agentleFS
Sign inStart free
r-irber-irbe/proof-skills/skills/lean-integration-protocol/SKILL.md

lean-integration-protocol

Skill3 starsChanged 24 days agoApache-2.0View on GitHub

USE FOR: Cross-skill integration protocol defining how all 39 skills work together. DO NOT USE FOR: any single-skill execution (use that skill directly). TRIGGERS: integration protocol, skill integration, cross-skill.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    STOP if the question is about a single skill's execution — delegate to that skill directly.

    line 46
  2. Very specific:

    STOP if the integration target is the gateway itself — delegate to @lean-gateway.

    line 47
  3. Distinctive:

    STOP if the protocol would create a cycle — surface the cycle and request HITL design judgment.

    line 48

≈ “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-40: Integration Protocol

Defines how all skills in the project ecosystem work together as a coherent system.

Routing

  • USE FOR: Cross-skill integration protocol defining how all 39 skills work together. Covers the complete lifecycle from document to proof to document, inter-cluster communication, workflow templates for common tasks, and the master orchestration patterns. Use when coordinating multi-skill workflows or diagnosing cross-skill issues.
  • DO NOT USE FOR: any single-skill execution (use that skill directly); the review council itself (use @lean-review-council); the gateway (use @lean-gateway).
  • TRIGGERS: integration protocol, skill integration, cross-skill, skill lifecycle, inter-cluster routing.

Workflow

  1. Identify the cross-skill question: which skills, what data flows, which handoffs.
  2. Pick the lifecycle section of the body matching the flow (document → spec → proof → doc, or council ↔ research).
  3. Produce the integration recipe — explicit sequence of skill invocations + artifact handoffs.
  4. Hand off: to @lean-review-council for council orchestration, to @lean-enforcement for CI, to @lean-zettelkasten.

Recovery & STOP

  • STOP if the question is about a single skill's execution — delegate to that skill directly.
  • STOP if the integration target is the gateway itself — delegate to @lean-gateway.
  • STOP if the protocol would create a cycle — surface the cycle and request HITL design judgment.

Handoffs

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

Detailed reference

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

SectionTopic
Part 1The Three Lifecycles
Part 2Standard Workflow Templates
Part 3Inter-Cluster Communication Protocols
Part 4Feedback Loop Inventory
Part 5Personas and Roles (Complete)
Part 6Conflict Resolution
Part 7Bootstrapping a New Project
Part 8Retrofitting an Existing Project (RETRO Protocol Summary)
Part 9Integration Anti-Patterns

See also

  • ../../references/lean-integration-protocol-handbook.md — Full handbook (extracted from this skill)
  • ../lean-review-council/SKILL.md — Successor
  • ../lean-enforcement/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