lean-doc-improvement
Skill3 starsChanged 24 days agoApache-2.0View on GitHub
USE FOR: Update academic papers, technical reports, and documentation based on results from Lean 4 formalization. DO NOT USE FOR: extracting requirements from papers (@lean-doc-requirements). TRIGGERS: update paper, doc improvement, paper revision.
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-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-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
5 rules. About 0 are common, 2 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
USE FOR: Update academic papers, technical reports, and documentation based on results from Lean 4 formalization.
- Distinctive: line 38
TRIGGERS: update paper, doc improvement, paper revision, documentation update from Lean, doc-feedback consumer.
- Very specific: line 50
STOP if the question is about extracting requirements from the paper — delegate to @lean-doc-requirements.
- Very specific: line 51
STOP if a fresh blueprint is needed — delegate to @lean-blueprint.
- Very specific: line 52
STOP if the Lean result is wrong (not the paper) — delegate to @lean-proof-review first.
≈ “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 Results-to-Document Improvement
Systematically update documents when Lean formalization produces new insights, corrections, or metrics.
Routing
- USE FOR: Update academic papers, technical reports, and documentation based on results from Lean 4 formalization. Use when formal verification reveals paper imprecisions, missing hypotheses, sharper bounds, new insights, or when metrics need synchronization. Covers paper appendix updates, verification tables, erratum entries, insight propagation, and metric synchronization between Lean and documents.
- DO NOT USE FOR: extracting requirements from papers (use @lean-doc-requirements); blueprint generation (use @lean-blueprint); report compilation (use @lean-report).
- TRIGGERS: update paper, doc improvement, paper revision, documentation update from Lean, doc-feedback consumer.
Workflow
- Triage the change: which paper/document needs updating, which Lean result triggers it, and what's the delta.
- Pick the section/template from the body matching the update class (definition, theorem, proof-strategy, errata).
- Produce the patch with precise pointers to the Lean source + before/after text.
- Hand off: to
@lean-doc-feedbackfor the doc-sync record, to@lean-reportif the paper feeds into a report, to@lean-zettelkasten.
Recovery & STOP
- STOP if the question is about extracting requirements from the paper — delegate to
@lean-doc-requirements. - STOP if a fresh blueprint is needed — delegate to
@lean-blueprint. - STOP if the Lean result is wrong (not the paper) — delegate to
@lean-proof-reviewfirst.
Handoffs
- Predecessors:
agent:gateway,skill:lean-research. - Successors:
skill:lean-doc-feedback,skill:lean-report,skill:lean-zettelkasten.
Detailed reference
Full content for lean-doc-improvement lives in
references/lean-doc-improvement-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 | Trigger Events |
| Part 2 | Document Update Types |
| Part 3 | Update Workflow |
| Part 4 | LaTeX Integration Patterns |
| Part 5 | Feedback to Other Skills |
| Part 6 | Metric Dashboard |
See also
../../references/lean-doc-improvement-handbook.md— Full handbook (extracted from this skill)../lean-doc-feedback/SKILL.md— Successor../lean-report/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.