Claude Code 플러그인

@ai-builder-club · AI-Builder-Club/skills

1.3천

Loops (a file-based knowledge base) + a codebase harness (dev-local, e2e, crabbox cloud boxes, verify-before-ship) so agents can run, test, and ship code autonomously.

@finding-unknowns-skills · Neeeophytee/finding-unknowns-skills

372

Skills for finding unknowns before they get expensive, testing assumptions, examining test blindspots, and rightsizing agent context.

@allanops · AllanOps/Clean-Backend

9

The backend habits an AI assistant misses on its own — API versioning, feature flags, circuit breakers, and four more. Measured, not asserted.

@tt-a1i · tt-a1i/matt-skills-with-to-goal

195

Independent engineering skills with verifiable goal handoffs and optional forked execution.

@agent-ready-repo · eugenelim/agent-ready-repo

29

Build the web surface, then prove it holds up. HTML, CSS, and JS with a real token system, a WCAG 2.2 AA target, and Core Web Vitals measured rather than asserted. A reviewer reads the diff for the regressions those three tend to hide.

@dev-flow · lukedj78/dev-flow

5

57 skills over one .workflow/meta.json contract: PRD → design → scaffold → modules → tests → pre-deploy gates → deploy, for Next.js 16 web, Expo/RN mobile, turborepo monorepos and an eve agent engine.