Route backend tasks to the right library skill. Detects intent and returns specific skill file paths to load.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
You are the Backend Gateway. Your job is to detect intent from the current task and return the exact library skill paths that should be loaded. Do NOT execute the task — only route to the right knowledge.
Read the task description and match against these patterns:
| Intent Keywords | Load Skill |
|---|---|
tdd, test-driven, red-green, failing test first | skills/library/backend/developing-with-tdd/SKILL.md |
debug, diagnose, trace, investigate, root cause | skills/library/backend/debugging-systematically/SKILL.md |
auth, jwt, oauth, session, token, login | skills/library/backend/implementing-auth/SKILL.md |
middleware, interceptor, pipeline, chain | skills/library/backend/writing-middleware/SKILL.md |
cache, redis, memcache, invalidate | skills/library/backend/caching-strategies/SKILL.md |
queue, worker, job, background task, async | skills/library/backend/async-job-queues/SKILL.md |
websocket, realtime, socket.io, sse | skills/library/backend/realtime-connections/SKILL.md |
error handling, exception, retry, circuit breaker | skills/library/backend/error-handling-patterns/SKILL.md |
rate limit, throttle, ddos | skills/library/security/rate-limiting/SKILL.md |
Return ONLY this — no prose:
GATEWAY_BACKEND:
Domain: backend
Skills to load:
- [absolute/path/to/SKILL.md]
- [absolute/path/to/SKILL.md]
Instructions: Read the above skill files before proceeding with your task.
If no specific skill matches, return:
GATEWAY_BACKEND:
Domain: backend
Skills to load: none (proceed with general backend patterns)
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Drive a real browser from the command line — open pages, snapshot the interactive elements as refs, click and fill by ref, read text, run JS, screenshot. Use when a task needs a live browser: checking a page renders, walking a login or checkout flow, scraping something that only exists after JavaScript runs, or reproducing a UI bug.
中文简介正在准备中。当前显示原文说明。
Run linters/typecheckers to calculate health score.
中文简介正在准备中。当前显示原文说明。
Comprehensive UI/UX compliance check (A11y, performance, responsive).
中文简介正在准备中。当前显示原文说明。
Infrastructure-first security audit (OWASP, secrets, dependencies).
中文简介正在准备中。当前显示原文说明。
Setup authentication flow (register, login, session/JWT, middleware)
中文简介正在准备中。当前显示原文说明。
Deep knowledge about deploying applications to AWS (EC2, ECS, S3, CloudFront, Cloud Run).
中文简介正在准备中。当前显示原文说明。