lean-doc-requirements
Skill3 starsChanged 24 days agoApache-2.0View on GitHub
USE FOR: Extract formal requirements from academic papers, technical reports, and design documents. DO NOT USE FOR: paper update post-Lean (@lean-doc-improvement). TRIGGERS: doc requirements, requirement extraction, informal-to-Lean.
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-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-prSkill
- 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
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Read the source document; identify each informal mathematical claim, its scope, and implicit assumptions.
- Very specific: line 48
STOP if the document is being updated FROM Lean — delegate to @lean-doc-improvement.
- Distinctive: line 49
STOP if claims are too vague to formalise — request HITL clarification.
- Very specific: line 50
STOP if a project-level blueprint is needed — delegate to @lean-blueprint.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lean 4 Document-to-Requirements
Extract formal specification requirements from informal documents (papers, reports, specs) and map them to Lean 4 theorem statements.
Routing
- USE FOR: Extract formal requirements from academic papers, technical reports, and design documents. Use when converting informal mathematical claims into Lean 4 theorem specifications. Covers claim extraction from LaTeX sources, equation identification, proposition mapping, hypothesis inference, and requirement traceability from document to formal specification.
- DO NOT USE FOR: paper update post-Lean (use @lean-doc-improvement); specification design (use @lean-specification); blueprint generation (use @lean-blueprint).
- TRIGGERS: doc requirements, requirement extraction, informal-to-Lean, claim extraction, paper-to-spec.
Workflow
- Read the source document; identify each informal mathematical claim, its scope, and implicit assumptions.
- Pick the requirement template from the body matching the claim class (definition, theorem, lemma, tactic-rule).
- Produce a draft Lean specification (signature only, no proof) with traceability back to the source.
- Hand off: to
@lean-specificationfor the formal spec design, to@lean-prooffor the proof, to@lean-zettelkasten.
Recovery & STOP
- STOP if the document is being updated FROM Lean — delegate to
@lean-doc-improvement. - STOP if claims are too vague to formalise — request HITL clarification.
- STOP if a project-level blueprint is needed — delegate to
@lean-blueprint.
Handoffs
- Predecessors:
agent:gateway,skill:lean-research. - Successors:
skill:lean-specification,skill:lean-proof,skill:lean-zettelkasten.
Detailed reference
Full content for lean-doc-requirements lives in
references/lean-doc-requirements-handbook.md.
Load that file when the skill is convened; the SKILL.md only carries
the dispatch contract and the parts index.
| Section | Topic |
| Part 1 | Extraction Pipeline |
| Part 2 | Claim Extraction Protocol |
| Part 3 | Hypothesis Inference |
| Part 4 | Batch Extraction Workflow |
| Part 5 | Council Integration |
| Part 6 | Requirements Traceability |
See also
../../references/lean-doc-requirements-handbook.md— Full handbook (extracted from this skill)../lean-specification/SKILL.md— Successor../lean-proof/SKILL.md— Successor../lean-zettelkasten/SKILL.md— Successor
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.