调试
定位并修复问题，分析错误
sp-coding-agent
cuongpt083
Use when a coding task is vague or under-specified. Extracts missing context across 9 code-native categories before the agent executes file changes. Designed for OpenAI Codex, Anthropic Claude Code, and Google Gemini Code Assist.
planning-task-classifier
OzeroHAX
Classify a task (bug/feature/refactor/migration) and what the plan must emphasize
clarity-gate
frmoretto
Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.
planning-scope-minimization
OzeroHAX
Minimize changes for bugs/incidents: the smallest safe fix
testing-load
OzeroHAX
Load testing (k6/JMeter scenarios, benchmarks)
planning-requirements-extraction
OzeroHAX
Extract requirements from a request: behavior, AC, constraints; for bugs - repro
planning-change-inventory
OzeroHAX
Enumerate concrete files/components and intended edits tied to AC; not broad cross-system impact analysis
testing-contract
OzeroHAX
Verify provider-consumer API contract compatibility and versioning; not ad-hoc endpoint behavior checks
collaborating-with-codex
GuDaStudio
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.
webapp-testing
xenitV1
Web application testing principles. E2E, Playwright, deep audit strategies.
systematic-debugging
xenitV1
4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.
testing-patterns
xenitV1
Testing patterns and principles. Unit, integration, mocking strategies.
nextjs-best-practices
xenitV1
Next.js App Router principles. Server Components, data fetching, routing patterns.
lint-and-validate
xenitV1
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
brainstorming
xenitV1
Socratic questioning protocol + user communication. MANDATORY for complex requests, new features, or unclear requirements. Includes progress reporting and error handling.
behavioral-modes
xenitV1
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
react-patterns
xenitV1
Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
mcp-builder
xenitV1
MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
nodejs-best-practices
xenitV1
Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.
server-management
xenitV1
Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.
svelte
dylantarre
Builds token-driven Svelte 5 components with runes ($state, $props) and TypeScript. Use when creating Svelte component libraries, integrating design tokens, or building SvelteKit design system components.
react
dylantarre
Builds token-driven React components with TypeScript and modern patterns. Use when creating React component libraries, integrating CSS custom properties, or building Next.js design system components with forwardRef and composition.
vue
dylantarre
Builds token-driven Vue 3 components with Composition API and TypeScript. Use when creating Vue component libraries, integrating design tokens, or building Nuxt design system components with composables.
isentinel
christopher-buss
Opinionated preferences for roblox-ts development. Use when setting up new roblox-ts projects or when coding style/tooling decisions arise.