菜单
Use for backend / admin / database / API / Supabase work — schema changes, new routes, admin features, import/export flows.
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
| name | backend-admin-supabase |
| description | Use for backend / admin / database / API / Supabase work — schema changes, new routes, admin features, import/export flows. |
| when_to_use | ["Adding a server route","Touching the Supabase schema","Building / modifying the admin panel","Import / export flows for shops, leads, newsletter, billing"] |
| related_files | ["server/**","supabase/**","admin/**","docs/API_BACKEND_FOUNDATION.md","docs/SUPABASE_SCHEMA.md","docs/ADMIN_GUIDE.md"] |
| related_prompts | [".github/prompts/backend-admin-supabase.prompt.md"] |
Anchors backend work to the patterns the repo already uses: thin routes, lib/repository separation, file-fallback for tests, admin/audit boundary, RLS-by-default.
docs/API_BACKEND_FOUNDATION.md and docs/SUPABASE_SCHEMA.md.lib/; persistence in repositories/ with file fallback.node:test, using env-overridden file paths for hermetic runs.docs/ (route table, schema doc, env vars).npm test, npm run lint, npm run validate..env.example + docs/environment-variables.md.Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
Debugging specialist for errors, test failures, and unexpected behavior. Use when encountering reproducible bugs; follow reproduction steps and remove instrumentation before finishing.
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
Adversarial multi-model code review — launch parallel readonly reviewers on different models, then synthesize consensus vs lone findings. Do not apply fixes unless the user asks.
Reproduce reported bugs before fixing. Provide evidence of reproduction and the fix; do not stop after repro to ask the user—continue to fix.
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor SDK - TypeScript (@cursor/sdk) or Python (cursor-sdk / cursor_sdk). Use when integrating Cursor agents programmatically; Agent.create, Agent.prompt, streaming, local vs cloud runtime, MCP, errors.