菜单
Deploy backend and/or frontend services. Use after npm run build completes, when restarting services, when user mentions deploy/build/restart, or when page shows Application error. Also trigger on 502/503 errors, service health check failures, or after code changes that need deployment.
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
Test API endpoints with proper authorization including Basic Auth and session cookies. Use when testing curl requests, checking API responses, getting 401 Unauthorized, session expired errors, or verifying endpoint behavior after changes.
Implement accumulated improvements from improvements-backlog into AI rules and skills. Use when backlog has 5+ items, weekly rule update cycle, 2+ high priority improvements exist, before important releases, when same error repeated 3+ times, when user says implement improvements/process backlog/update rules from errors.
Fix bugs, errors, exceptions, and unexpected behavior. Use when debugging, fixing errors, handling crashes, or when user mentions bug, error, broken, not working, crash, exception, 500 error, Application error, white screen, TypeError, undefined is not a function, or unexpected behavior.
Analyze Claude Code prompt cache efficiency and costs. Use when user asks about cache performance, token usage, session costs, how much a session cost, wants to optimize prompt caching, when costs seem high, when context window is filling up, or mentions cache-analyzer/cache hits/token costs/session metrics/cost analysis.
Review code for quality, security, and maintainability. Use when reviewing pull requests, examining code changes, doing QA checks, architecture review, or CTO review. Also trigger for COMPLEX tasks affecting more than 5 files, API contract changes, or data migrations.
Create new skills, modify and improve existing skills, create or update AI rules. Use when creating rules, building skills, adding coding standards, updating .claude/rules/ or .claude/skills/, converting Cursor rules to Claude Code, measuring skill performance, running evals, or optimizing skill descriptions.
| name | deploy-app |
| description | Deploy backend and/or frontend services. Use after npm run build completes, when restarting services, when user mentions deploy/build/restart, or when page shows Application error. Also trigger on 502/503 errors, service health check failures, or after code changes that need deployment. |
| allowed-tools | Bash, Read |
| model | sonnet |
| user-invocable | true |
Build, restart services, and verify the app is working.
Configuration: .cursor/config/project.config.json
Next.js serves the old build until the systemd service restarts. If you build but forget to restart, users see stale code. If you restart without building, the service may crash on missing files. The sequence build -> restart -> verify exists because each step depends on the previous one succeeding.
Run: bash ${CLAUDE_SKILL_DIR}/scripts/deploy-backend.sh
Or manually:
npm run build (from project root)sudo systemctl restart crmaicurl -s -u user:pass "https://site/api/health"systemctl status crmai | tail -10Run: bash ${CLAUDE_SKILL_DIR}/scripts/deploy-frontend.sh
Or manually:
cd apps/web && npm run buildsudo systemctl restart crmai-webcurl -s -u user:pass "https://site/" | grep "Application error"systemctl status crmai-web | tail -10Run: bash ${CLAUDE_SKILL_DIR}/scripts/deploy-all.sh
Run: bash ${CLAUDE_SKILL_DIR}/scripts/verify-pages.sh
Basic Auth credentials: read from .cursor/.secrets/ (path in config)