lean-pr
Skill3 starsChanged 24 days agoApache-2.0View on GitHub
USE FOR: opening, titling, or labelling a PR against any Lean ecosystem repo (`leanprover/lean4`. DO NOT USE FOR: in-tree proof review (@lean-proof-review). TRIGGERS: PR, pull request, "open a PR", changelog label, bors.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- leanprover/skillstheir own version, first seen Feb 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- leanprover/skills★ 72same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-guard-judge-evalSkill
- applied-data-information-securitySkill
- applied-engineering-disciplinesSkill
- applied-legal-reasoningSkill
- epistemic-discovery-engineSkill
- epistemic-mappingSkill
- hol-metamath-adapterSkill
- isabelle-isar-adapterSkill
- itp-cross-portingSkill
- lean-ai-formalizationSkill
- lean-applied-reasoningSkill
- lean-axiom-closureSkill
- lean-bigraph-modelingSkill
- lean-bisectSkill
- lean-blueprintSkill
- lean-buildSkill
- lean-causal-reasoningSkill
- lean-competitive-mathSkill
- lean-convergence-verificationSkill
- lean-core-onlySkill
- lean-dag-visualizerSkill
- lean-deep-auditSkill
- lean-doc-feedbackSkill
- lean-doc-improvementSkill
- lean-doc-requirementsSkill
- lean-enforcementSkill
- lean-formalization-breakdownSkill
- lean-gatewaySkill
- lean-integration-protocolSkill
- lean-knowledge-formalizationSkill
- lean-math-analysisSkill
- lean-math-discreteSkill
- lean-math-dynamicalSkill
- lean-math-foundationsSkill
- lean-math-optimizationSkill
- lean-math-stochasticSkill
- lean-mweSkill
- lean-nested-learningSkill
- lean-package-researchSkill
- lean-pedagogical-expositionSkill
- lean-proof-refactorSkill
- lean-proof-repairSkill
- lean-proof-reviewSkill
- lean-proofSkill
- lean-quality-engineSkill
- lean-replay-verificationSkill
- lean-reportSkill
- lean-researchSkill
- lean-retroactive-auditSkill
- lean-retro-methodologySkill
- lean-review-councilSkill
- lean-security-formalizationSkill
- lean-setupSkill
- lean-specificationSkill
- lean-tautology-triageSkill
- lean-upstream-portingSkill
- lean-vendor-substrateSkill
- lean-zettelkastenSkill
- math-product-managementSkill
- The first 60 shown.
The file
Files
lean-pr
Agnostic PR-workflow contract for the whole Lean ecosystem. Upstream-specific conventions (Lean 4 core, Mathlib 4) live in
references/upstream/lean4-pr.mdandreferences/upstream/mathlib4-pr.md; this skill dispatches into them based on target repository.
Routing
- USE FOR: any PR action against a Lean-ecosystem repo: branch-from-fork, title shaping (
<type>: <subject>for Lean core,<type>(<scope>): <subject>for Mathlib), description authoring (first paragraph = changelog text), pre-flight validation (clean build, 0 sorry, 0 warnings, 0 debug probes), label selection per repo, runninglake exe mk_allafter Mathlib file renames, cross-linking dependent PRs via- [ ] depends on: #XXXX. - DO NOT USE FOR: in-tree proof review (
@lean-proof-review); Mathlib-specific review checklists (references/upstream/mathlib4-review.md); writing
Workflow
- Pre-flight verification -- ensure local build passes cleanly via
lake build. Confirm zerosorry, zeroadmit, zero unproven goals, and no leftovertrace_stateor#checkprobes. - Pick conventions -- consult the dispatch table (Lean 4 core / Mathlib 4 / Batteries / downstream). Read
the relevant
references/upstream/<repo>-pr.mdif unfamiliar. STOP and ask if the target repo isn't in the table. - Title + description -- imperative present tense, lowercase subject, no period. First paragraph of
description = changelog
text,
starts with "This PR
...". Skip
## Summary/## Test planheaders -- CI and git diff carry that.
Recovery & STOP
- Unknown target repo (not in dispatch table) -> STOP, ask which conventions apply before pushing.
- Missing
changelog-*label on Lean corefeat/fixPR -> CI will block; readreferences/upstream/lean4-pr.mdSection Changelog labels before re-pushing. - Mathlib CI fails after file rename -> most common cause is forgetting
lake exe mk_all; re-run and amend.
Handoffs
- Predecessors / successors: see FM
handoffs. Typical inbound:@lean-build(clean local build),@lean-mwe(for upstream bug-report PRs),@lean-bisect(when filing a known-version regression),@lean-proof-review(when review green-lit a contribution). Typical outbound:@lean-proof-review(for in-tree feedback) or@lean-zettelkasten(recording PR-process lessons). - REDIRECT pointer:
lean-prslug routes here (preserved per Chesterton-protocol).
Detailed reference
Full encyclopedic reference, decision trees, and lookup tables live in
references/lean-pr-handbook.md .
See also
../../references/lean-pr-handbook.md-- Handbook Handbook../lean-gateway/SKILL.md-- Top-level skill router
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
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.

