菜单
Lists available Cursor agents (planner, architect, tdd-guide, code-reviewer, security-reviewer, build-error-resolver, e2e-runner, refactor-cleaner, doc-updater) and when to use each. Use when the user asks which agent to use, how to delegate work, or what agents are available.
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。
基于 SOC 职业分类
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.
Automate browser interactions, test web pages and work with Playwright tests.
Advanced guidelines and best practices for writing tests using Vitest. Apply this skill when generating, reviewing, or refactoring test codes to prevent common pitfalls and ensure high performance.
Fixed 1536×864 touch viewport — grid, margins, 8px rhythm, touch targets, typography, components, vertical rhythm, and QA checklist for panel/kiosk/HMI. Use when designing or implementing UIs for this resolution with touch-first input.
Async parallelization patterns — Promise.all, waterfall prevention, dependency-based parallelism, RSC component composition, deferred await. Use when optimizing async operations, API routes, or data fetching.
Authenticate server actions with the same rigor as API routes (session, token, CSRF). Use when implementing or securing Next.js server actions.
| name | agent-orchestration |
| description | Lists available Cursor agents (planner, architect, tdd-guide, code-reviewer, security-reviewer, build-error-resolver, e2e-runner, refactor-cleaner, doc-updater) and when to use each. Use when the user asks which agent to use, how to delegate work, or what agents are available. |
Located in ~/.cursor/agents/:
| Agent | Purpose | When to Use |
|---|---|---|
| planner | Implementation planning | Complex features, refactoring |
| architect | System design | Architectural decisions |
| tdd-guide | Test-driven development | New features, bug fixes |
| code-reviewer | Code review | After writing code |
| security-reviewer | Security analysis | Before commits |
| build-error-resolver | Fix build errors | When build fails |
| e2e-runner | E2E testing | Critical user flows |
| refactor-cleaner | Dead code cleanup | Code maintenance |
| doc-updater | Documentation | Updating docs |
No user prompt needed:
ALWAYS use parallel Task execution for independent operations:
# GOOD: Parallel execution
Launch 3 agents in parallel:
1. Agent 1: Security analysis of auth.ts
2. Agent 2: Performance review of cache system
3. Agent 3: Type checking of utils.ts
# BAD: Sequential when unnecessary
First agent 1, then agent 2, then agent 3
For complex problems, use split role sub-agents: