~ / rigs / tansuasici / claude-design-kit

tansuasici/claude-design-kit

Drop-in starter templates that make Claude Code design like an opinionated designer-engineer instead of a template generator — interfaces that look chosen, not defaulted. 6 hooks, 8 skills, 3 review agents.

↗ GitHub ★ 0 NOASSERTION updated 16d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~3.8k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Quality 56/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit tansuasici/claude-design-kit/.claude ./rig-claude-design-kit  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit tansuasici/claude-design-kit/.claude/skills/brand-method .claude/skills/brand-method
$ npx degit tansuasici/claude-design-kit/.claude/skills/design-brief .claude/skills/design-brief
$ npx degit tansuasici/claude-design-kit/.claude/skills/direction .claude/skills/direction
$ npx degit tansuasici/claude-design-kit/.claude/skills/interface-check .claude/skills/interface-check
$ npx degit tansuasici/claude-design-kit/.claude/skills/motion-craft .claude/skills/motion-craft
$ npx degit tansuasici/claude-design-kit/.claude/skills/motion-review .claude/skills/motion-review
$ npx degit tansuasici/claude-design-kit/.claude/skills/slop-audit .claude/skills/slop-audit
$ npx degit tansuasici/claude-design-kit/.claude/skills/stress-ui .claude/skills/stress-ui
$ curl -fsSL --create-dirs -o .claude/agents/design-critic.md https://raw.githubusercontent.com/tansuasici/claude-design-kit/main/.claude/agents/design-critic.md
$ curl -fsSL --create-dirs -o .claude/agents/interface-reviewer.md https://raw.githubusercontent.com/tansuasici/claude-design-kit/main/.claude/agents/interface-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/motion-reviewer.md https://raw.githubusercontent.com/tansuasici/claude-design-kit/main/.claude/agents/motion-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/design-critic.md https://raw.githubusercontent.com/tansuasici/claude-design-kit/main/agents/design-critic.md
$ curl -fsSL --create-dirs -o .claude/agents/interface-reviewer.md https://raw.githubusercontent.com/tansuasici/claude-design-kit/main/agents/interface-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/motion-reviewer.md https://raw.githubusercontent.com/tansuasici/claude-design-kit/main/agents/motion-reviewer.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Bash(cat *id_rsa*)",
      "Bash(cat .env*)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": ".claude/hooks/branch-protect.sh"
          },
          {
            "type": "command",
            "command": ".claude/hooks/block-dangerous-commands.sh"
          }
        ]
      }
    ]
  }
}

Skills (8)

Subagents (6)

design-critic
model: opus
Independent visual critic. Judges a rendered screen against DESIGN_MAP.md (character, world, signature, tokens) and the slop signs, runs the competitor test, and returns a ranked list of what makes it
interface-reviewer
model: opus
Independent interface-behaviour reviewer. Audits UI code (and the running screen, if a browser is available) against agent_docs/interface-guidelines.md: keyboard, focus, targets, forms, URL state, fee
motion-reviewer
model: opus
Independent motion reviewer. Measures every animation in scope against the ten motion standards in /motion-review (justified, frequency, easing, duration, origin, interruptibility, GPU-only, accessibi
design-critic
model: opus
Independent visual critic. Judges a rendered screen against DESIGN_MAP.md (character, world, signature, tokens) and the slop signs, runs the competitor test, and returns a ranked list of what makes it
interface-reviewer
model: opus
Independent interface-behaviour reviewer. Audits UI code (and the running screen, if a browser is available) against agent_docs/interface-guidelines.md: keyboard, focus, targets, forms, URL state, fee
motion-reviewer
model: opus
Independent motion reviewer. Measures every animation in scope against the ten motion standards in /motion-review (justified, frequency, easing, duration, origin, interruptibility, GPU-only, accessibi

Hooks (6)

eventmatcherruns
SessionStart*.claude/hooks/session-start.sh
UserPromptSubmit*.claude/hooks/prompt-router.sh
PreToolUseBash.claude/hooks/branch-protect.sh
PreToolUseBash.claude/hooks/block-dangerous-commands.sh
PostToolUseEdit|Write|MultiEdit.claude/hooks/slop-scan.sh
PostToolUseEdit|Write|MultiEdit.claude/hooks/motion-gate.sh

Permissions

deny (2)
Bash(cat *id_rsa*)
Bash(cat .env*)
ask (0)
—
allow (10)
Bash(git status*)
Bash(git diff*)
Bash(git log*)
Bash(git branch*)
Bash(git show*)
Bash(ls*)
Bash(pwd)
Bash(which*)
Bash(cat DESIGN_MAP.md)
Bash(cat linear.md)

Similar rigs

copied ✓