Development

Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.

全栈开发规范百科全书 (React/TS/Node/Supabase). Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend/backend code.

This skill should be used when the user asks to "create custom DSPy module", "design a DSPy module", "extend dspy.Module", "build reusable DSPy component", mentions "custom module patterns", "module serialization", "stateful modules", "module testing", or needs to design production-quality custom DSPy modules with proper architecture, state management, and testing.

Quality Gate Teacher for Spec-Kit-Plus workflow. Acts as a strict reviewer that validates quality (not just existence) of each phase's output before allowing progression. Generates detailed reports and grades work like a teacher. Triggers: validate, quality gate, phase check, workflow status, q-status

Manages workflow state persistence and session recovery for sp.autonomous. Tracks phase progress, feature completion, and provides resume capability. Triggers: workflow state, session recovery, resume autonomous, progress tracking

Comprehensive testing patterns for Jest, Vitest, Playwright, and React Testing Library. Use when writing unit tests, integration tests, or E2E tests.

Ensures Spec-Kit-Plus workflow is properly initialized before autonomous builds. Use when: (1) /sp.autonomous fails to create directories, (2) .specify/ or .claude/ is missing, (3) starting a fresh project, (4) "directory not found" errors during workflow. Provides directory structure creation and template copying patterns.

Analyzes project requirements to identify missing skills and automatically creates them. Enforces MCP Code Execution pattern for skills that use external tools. This skill should be used when starting a new project to ensure all required skills exist.

Template skill demonstrating the MCP Code Execution pattern for 98%+ token efficiency. Use this as a reference when creating skills that interact with MCP servers. Triggers: mcp, code execution, token efficient, tool wrapper, external api

Database design patterns, SQL best practices, ORM usage (Prisma/Drizzle), and migration strategies. Use when designing schemas, writing queries, or optimizing database operations.

Validates that generated skills, agents, and hooks are production-ready before use. Scores components against quality criteria and grades them A-F. Triggers: validate component, quality check, production ready, component validation, skill quality, agent quality, hook quality, phase 6.5

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development. Use when writing any code to ensure consistent quality.

Detect and resolve TypeScript/JavaScript circular import dependencies. Use when: (1) "Cannot access 'X' before initialization" at runtime, (2) Import returns undefined unexpectedly, (3) "ReferenceError: Cannot access X before initialization", (4) Type errors that disappear when you change import order, (5) Jest/Vitest tests fail with undefined imports that work in browser.

Fix Prisma "Too many connections" and connection pool exhaustion errors in serverless environments (Vercel, AWS Lambda, Netlify). Use when: (1) Error "P2024: Timed out fetching a new connection from the pool", (2) PostgreSQL "too many connections for role", (3) Database works locally but fails in production serverless, (4) Intermittent database timeouts under load.

Debug getServerSideProps and getStaticProps errors in Next.js. Use when: (1) Page shows generic error but browser console is empty, (2) API routes return 500 with no details, (3) Server-side code fails silently, (4) Error only occurs on refresh not client navigation. Check terminal/server logs instead of browser for actual error messages.

Claudeception is a continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /claudeception command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or trial-and-error discovery. Creates new Claude Code skills when valuable, reusable knowledge is identified.

Backend architecture patterns, API design, database optimization, and server-side best practices. Use when building APIs, services, or server-side functionality.

REST API and GraphQL design patterns, authentication, error handling, and best practices. Use when building APIs, designing endpoints, or implementing backend services.

Use OpenSpec for specification-driven development. Apply when planning features, implementing changes, or managing project deliverables.

Git branch workflow for autonomous work. Apply when implementing features, fixes, or any code changes.

Systematic error diagnosis and resolution using first-principle analysis. Use when encountering any error message, stack trace, or unexpected behavior. Supports replay functionality to record and reuse solutions.

Execute set up local development workflow with Sentry. Use when configuring Sentry for development environments, setting up debug mode, or testing error capture locally. Trigger with phrases like "sentry local dev", "sentry development", "debug sentry", "sentry dev environment".

Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.

Install and configure Sentry SDK authentication. Use when setting up a new Sentry integration, configuring DSN, or initializing Sentry in your project. Trigger with phrases like "install sentry", "setup sentry", "sentry auth", "configure sentry DSN".