agentleFS
Sign inStart free
stunt-doublestunt-double/stuntdouble-mcp/skills/check-design-system/SKILL.md

check-design-system

Skill1 starsChanged 32 days agoMITView on GitHub

Audit a live product against its design system (typography, colour, spacing, components, iconography) on rendered pages with evidence, and re-check automatically when the Figma library publishes.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    No rules supplied: ask for key tokens and component rules, or derive a draft from the most polished screens and confirm it.

    line 13
  2. Very specific:

    Wire in: if Figma is connected, create_workflow with a figma_event trigger so the audit re-runs on library publish.

    line 17

≈ “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

Check design system

  1. Context: list_workspaces(), list_projects(workspace_id). Match the URL to a project, or let create_checklist find or create it.
  2. Actor and rules:
    • list_actors(workspace_id), else create_actor(...) described as a design-system reviewer.
    • list_workspace_guidelines(workspace_id) first, then attach with set_project_guideline(project_id, guideline_id) or write add_project_guideline(project_id, category: "design_system", content, title). Token values and component dos and don'ts belong here.
    • update_workspace_guideline(workspace_id, guideline_id, apply_to_design_reviews: true) when the standard must also hold for design reviews from Slack or Linear, which carry no project.
    • No rules supplied: ask for key tokens and component rules, or derive a draft from the most polished screens and confirm it.
  3. One checklist per surface. Actors see only the rendered product, so phrase checks visually ("Primary CTAs use the brand primary colour and sentence case", "Form fields show a visible focus state"), never by class names or tokens.
  4. Run: run_checklist(checklist_id), poll get_checklist_run(run_id) until terminal, collect evidence per deviation.
  5. Report deviations by page with evidence and the rule each breaks.
  6. Wire in: if Figma is connected, create_workflow with a figma_event trigger so the audit re-runs on library publish; otherwise a schedule or deploy trigger (see setup-guardrails).

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