agentleFS
Sign inStart free
ek0212ek0212/agent-ready-repo-kit/skills/excalidraw-system-sketch/SKILL.md

excalidraw-system-sketch

Skill0 starsChanged 4 months agoMITView on GitHub

Plan or create Excalidraw sketches for fuzzy architecture, product flows, trust boundaries, before-and-after designs, or system maps. Use when user asks for an Excalidraw diagram, rough system sketch, spatial grouping, swimlanes, or visual exploration that Mermaid cannot express well.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create one readable spatial sketch plus durable Markdown summary.

    line 7
  2. Distinctive:

    Use when placement, grouping, swimlanes, or exploration matters.

    line 11
  3. Very specific:

    Create or update .excalidraw when compatible tooling exists.

    line 29
  4. Very specific:

    Write companion .md summary with purpose, components, boundaries, flows, and open questions.

    line 30
  5. Very specific:

    When text is enclosed by a shape, bind it when possible: shape boundElements includes { "type": "text", "id": "<text_id>" }, and text …

    line 38
  6. Distinctive:

    Avoid file-level detail unless diagram question requires it.

    line 39
  7. Very specific:

    Keep uncertain elements labeled Assumption or Open.

    line 40
  8. Distinctive:

    No Excalidraw tooling: return exact sketch plan and companion Markdown.

    line 44
  9. Distinctive:

    No secrets or private data embedded.

    line 54
  10. Distinctive:

    Use direct simple sentences.

    line 60

≈ “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 one readable spatial sketch plus durable Markdown summary.

Scope

Use when placement, grouping, swimlanes, or exploration matters. Use Mermaid for exact sequence, state, dependency, or GitHub-rendered architecture.

Inputs

  • Diagram purpose and audience.
  • Components, actors, systems, and flows.
  • Trust boundaries, secrets, user data, and external services.
  • Existing .excalidraw file or visual conventions, if any.

User or repository owns system facts. Mark inferred nodes and unresolved flows.

Workflow

  1. State one diagram question.
  2. List boxes, groups, arrows, boundaries, and annotations.
  3. Choose layout: left-to-right flow, swimlanes, nested zones, or before/after.
  4. Separate internal, external, trusted, and untrusted areas.
  5. Label secret and user-data entry points without including secret values.
  6. Create or update .excalidraw when compatible tooling exists.
  7. Write companion .md summary with purpose, components, boundaries, flows, and open questions.

Drawing Rules

  • One concept per sketch.
  • Short labels. Verb-led arrows.
  • Color encodes one stable meaning or stays decorative-free.
  • Boundaries visible without color alone.
  • When text is enclosed by a shape, bind it when possible: shape boundElements includes { "type": "text", "id": "<text_id>" }, and text element points back with containerId.
  • Avoid file-level detail unless diagram question requires it.
  • Keep uncertain elements labeled Assumption or Open.

Fallbacks

  • No Excalidraw tooling: return exact sketch plan and companion Markdown. State visual file not created.
  • Flow already precise: route to mermaid-architecture-map.
  • Missing system facts: create partial sketch with open questions; do not invent architecture.

Verify

  • Diagram answers stated question.
  • Main flow readable without zoom.
  • Enclosed labels stay bound to their shape when .excalidraw format supports it.
  • Trust boundaries and external systems explicit.
  • No secrets or private data embedded.
  • Companion summary matches visual.
  • Open questions named.

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

  • .excalidraw file when tooling permits.
  • Companion .md summary always.
  • Assumptions and unresolved items.

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