agentleFS
Sign inStart free
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/pm-architecture-review/SKILL.md

pm-architecture-review

Skill2 starsChanged 4 months agoMITView on GitHub

Review CodeFlowMu/FCoP proposals for architecture and governance boundary risk. Use when adding tools, skills, runtime logic, Panel buttons, lifecycle behavior, report/eval/issue-draft behavior, or anything that might mix MCP Skill with Agent Playbook Skill.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill before accepting a proposal that touches architecture, runtime governance, lifecycle, Panel/API, or FCoP semantics.

    line 10
  2. Distinctive:

    Check whether MCP is being turned into a decision brain.

    line 14
  3. Distinctive:

    Check Playbook vs MCP layer separation.

    line 15
  4. Distinctive:

    Check ADMIN, lifecycle, EVAL, REPORT, and public submission boundaries.

    line 16
  5. Very specific:

    Use the structure in docs/skills/pm-playbook/architecture-review.md.

    line 21
  6. Distinctive:

    Do not let PM Playbook become runtime API.

    line 25
  7. Distinctive:

    Do not bypass ADMIN.

    line 26
  8. Distinctive:

    Do not auto-submit GitHub issues.

    line 27
  9. Distinctive:

    Do not modify FCoP formal protocol.

    line 28
  10. Very specific:

    Do not add adopted-pending 0003.

    line 29

≈ “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

PM Architecture Review

When to use

Use this skill before accepting a proposal that touches architecture, runtime governance, lifecycle, Panel/API, or FCoP semantics.

Rules

  • Check whether MCP is being turned into a decision brain.
  • Check Playbook vs MCP layer separation.
  • Check ADMIN, lifecycle, EVAL, REPORT, and public submission boundaries.
  • Prefer minimal adjustments.

Required output

Use the structure in docs/skills/pm-playbook/architecture-review.md.

Forbidden actions

  • Do not let PM Playbook become runtime API.
  • Do not bypass ADMIN.
  • Do not auto-submit GitHub issues.
  • Do not modify FCoP formal protocol.
  • Do not add adopted-pending 0003.

Minimal example

Conclusion: risky
Risk: proposal lets EVAL submit public GitHub issues
Adjustment: create internal draft with admin_approved=false

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