Craft Analyze — Testing skill for Claude Code
Post-cycle analysis — QA, UX, Creative, and Style audits using MCP browser tools.
How to install Craft Analyze
Installs to ~/.claude/skills/drobins25-craft-craft-analyze/SKILL.md
mkdir -p ~/.claude/skills/drobins25-craft-craft-analyze && curl -fsSL https://raw.githubusercontent.com/drobins25/craft/HEAD/commands/craft-analyze.md -o ~/.claude/skills/drobins25-craft-craft-analyze/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Craft Analyze does
name: analyze description: "Post-cycle analysis — QA, UX, Creative, and Style audits using MCP browser tools."
Analyze
Run comprehensive analysis on what you've built. Findings persist between sessions — nothing gets lost.
Analysis Types
| Type | Agent | Finds |
|---|---|---|
| QA | qa-analyzer | Bugs, errors, edge cases |
| UX | ux-analyzer | Friction, accessibility, heuristic violations |
| Creative | creative-analyzer | Delight opportunities, feature id |
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Claude Code Spec Workflow — Automated Kiro-style Spec workflow for Claude Code 3.6k ★
- Cc Sdd — Spec-driven development (SDD) for your team's workflow 3.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Writing Craft
A blind tested skill for better creative writing. Nine signals three AI judges named after scoring 50 samples
Explore URL
Explore, analyze, and summarize a website or URL using the Playwright MCP browser.
18 Scroll Driven Product Landing Page Builder
You are an autonomous senior product website builder, creative director, frontend developer, copywriter, asset
Codex Skills
Five Codex CLI skills that give OpenAI Codex a Claude Code-style workflow (feature dev, PR review, browser tes
MCP Smoke
Post-publish MCP smoke test — installs the published tarball in /tmp, performs MCP initialize + tools/list JSO
Vi Chan Terminal
♡ Vi-Chan Terminal: a kawaii, Claude-Code-style AI agent for your terminal. Bring any API key (OpenAI, Gemini,
Related Agents
Deploy QA
Post-deploy verification in a real browser using the Playwright MCP tools - smoke tests of key journeys, conso
Manual QA
Use when a change needs to be exercised in a real running app — not unit tests, but a human-style check of the
Post Critic
Red-teams a finished infographic for copy hooks, clean creative structure, verified identity assets, typograph