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

lean-knowledge-formalization

Skill3 starsChanged 24 days agoApache-2.0View on GitHub

USE FOR: Knowledge representation, ontology engineering, symbolic AI, commonsense reasoning, causal reasoning. DO NOT USE FOR: KRR methodology not in Lean (@lean-knowledge-formalization). TRIGGERS: knowledge formalisation, ontology in Lean, symbolic AI Lean.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    STOP if the question is methodological (not Lean) — delegate to @lean-knowledge-formalization / @lean-knowledge-formalization / …

    line 47
  2. Very specific:

    STOP if Mathlib lacks the needed structure — escalate to @lean-research.

    line 50
  3. Very specific:

    STOP if the encoding requires graph-theoretic foundations not in the body — delegate to @lean-math-discrete or @lean-math-discrete.

    line 51

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 @lean-knowledge-formalization); commonsense reasoning methodology (use @lean-knowledge-formalization); causal/deontic methodology (use @lean-causal-reasoning).
  • 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 @lean-knowledge-formalization / @lean-knowledge-formalization / @lean-causal-reasoning.
  • 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 @lean-math-discrete.

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

  • ../../references/lean-knowledge-formalization-handbook.md — Full handbook (extracted from this skill)
  • ../lean-proof-review/SKILL.md — Successor
  • ../lean-causal-reasoning/SKILL.md — Successor
  • ../lean-zettelkasten/SKILL.md — Successor

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