agentleFS
Sign inStart free
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/architect-system-design/SKILL.md

architect-system-design

Skill2 starsChanged 4 months agoMITView on GitHub

Produce CodeFlowMu/FCoP-aware system designs before implementation. Use when an architect needs to define problem, current architecture, proposed design, interfaces, alternatives, risks, and verification without creating runtime behavior by default.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Use this skill before implementing changes that affect architecture, interfaces, MCP tools, Panel/API, lifecycle, events, schemas, or …

    line 10
  2. Distinctive:

    Keep design separate from implementation unless implementation is explicitly in scope.

    line 17
  3. Distinctive:

    Do not treat local design as formal FCoP protocol change.

    line 25
  4. Distinctive:

    Do not add runtime APIs without explicit implementation scope.

    line 26
  5. Distinctive:

    Do not bypass ADMIN.

    line 27
  6. Very specific:

    Do not add adopted-pending 0003.

    line 28

≈ “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

Architect System Design

When to use

Use this skill before implementing changes that affect architecture, interfaces, MCP tools, Panel/API, lifecycle, events, schemas, or cross-module flow.

Rules

  • Describe current architecture before proposing changes.
  • Define interfaces and data flow.
  • Compare alternatives.
  • Keep design separate from implementation unless implementation is explicitly in scope.

Required output

Use docs/skills/architect-playbook/system-design.md.

Forbidden actions

  • Do not treat local design as formal FCoP protocol change.
  • Do not add runtime APIs without explicit implementation scope.
  • Do not bypass ADMIN.
  • Do not add adopted-pending 0003.

Minimal example

Problem: issue draft safety needs visibility
Interface: internal draft frontmatter safety_check
Risk: accidental public submission
Verification: draft contains 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