agentleFS
Sign inStart free
r-irber-irbe/proof-skills/skills/lean-retro-methodology/SKILL.md

lean-retro-methodology

Skill3 starsChanged 24 days agoApache-2.0View on GitHub

USE FOR: running a Lean 4 corpus retrospective: RETRO protocol (Refactor-Extract-Test-Refine-Optimize). DO NOT USE FOR: single proof review (@lean-proof-review). TRIGGERS: retro, retrospective, RETRO protocol.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    STOP if a phase's enforcement script fails (handbook Part 3) — do not advance to the next phase.

    line 48
  2. Distinctive:

    STOP if Optimize phase produces no actionable cross-skill rewires after RALPH iteration 3 (handbook Part 7) — close the retro and document …

    line 49
  3. Distinctive:

    STOP on detection of any handbook Part 8 anti-pattern — back out and re-plan.

    line 53

≈ “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

SK-35: Retroactive Formalization Methodology

Operational dispatch contract for @lean-retro-methodology.

Routing

  • USE FOR / DO NOT USE FOR / TRIGGERS — see the description field in the YAML frontmatter above. Same dispatch contract is restated here for in-skill discovery.
  • USE FOR: running a Lean 4 corpus retrospective — RETRO protocol (Refactor-Extract-Test-Refine-Optimize), adapting to project scale (Solo / Small / Medium / Large), per-phase enforcement scripts, cross-skill optimization rules, retro personas, tracking documents, embedded RALPH inside RETRO phases.
  • DO NOT USE FOR: single proof review (use @lean-proof-review); council convocation (use @lean-review-council); research (use @lean-research);

Workflow

  1. Pick the project scale (handbook Part 2) — determines depth + cadence.
  2. Sequence the RETRO phases (handbook Part 1 — Refactor → Extract → Test → Refine → Optimize); inside each phase run the embedded RALPH loop (handbook Part 7).
  3. Apply per-phase enforcement scripts (handbook Part 3) as the phase gate.
  4. Apply cross-skill optimization rules (handbook Part 4) once Refine + Optimize have data.
  5. Emit the per-phase tracking docs (handbook Part 6) and audit against handbook Part 8 anti-patterns.

Recovery & STOP

  • STOP if a phase's enforcement script fails (handbook Part 3) — do not advance to the next phase.
  • STOP if Optimize phase produces no actionable cross-skill rewires after RALPH iteration 3 (handbook Part 7) — close the retro and document why.
  • STOP on detection of any handbook Part 8 anti-pattern — back out and re-plan.

Handoffs

  • Predecessors: agent:gateway, skill:lean-review-council, skill:lean-research.
  • Successors: skill:lean-enforcement, skill:lean-zettelkasten, skill:lean-doc-feedback, skill:lean-review-council.

Detailed reference

Full encyclopedic reference, decision trees, and lookup tables live in references/lean-retro-methodology-handbook.md .

See also

  • ../../references/lean-retro-methodology-handbook.md -- Complete lean-retro-methodology Handbook
  • ../lean-gateway/SKILL.md -- Top-level skill router

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