agentrigs
+ submit rig
~ / rigs / ibelick / ui-skills

ibelick/ui-skills

Skills for Design Engineers

↗ GitHub ★ 9,519 mit updated 2d ago collection Codex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~817 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit ibelick/ui-skills/skills ./rig-ui-skills/skills

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 ibelick/ui-skills/skills/baseline-ui .claude/skills/baseline-ui
$ npx degit ibelick/ui-skills/skills/create-design-md .claude/skills/create-design-md
$ npx degit ibelick/ui-skills/skills/fixing-accessibility .claude/skills/fixing-accessibility
$ npx degit ibelick/ui-skills/skills/fixing-metadata .claude/skills/fixing-metadata
$ npx degit ibelick/ui-skills/skills/fixing-motion-performance .claude/skills/fixing-motion-performance
$ npx degit ibelick/ui-skills/skills/improve-ui .claude/skills/improve-ui
$ npx degit ibelick/ui-skills/skills/ui-skills-root .claude/skills/ui-skills-root

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (7)

baseline-uicreate-design-mdfixing-accessibilityfixing-metadatafixing-motion-performanceimprove-uiui-skills-root

Similar rigs

Ralph-Workflow/Ralph-Workflow
Autopilot for AI Coding Agents, supports OpenCode, Claude Code, pi.dev, Cursor, and many more
★ 6 project Claude CodeCodex 1 mcp 28 skills today
Skill Collector 9.0k tok ·
HatriGt/agent-sandbox
A cloud sandbox for coding agents, on your own server. Start a run from the dashboard, from any agentic IDE (Cursor, Claude Code, Codex, VS Code), or from a script — it runs in an isolated KVM microVM and streams back live.
★ 0 project Claude Code 7 skills today
Pragmatist 391 tok ·
AjayIrkal23/agentic-mercy-10x
My complete Claude Code agentic workspace - 200+ curated skills, 9-agent specialist mesh, 3-act /invoke orchestration, enforcement hooks. Clone + one command = full setup.
★ 13 collection Claude CodeCodex 129 skills 18 agents 3d ago
Orchestrator 8.6k tok ·
Harmitx7/tribunal-kit
A universal, native-Rust governance layer for AI coding agents. Enforces Subagent-Driven Development (SDD) to stop hallucinations before they hit disk.
★ 5 collection Claude CodeCodexGemini CLI 150 skills 7d ago
Skill Collector 9.9k tok ·
copied ✓