agentsclimarketplace

Lean knowledge formalization

Skill r-irbe/proof-skills/skills/lean-knowledge-formalization

APM-installable agent skills for Lean 4 and Mathlib4 — proof tactics, math domains, review and research workflows, generic tooling.

Install
npx -y skills add r-irbe/proof-skills --skill lean-knowledge-formalization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

USE FOR: Knowledge representation, ontology engineering, symbolic AI, commonsense reasoning, causal reasoning, legal reasoning, and abductive inference in Lean 4. Use when formalizing knowledge structures, reasoning systems, argumentation frameworks, deontic logic, defeasible reasoning, or any domain where structured knowledge and inference must be formally verified. Core skill for knowledge-lifecycle and provenance architectures. DO NOT USE FOR: KRR methodology not in Lean (use @ai-symbolic-neuro); commonsense reasoning methodology (use @ai-commonsense-reasoning); causal/deontic methodology (use @ai-causal-deontic). TRIGGERS: knowledge formalisation, ontology in Lean, symbolic AI Lean, abductive inference Lean, legal reasoning Lean.

SKILL.md

4.0 KB, as published. Nobody here has run it

Lean 4 Knowledge Systems & Reasoning Formalization

Guide to formalizing knowledge representation, reasoning systems, and domain-specific logic in Lean 4.

Routing

  • USE FOR: Knowledge representation, ontology engineering, symbolic AI, commonsense reasoning, causal reasoning, legal reasoning, and abductive inference in Lean 4. Use when formalizing knowledge structures, reasoning systems, argumentation frameworks, deontic logic, defeasible reasoning, or any domain where structured knowledge and inference must be formally verified. Core skill for knowledge-lifecycle and provenance architectures.
  • DO NOT USE FOR: KRR methodology not in Lean (use @ai-symbolic-neuro); commonsense reasoning methodology (use @ai-commonsense-reasoning); causal/deontic methodology (use @ai-causal-deontic).
  • TRIGGERS: knowledge formalisation, ontology in Lean, symbolic AI Lean, abductive inference Lean, legal reasoning Lean.

Workflow

  1. Classify the knowledge object: ontology, taxonomy, causal model, deontic norm, or abductive rule.
  2. Pick the matching encoding pattern from the body (description-logic encoding, SCM encoding, etc.).
  3. Produce the Lean encoding; check Mathlib primitives at the current pin.
  4. Hand off: to @lean-causal-reasoning if causal-DAG-specific, to @lean-proof-review for review, to @lean-zettelkasten.

Recovery & STOP

  • STOP if the question is methodological (not Lean) — delegate to @ai-symbolic-neuro / @ai-commonsense-reasoning / @ai-causal-deontic.
  • STOP if Mathlib lacks the needed structure — escalate to @lean-research.
  • STOP if the encoding requires graph-theoretic foundations not in the body — delegate to @lean-math-discrete or @math-graph-knowledge.

Handoffs

  • Predecessors: agent:gateway, skill:lean-research.
  • Successors: skill:lean-proof-review, skill:lean-causal-reasoning, skill:lean-zettelkasten.

Detailed reference

Full content for lean-knowledge-formalization lives in references/lean-knowledge-formalization-handbook.md. Load that file when the skill is convened; the SKILL.md only carries the dispatch contract and the parts index.

SectionTopic
Part 1Knowledge Representation
Part 2Reasoning Systems
Part 3Legal Reasoning
Part 4Symbolic AI
Part 5Intelligence Analysis Reasoning
Part 6Research Council Integration

See also

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.