agentleFS
ek0212ek0212/agent-ready-repo-kit/skills/mermaid-architecture-map/SKILL.md

mermaid-architecture-map

Skill0 starsChanged 4 months agoMITView on GitHub

Create concise Mermaid diagrams for architecture, data flow, request sequence, lifecycle state, dependencies, or trust boundaries in Markdown. Use when prose hides flow or ownership, user asks for Mermaid, repository needs GitHub-rendered diagram, or system boundary must be explicit.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Create smallest diagram that makes one relationship clear.

    line 7
  2. Very specific:

    Use for exact flow, sequence, state, dependency, and boundary diagrams.

    line 11
  3. Distinctive:

    Use short node labels and verb-led edges.

    line 33
  4. Distinctive:

    No secrets or private values present.

    line 51
  5. Distinctive:

    Use direct simple sentences.

    line 55

≈ “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

Create smallest diagram that makes one relationship clear.

Scope

Use for exact flow, sequence, state, dependency, and boundary diagrams. Use excalidraw-system-sketch for fuzzy spatial exploration, swimlanes, or rough before-and-after thinking.

Inputs

  • Diagram question and audience.
  • Verified components, actors, states, and edges.
  • External systems, trust boundaries, secrets, and user-data paths.
  • Target Markdown file or standalone .mmd path.

User or repository owns architecture facts. Label inference and unknowns.

Workflow

  1. State one question diagram answers.
  2. Pick simplest type:
    • flowchart LR: architecture, ownership, boundaries.
    • sequenceDiagram: ordered request or agent flow.
    • stateDiagram-v2: lifecycle and transitions.
    • graph TD: dependency hierarchy.
  3. Include only nodes needed for question.
  4. Group system and trust boundaries.
  5. Label external services and secret/user-data entry points. Never include secret values.
  6. Use short node labels and verb-led edges.
  7. Save .mmd; embed in Markdown when requested.

Fallbacks

  • Missing facts: draw verified subset and list unknown edges.
  • Diagram becomes dense: split by question, not arbitrary file count.
  • Spatial grouping matters more than exact flow: route to Excalidraw.
  • Renderer lacks feature: use simpler supported syntax.

Verify

  • Mermaid syntax renders.
  • Brackets and quotes balanced.
  • Labels avoid unsupported Markdown.
  • Direction and edge labels readable.
  • Boundaries and external systems explicit.
  • Diagram fits PR review without excessive detail.
  • No secrets or private values present.

Writing

Use direct simple sentences. Skip rhetorical flourishes. Avoid X-not-Y contrasts, self-answering rhetorical questions, em dashes, alliterative three-part phrases, vague inspirational pivots, unsourced claims, and unverified quotes.

Output

Return .mmd or embedded Mermaid block plus short assumptions/open-questions note when needed.

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.