scottnarmstrong/leanautoformalizationskills/lean-workflow
Claude Code and agent skill by scottnarmstrong/leanautoformalizationskills
- community
Checking that the SKILL.md file is still in the repository.
Route Lean 4 work through a repository's Mathlib/Lake conventions. Use when editing Lean files, checking source fidelity or axioms, searching dependencies, validating focused targets, or protecting dependency build artifacts.
Install
npx vskill@latest install scottnarmstrong/leanautoformalizationskills/lean-workflowSKILL.md
Lean workflow
Use this as the general router for a Lean 4 repository built with Lake and Mathlib. Read the repository's own instructions first; they override generic commands and thresholds here. Select a more focused sibling skill when it applies:
lean-project-architecturefor public declarations, abstractions, module boundaries, or imports;lean-search-discoverybefore attempting a new proof;lean-proof-patternswhile translating or repairing a proof;lean-naming-stylefor declarations, files, namespaces, and docstrings;lean-elaborationfor measured performance diagnosis or repair;lean-elaboration-testfor a repository-wide performance snapshot;lean-statement-auditfor exact source-to-declaration correspondence;lean-orchestratorfor an explicitly authorized multi-agent formalization effort.
Use build-proof-dependency-graph for a source-level proof dependency database. It records source topology; it does not determine Lean proof status.
Build and dependency hygiene
- Treat pinned dependencies and their compiled artifacts as read-only during routine project work.
- Never delete dependency
.olean,.ilean, trace, hash, IR, or object files as an invalidation shortcut. - Follow repository-provided build wrappers and cache guards. Otherwise validate the narrowest project target that covers the edit, for example
lake build Project.Foo.Bar. - Do not run
lake clean, update the toolchain or dependency pins, or trigger a full dependency rebuild without explicit authorization. - Before a destructive project-artifact invalidation, resolve the exact project-owned path and confirm that no dependency tree can match it.
- Distinguish project compilation from dependency compilation in build and performance reports.
Workflow
- Read
AGENTS.mdorCLAUDE.md, the Lake configuration, toolchain file, target module, and nearby imports. - Identify the authoritative mathematical source when a declaration represents an external claim. Preserve its binders, carriers, quantifiers, hypotheses, constants, and endpoint conditions.
- Search Mathlib and the project before adding a declaration or inventing a proof route.
- Do not move proof obligations into hypotheses, introduce custom axioms, or disguise unfinished proofs. Keep any explicitly authorized draft theorem quarantined and visibly marked under the repository's draft policy.
- Make the smallest coherent edit and validate it with the repository's guarded command or the narrowest appropriate Lake/Lean command.
- Audit affected public declarations for
sorry, custom axioms, hidden stronger hypotheses, quantifier drift, and constant-dependence drift. Run#print axiomsfrom an untracked probe or other repository-approved audit path, not from a compiled source file. - Report exact commands and targets, skipped validation, remaining placeholders, and source mismatches.
If work is delegated, obey the repository's agent policy and give each worker a bounded, disjoint task. Do not infer a model requirement, concurrency policy, or permission to spawn agents from this skill.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/lean-workflow/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/scottnarmstrong/leanautoformalizationskills/lean-workflow)