shipshape-skills

Diagnose and incrementally fix build and type errors with minimal changes. Use when the build is broken, TypeScript reports errors, or CI fails due to compilation issues.

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.

Full development workflow for new features — 10 stages from brainstorming to code review. Use when the user wants to build a new feature, add functionality, or implement a user story. Each stage has its own detailed skill file.

Initialize project for shipshape-skills — generate CLAUDE.md and project-specific skills structure through interactive questions.

Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.

Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

Iteratively write, review, and improve frontend unit tests until quality score >= 9.2. Supports Vue 3 (Vitest + @vue/test-utils) and React (Vitest/Jest + React Testing Library). Auto-triggers when writing or improving unit tests.

當使用者描述程式行為與預期不符時觸發 — 不論是明確說「有 bug」，還是隱含的「為什麼會這樣」「明明應該 X 卻 Y」「這裡怪怪的」。修復後判斷根因是否值得沉澱到 cookbook、memory 或 workflow，防止同類錯誤再次發生。只要使用者的描述暗示了「現狀 ≠ 預期」，就應該考慮觸發此 skill。

Universal coding standards for TypeScript, JavaScript, React, and Node.js. Use when reviewing code quality, enforcing naming and structural conventions, refactoring for maintainability, or setting up a new module. Also triggers when code smells like deep nesting, magic numbers, or unclear naming are detected.

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing, debugging, or improving end-to-end tests with Playwright. Triggers for any E2E testing task even if Playwright is not explicitly mentioned.

React 前端開發模式，涵蓋 Hooks、狀態管理、Custom Hooks、效能優化與常見反模式。當建構 React 元件、撰寫自定義 Hook、管理狀態或優化效能時觸發。即使使用者沒有明確提到 React patterns，只要涉及 React 開發就應該使用此 skill。

3 hooks across 3 events