agentleFS
Sign inStart free
r-irber-irbe/proof-skills/skills/lean-proof-review/SKILL.md

lean-proof-review

Skill3 starsChanged 24 days agoApache-2.0View on GitHub

USE FOR: reviewing one Lean 4 proof / file for correctness, soundness, statement faithfulness, non-triviality. DO NOT USE FOR: writing a new proof (@lean-proof). TRIGGERS: proof review, audit proof, verify Lean, 4-layer checklist.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
SKILL.md

lean-proof-review

⚠️ MANDATORY (hot-tier): layers L1 (soundness) and L2 (statement) are hard gates — a failure at either MUST block sign-off, regardless of L3/L4. Skipping Persist = incomplete.

Routing

  • USE FOR: auditing a single Lean 4 proof or file across the 4-layer checklist (L1 soundness, L2 statement, L3 non-triviality, L4 quality); cross-checking that imported tactics from the project automation stack are used correctly; spotting common pitfalls (vacuous truth, unused hypothesis, broken simp set, scope drift).
  • DO NOT USE FOR: authoring the proof (delegate to @lean-proof); convening a multi-agent review (delegate to @lean-review-council); running the CI scripts (delegate to @lean-enforcement).
  • TRIGGERS: proof review, audit proof, verify Lean, 4-layer checklist, lean-pitfalls, proof quality.

Workflow

  1. Discover [discover] — read the target file, locate the theorem(s), find the source spec and any prior review record.
  2. L1 soundness [validate] — confirm no sorry, no admit, no sorryAx, and no unauthorized Lean.ofReduceBool via lean_axiom_closure ({"symbol": "...", "module": "..."}) and lean_diagnostics ({"filePath": "..."}); defer to @lean-enforcement for full-module axiom audit if needed.

Recovery & STOP

  • L1 fails (sorry / admit / sorryAx) → STOP, do NOT proceed to L2-L4; escalate to author.
  • L2 fails (statement drift) → STOP, escalate to spec owner before any proof judgement.
  • lake build red on containing file → STOP, ask author to fix build first.
  • Confidence < 90 % on a tactic suggestion → mark as advisory, do NOT block.
  • Scope drift (edits to non-proof files) → immediate STOP, re-anchor.

Handoffs

  • Predecessors / successors: see FM handoffs (grammar from ADR-0080).
  • Source spec: specs/lean/proof-review/requirements.md — every G-rule traces to an AC there.
  • Related ADRs: ADR-0076, ADR-0080.
  • Reference: see references/lean-proof-review-handbook.md for the full project automation stack, proof-search priority table, reusable Tactics lemma library, common Lean pitfalls, and the 4-layer verification checklist (original v1 content, preserved verbatim).

Detailed reference

Full encyclopedic reference, decision trees, and lookup tables live in references/lean-proof-review-handbook.md .

See also

  • ../../references/lean-proof-review-handbook.md -- Complete lean-proof-review Handbook
  • ../lean-gateway/SKILL.md -- Top-level skill router

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.

Check your setup, free