated but not required by the license. See also CITATION.cff.
@software{lean4-skills,
author = {Cameron Freer},
title = {Lean 4 {Skills}: Theorem proving skill and workflow pack for {AI} coding agents},
url = {https://github.com/cameronfreer/lean4-skills},
month = oct,
year = {2025}
}
Похожие ресурсы

lean-lsp-mcp
MCPMCP server for the Lean 4 theorem prover: lets agents read proof goals, diagnostics and definitions and search theorems via LeanSearch and Loogle, helping mathematicians and students with formal proofs. Needs uv and the Lean toolchain; run it from the Lean project root.
oOo0oOo/lean-lsp-mcp530
Math Olympiad
PluginOfficial Anthropic plugin that solves competition math such as IMO and Putnam problems, with adversarial checks by an independent verifier that only sees the clean proof. Gives up explicitly rather than bluffing when unsure, and outputs LaTeX/PDF once verified.
anthropics/claude-plugins-official40.1k
Jupyter Book
CLIBuilds Markdown and Jupyter notebooks into online textbook sites with a TOC, math, citations and cross-references, plus publication-quality PDF export; popular for course notes. A Jupyter subproject installed via pipx or npm; PDF export needs Typst or LaTeX.
jupyter-book/jupyter-book4.3k
Math Modeling Skill
SkillA three-stage workflow for math modeling contests like MCM/ICM and CUMCM: analysis, solving and plotting in Python or MATLAB, and a Word (optionally LaTeX) paper, with stage-check subagents and OpenAlex plus AnySearch literature search. Generated papers are for reference only.
XiaoMaColtAI/math-modeling-skill1.9k
Manim Skills
SkillBreaks a rough explanation idea into a scene-by-scene storyboard, then writes animation code following best practices for Manim Community or 3Blue1Brown's ManimGL, for math and physics explainers in class demos and educational videos. Needs Python, FFmpeg and LaTeX installed locally.
adithya-s-k/manim_skill1.2k
Math Modeling Skills
SkillTwo skills for the MCM/ICM and China's CUMCM math modeling contests: solver breaks down problems, picks models from a 95+ scenario decision matrix and gives Python or MATLAB templates; paper coaches abstracts, model validation and formatting from winning papers. Needs Python or MATLAB.
Lupynow/math-modeling-skills423