菜单
Run typecheck, lint, test, and build quality gates
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Open the Claude Session Dashboard in the browser. Starts it first if not already running. Checks for and installs updates before starting.
Analyze ~/.claude session files to find unused agent skills and reduce context token waste. Scans subagent JSONL files for injected skills and cross-references with agent responses.
Full SDLC pipeline: design → plan → implement → review → test → ship. Use this skill when the user wants to BUILD A NEW FEATURE that spans multiple files across scanner, server functions, and UI layers — anything requiring architecture design, an implementation plan, and coordinated changes across a vertical slice. Trigger on: /feature command, 'build/implement/add [feature]' requests involving new server functions + UI components, multi-step feature work needing TDD and code review. Do NOT trigger for: bug fixes, refactors, small UI tweaks, single-file changes, CI fixes, test runs, or PR reviews.
Investigate and fix the latest failing CI workflow
Fix a GitHub issue end-to-end
Investigate a URL or page using Playwright browser
基于 SOC 职业分类
| name | quality-check |
| description | Run typecheck, lint, test, and build quality gates |
| user-invocable | true |
Run the full quality suite for the project.
Run each check sequentially from apps/web/. Report pass/fail for each:
cd apps/web && npm run typecheck
cd apps/web && npm run lint
cd apps/web && npm run test
cd apps/web && npm run build
After all checks complete, output a summary table:
| Check | Status |
|---|---|
| typecheck | PASS/FAIL |
| lint | PASS/FAIL |
| test | PASS/FAIL |
| build | PASS/FAIL |
If any check fails, show the first 20 lines of errors and suggest fixes.
src/routes/demo/ should be ignored