agentleFS
Sign inStart free
sukirman1901sukirman1901/frontend-expert/CLAUDE.md

frontend-expert

CLAUDE.md9 starsChanged 2 months agoMITView on GitHub

Claude Code entry point for Frontend Expert. 1. Do not wait for slash commands. Map intent → skills via AGENTS.md + rules 2. Blank-canvas / ambiguous UI → design-direction (2–3 approaches) before coding 3. Then → design-foundations (structural layout) → tokens → (+ typography/color/surfaces/content owners when relevant) → (+ marketing if marketing) → (+ shell/data/forms) → components → anti-slop-code → responsive → motion → anti-slop-design → polish → accessibility Blank-canvas compare/stress → prototype after design-direction, before foundations 4. Tests when…

The file

We split this CLAUDE.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the project already has a design system, use custom mode (do not override with presets)

    line 25
  2. Distinctive:

    Before DONE on UI builds → Conventions check including Responsive, Hierarchy, Typography, Control geometry, Motion, Shell, Landing (if …

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

CLAUDE.md

Claude Code entry point for Frontend Expert.

Plugin assets

  • Skills: skills/ (33 skills — suite root frontend-expert + domain pillars; see docs/pillars.md)
  • Agents: agents/design-reviewer.md, agents/ui-developer.md, agents/test-engineer.md
  • Commands: /design, /audit, /ui, /test-ui, /polish — optional
  • Rules: .claude/rules/design-system.md (chat-first + judgment)
  • Hooks: hooks/hooks.json auto-loaded by Claude Code (SessionStart + PostToolUse). Do not duplicate that path in .claude-plugin/plugin.json.
  • Tokens: tokens/*.css + decision tree / scoring in references/token-preset-scoring.md (+ tokens/README.md)
  • Evals: evals/ (E1–E33)

Default behavior (chat-first + judgment)

  1. Do not wait for slash commands. Map intent → skills via AGENTS.md + rules
  2. Blank-canvas / ambiguous UI → design-direction (2–3 approaches) before coding
  3. Then → design-foundations (structural layout) → tokens → (+ typography/color/surfaces/content owners when relevant) → (+ marketing if marketing) → (+ shell/data/forms) → components → anti-slop-code → responsive → motion → anti-slop-design → polish → accessibility Blank-canvas compare/stress → prototype after design-direction, before foundations
  4. Tests when asked → test-engineer + testing
  5. Audit when asked → design-reviewer skill chain (/design or /audit); never fabricate visual scores; animated UI uses motion-inspection
  6. “Rapihin / polish sampai bagus” → quality-loop (/polish), capped iterations
  7. Honor hook advisories from anti-slop-scan.sh
  8. If the project already has a design system, use custom mode (do not override with presets)
  9. Icons: MUST use Reicon in shipped markup unless project icon lib or text-only waiver (references/compliance-gates.md)
  10. Before DONE on UI builds → Conventions check including Responsive, Hierarchy, Typography, Control geometry, Motion, Shell, Landing (if marketing), A11y; use n/a or an explicit waiver only when a gate does not apply (references/compliance-gates.md)

References

See AGENTS.md for the auto intent map, docs/pillars.md for suite pillars, docs/pack-layers.md for layers.

Verify

./scripts/smoke-test.sh

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