a11y
Accessibility audit + auto-fix (WCAG 2.2 A/AA). Scans built/static HTML for screen-reader, keyboard, and structure failures,…
Run Lighthouse performance audit with auto-fix for common issues. Use when user wants to check or improve site performance.
Claude Code
$ npx -y skills add Houseofmvps/ultraship --skill perf-audit --agent claude-code
Codex
$ npx skills add Houseofmvps/ultraship --skill perf-audit -a codex -y
Cursor
$ npx skills add Houseofmvps/ultraship --skill perf-audit -a cursor -y
Gemini CLI
$ npx skills add Houseofmvps/ultraship --skill perf-audit -a gemini-cli -y
GitHub Copilot
$ npx skills add Houseofmvps/ultraship --skill perf-audit -a github-copilot -y
OpenCode
$ npx skills add Houseofmvps/ultraship --skill perf-audit -a opencode -y
Windsurf
$ npx skills add Houseofmvps/ultraship --skill perf-audit -a windsurf -y
name: perf-audit description: Run Lighthouse performance audit with auto-fix for common issues. Use when user wants to check or improve site performance. argument-hint: "<url>" allowed-tools: Bash, Read, Edit, Grep, Glob
Run Lighthouse against the project and fix performance issues.
node ${CLAUDE_PLUGIN_ROOT}/tools/lighthouse-runner.mjs <url>Parse JSON output for scores and opportunities.
Present all four Lighthouse scores:
Report Core Web Vitals with targets:
Before fixing, identify what's actually causing problems:
**LCP too high?** Check `lcp_element` in results — fix THAT specific element:
**CLS too high?** Check diagnostics for layout shift sources:
**Unused resources?** Check `wasted_resources`:
**Third-party scripts slow?** Check `third_party_impact`:
For each opportunity, apply fixes using Edit tool:
**Performance fixes (high impact first):**
**Accessibility fixes:**
**Fix, don't just audit.** Identify the specific elements causing problems. Apply every automated fix possible. For build-tool changes (code splitting, tree shaking), provide exact config recommendations.
"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.
Accessibility audit + auto-fix (WCAG 2.2 A/AA). Scans built/static HTML for screen-reader, keyboard, and structure failures,…
Living Architecture Map — auto-generate Mermaid diagrams of your codebase. Use when user wants to visualize architecture,…
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.…
Post-deploy canary monitoring — checks site health, detects regressions, monitors for errors after deployment. Use after…
Learn From the Best — analyze patterns from any codebase and apply them to yours. Use when user wants to adopt best practices…
Code review with principal-engineer-level depth. Reviews for correctness, performance, security, maintainability, and…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.