openmath-lean-theorem
Configures Lean environments, installs external proof skills, runs preflight checks, and guides the workflow for proving downloaded OpenMath Lean theorems locally.
Best use case
openmath-lean-theorem is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Configures Lean environments, installs external proof skills, runs preflight checks, and guides the workflow for proving downloaded OpenMath Lean theorems locally.
Teams using openmath-lean-theorem should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openmath-len-theorem/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openmath-lean-theorem Compares
| Feature / Agent | openmath-lean-theorem | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Configures Lean environments, installs external proof skills, runs preflight checks, and guides the workflow for proving downloaded OpenMath Lean theorems locally.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# OpenMath Lean Theorem ## Instructions Set up the Lean proving environment, validate toolchains, and prove downloaded OpenMath theorems locally. Assumes the theorem workspace was already created by the `openmath-open-theorem` skill. ### Workflow checklist - [ ] **Environment**: Verify `lean`, `lake`, and `elan` are installed and match the workspace `lean-toolchain`. - [ ] **External skills**: Install required Lean proof skills from [leanprover/skills](https://github.com/leanprover/skills). Preferred manual install: ```bash npx leanprover-skills install lean-proof npx leanprover-skills install mathlib-build ``` If you use preflight auto-install, pass an explicit target such as `--install-dir .codex/skills` or `--install-dir .claude/skills` so the write location is deliberate. - [ ] **Preflight**: Run `python3 scripts/check_theorem_env.py <workspace>` (see [references/preflight.md](references/preflight.md)). - [ ] **Prove**: Use `lean-proof` / `mathlib-build` skills to complete the proof. See [references/proof_playbook.md](references/proof_playbook.md) for the OpenMath-specific proving loop. - [ ] **Verify**: Confirm `lake build -q --log-level=info` passes and no `sorry` remains. - [ ] **Submit**: Use the `openmath-submit-theorem` skill to hash and submit the proof. ### Scripts | Script | Command | Use when | |--------|---------|----------| | Preflight check | `python3 scripts/check_theorem_env.py <workspace>` | After download, before proving; validates toolchain, required skills, and initial build. | | Preflight (auto) | `python3 scripts/check_theorem_env.py <workspace> --auto-install-skills --install-dir <path>` | Auto-install missing Lean skills during preflight into an explicit skills dir. | ### Notes - **Lean version**: Scaffolds pin `leanprover/lean4:v4.28.0` and `mathlib4 v4.28.0` (set by `openmath-open-theorem`'s `download_theorem.py`). - **External skills**: Not bundled. Required: `lean-proof`, `mathlib-build`. Optional: `lean-mwe`, `lean-bisect`, `nightly-testing`, `mathlib-review`, `lean-setup`. Manual `npx leanprover-skills install ...` is preferred; preflight auto-install clones the upstream repo and copies the missing directories into the selected skills dir. - **Benchmarking**: For agent evaluation, prompt comparison, or regression testing on the bundled Lean benchmark corpus, use the separate `openmath-lean-benchmark` skill. ## References Load when needed (one level from this file): - **[references/preflight.md](references/preflight.md)** — Preflight command and Lean/Rocq checks. - **[references/proof_playbook.md](references/proof_playbook.md)** — Step-by-step workflow for proving a downloaded Lean theorem locally. - **[references/languages.md](references/languages.md)** — Lean version and standard library.
Related Skills
Cleaning Business Operations
Commercial and residential cleaning business operations agent. Covers pricing, bidding, staffing, supply costs, insurance, OSHA compliance, quality control, and growth from solo operator to multi-crew company.
diskclean
AI-assisted disk space scanner and cleaner. Finds reclaimable space (node_modules, build caches, package caches, downloads, Docker, Xcode, logs) and intelligently cleans safe items with strict guardrails.
openmath-submit-theorem
Submits proofs to the OpenMath platform using a two-stage commit-reveal flow. Use when the user wants to commit a proof hash or reveal a Lean/Rocq proof on the Shentu network.
openmath-rocq-theorem
Configures Rocq environments, runs preflight checks, and guides the proving workflow for OpenMath Rocq theorems. Use when the user wants to set up Rocq tooling, prove a downloaded OpenMath theorem in Rocq/Coq, or verify and submit a Rocq proof.
openmath-open-theorem
Queries open formal verification theorems from the OpenMath platform. Use when the user asks for a list of open theorems, wants Lean or Rocq-specific theorems, needs full detail for a theorem ID, or wants to download a theorem and scaffold a local proof workspace.
openmath-claim-reward
Claims earned rewards from the OpenMath platform. Use when the user wants to query claimable imported/proof rewards or withdraw verified Shentu rewards after a proof has passed verification.
mac-cleaner
Analyze and safely clean disk space on macOS. Use when the user asks about Mac storage, "System Data" taking too much space, disk cleanup, freeing up space, or managing storage on macOS. Covers caches, iOS simulators, Xcode data, trash, logs, and browser caches. Safe for everyday Mac users.
apple-photos-cleaner
Analyze, clean up, and organize Apple Photos libraries. Find and report junk photos (screenshots, low-quality, burst leftovers, duplicates), analyze storage usage, generate photo timeline recaps, plan smart exports, analyze Live Photos, check iCloud sync, audit shared libraries, detect similar photos, curate seasonal highlights, and score face quality. All analysis operations are READ-ONLY on the database (safe). macOS only. Requires Python 3.9+ (stdlib only) and access to the Apple Photos SQLite database. Trigger on: Photos cleanup, photo storage, duplicate photos, junk photos, screenshot cleanup, Photos analysis, photo timeline, photo export, Photos library stats, burst cleanup, storage hogs, photo organization, Live Photos, iCloud sync, shared library, similar photos, seasonal highlights, face quality, portraits.
dev-machine-cleanup
开发机清理技能 - 异步清理日志和临时文件（不阻塞主会话）
auto-cleaning-disk
Automatically clean disk space by removing temp files, browser cache, recycle bin/trash, and log files — safely, without deleting any important files. Use this skill whenever the user asks to clean their disk, free up space, remove junk files, clear cache, empty trash, or says things like "disk full", "storage is low", "computer is slow", "clean my disk", "remove junk files", or wants to speed up their system. Works on Windows, Linux, and Mac. Always ask user whether to run automatically or with confirmation.
mac-cleanup
Cleans up system caches, trash, and old downloads on macOS.
desktop-cleanup-playbook
为桌面文件生成整理方案、分类规则和阶段性清理计划，先分析再行动。；use for desktop, cleanup, organization workflows；do not use for 自动删除桌面文件, 越权访问系统目录.