check-design-system
Audit a live product against its design system (typography, colour, spacing, components, iconography) on rendered pages with evidence, and re-check…
Skill by stunt-double
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/stunt-double-check-design-system
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/check-design-system
What's inside
- Skill name
check-design-system- Description
- 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.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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`).From stunt-double/stuntdouble-mcp, MIT.
More from stunt-double/stuntdouble-mcp
- 0.609score
Stunt Double
stuntdouble.ioOfficial
Deploy AI user personas to validate user journeys at scale.
ConnectorAFreshness: ARemote★ 1Claude Code +3 - 0.579score
check-agent-readiness
stunt-double
Check how well AI agents can find, understand and act on a website using the Stunt Double Index (agent readiness, AI visibility, checkout or support by…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
check-brand
stunt-double
Audit a product or site against brand and tone-of-voice guidelines, with an actor reading every in-scope page like a customer and flagging copy, voice and…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
check-compliance
stunt-double
Check a product against legal and compliance requirements (cookie consent, privacy and terms access, required disclosures, claim substantiation, unsubscribe…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
check-continuity
stunt-double
Check continuity across surfaces (pricing, plan names, terminology, feature names, promises) between marketing site, product, docs and emails, with actors…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
create-actor-panel
stunt-double
Create and configure Stunt Double actors (AI personas) with system prompts and knowledge entries, to cover user segments such as first-time users, enterprise…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
design-review
stunt-double
Run a design review of a proposed design, flow, prototype or live URL by interviewing several Stunt Double actors and synthesising themes, friction and…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
maintain-automations
stunt-double
Change an existing Stunt Double workflow or checklist without losing run history: retime triggers, edit and rewire steps, build condition branches, update…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
run-qa-suite
stunt-double
Run every Stunt Double workflow and checklist in a workspace and produce a GO, CONDITIONAL or NO-GO release-readiness report.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
run-user-interview
stunt-double
Plan, configure and launch a structured user interview with AI participants against a live URL on Stunt Double, then read the synthesised report (summary…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
run-ux-validation
stunt-double
Validate a user journey before merge or release by running Stunt Double workflows and checklists and reporting pass or fail with failure detail.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
triage-feedback
stunt-double
Review, categorise and manage Stunt Double feedback submissions (new items, severity, status, patterns) across projects.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 16, 2026 (13 days ago)
- Last release
- Oct 14, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/stunt-double/stuntdouble-mcp
- Website
- stuntdouble.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from stunt-double
- 0.579score
check-agent-readiness
stunt-double
Check how well AI agents can find, understand and act on a website using the Stunt Double Index (agent readiness, AI visibility, checkout or support by…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
check-brand
stunt-double
Audit a product or site against brand and tone-of-voice guidelines, with an actor reading every in-scope page like a customer and flagging copy, voice and…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
check-compliance
stunt-double
Check a product against legal and compliance requirements (cookie consent, privacy and terms access, required disclosures, claim substantiation, unsubscribe…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
check-continuity
stunt-double
Check continuity across surfaces (pricing, plan names, terminology, feature names, promises) between marketing site, product, docs and emails, with actors…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
create-actor-panel
stunt-double
Create and configure Stunt Double actors (AI personas) with system prompts and knowledge entries, to cover user segments such as first-time users, enterprise…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
design-review
stunt-double
Run a design review of a proposed design, flow, prototype or live URL by interviewing several Stunt Double actors and synthesising themes, friction and…
SkillAFreshness: A★ 1Claude Code +9
Cite this page
check-design-system skill. Agent Mart. https://agentmart.dev/skills/stunt-double-check-design-system (last updated 2026-10-24)