agentsclimarketplace

Lean applied reasoning

Skill r-irbe/proof-skills/skills/lean-applied-reasoning

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-applied-reasoning

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: Applied reasoning for intelligence analysis, strategy creation and analysis, brainstorming methodologies, investigative reasoning, and domain-specific decision-making. Use when formalizing strategic frameworks, situational analysis, hypothesis generation workflows, decision-under-uncertainty models, or when connecting theoretical formalization to practical operational contexts. Bridges mathematical formalization to real-world application domains. DO NOT USE FOR: pure intelligence-analysis methodology (use @applied-intelligence-analysis); strategy analysis methodology (use @applied-strategy-analysis); legal reasoning methodology (use @applied-legal-reasoning). TRIGGERS: applied reasoning, intelligence formalisation, strategy formalisation, investigative reasoning, domain-specific reasoning.

SKILL.md

4.1 KB, as published. Nobody here has run it

Lean 4 Applied Reasoning & Strategy

Guide to formalizing applied reasoning — from intelligence analysis to strategic decision-making — in Lean 4.


Routing

  • USE FOR: Applied reasoning for intelligence analysis, strategy creation and analysis, brainstorming methodologies, investigative reasoning, and domain-specific decision-making. Use when formalizing strategic frameworks, situational analysis, hypothesis generation workflows, decision-under-uncertainty models, or when connecting theoretical formalization to practical operational contexts. Bridges mathematical formalization to real-world application domains.
  • DO NOT USE FOR: pure intelligence-analysis methodology (use @applied-intelligence-analysis); strategy analysis methodology (use @applied-strategy-analysis); legal reasoning methodology (use @applied-legal-reasoning).
  • TRIGGERS: applied reasoning, intelligence formalisation, strategy formalisation, investigative reasoning, domain-specific reasoning.

Workflow

  1. Classify the applied-reasoning task: intelligence-formalisation, strategy-formalisation, investigative-reasoning, or domain-specific reasoning.
  2. Pick the corresponding body section; identify the Lean primitives + Mathlib lemmas it depends on.
  3. Write the Lean encoding; verify Mathlib primitives exist at the current pin.
  4. Hand off: to @lean-proof-review for review, to @lean-enforcement for CI, to @lean-zettelkasten.

Recovery & STOP

  • STOP if the question is purely methodological (no Lean) — delegate to the matching applied-* skill.
  • STOP if Mathlib primitives are missing — escalate to @lean-research.
  • STOP if the spec is informal — delegate to @lean-specification first.

Handoffs

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

Detailed reference

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

SectionTopic
Part 1Intelligence Analysis Formalization
Part 2Strategy Formalization
Part 3Brainstorming Methodology
Part 4Investigative Reasoning (Project Core Domain)
Part 5Decision Under Uncertainty
Part 6Project & Product Management for Mathematics
Part 7Research 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.