ai-agent-basics
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
Integrate LLMs into applications - APIs, prompting, fine-tuning, and context management
Build multi-agent systems - orchestration, coordination, workflows, and distributed architectures
Expert knowledge for interpreting Figma design tokens and generating iOS-native SwiftUI code. Includes token mapping rules, design system patterns, and SwiftUI best practices for creating production-ready iOS a...
Arquitecto de Software Senior autónomo. Se activa automáticamente para: decisiones técnicas, validación de código, corrección de errores, elección de frameworks, arquitectura, seguridad, performance y debugging...
Validador de Terraform/Infrastructure as Code. Revisar configuraciones de infraestructura, detectar problemas de seguridad, optimizar costos, validar best practices de AWS/GCP/Azure.
Reviewer de manifests Kubernetes. Validar deployments, services, ingress, configmaps, secrets. Detectar problemas de seguridad, recursos mal configurados, best practices de K8s.
Generador de documentación OpenAPI/Swagger. Usar para documentar APIs REST, generar especificaciones OpenAPI 3.0, crear documentación interactiva y exportar a Swagger UI/Redoc.
Analizador de rendimiento de código. Detecta N+1 queries, memory leaks, CPU bottlenecks, bundle size issues, rendering problems en React. Optimiza queries SQL, caching, lazy loading.
Sistema de auto-routing que detecta el tipo de tarea y activa el agente especializado correcto automáticamente. Se activa con cualquier tarea de desarrollo.
Auditoría de seguridad OWASP Top 10. Usar para revisar código en busca de vulnerabilidades, validar autenticación/autorización, analizar input sanitization, detectar SQL injection, XSS, CSRF y otras vulnerabili...
Self-review and fix PR issues after creating a PR. Use after PR creation, when user says "PRレビュー", "セルフレビュー", "PR修正", or "review my PR". Runs pr-review-toolkit and fixes critical/important issues a...
Run code quality checks for Laravel Spectrum (PHPStan, Laravel Pint, PHPUnit). Use when user mentions "lint", "format", "code quality", "PR準備", "コミット前チェック", or before creating commits/PRs. Also use a...
"Research workflow patterns specific to {project}. Covers research agent coordination, source management, and synthesis strategies."
"Domain vocabulary and entity relationships for {project}. Ensures consistent terminology and model understanding."
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
Invoke external AI CLIs via native Task agents (Claude, Codex, Gemini, Cursor). Primary mode for multi-provider orchestration with fork-terminal fallback for auth.
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.
"Custom test patterns and fixtures for {project}. Covers E2E, integration, and specialized testing requirements."
交互式生成 GitHub Copilot agents.md 文件的工作流。当用户请求创建代理、构建自定义 Copilot 代理、生成 agents.md 或需要帮助配置 GitHub Copilot 自定义代理时使用。触发短语包括"创建代理"、"生成 agent.md"、"做一个文档...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoid...
通过 bird CLI 发布和管理 Twitter/X 内容。使用此 skill 当用户需要:(1) 发布推文或帖子,(2) 回复推文,(3) 读取或获取推文内容,(4) 搜索推文,(5) 查看 mentions/bookmarks/likes,(6) 附带图片或视频发推。触发词包括:...
Framework for building AI agents that work effectively across multiple context windows on complex, long-running tasks. Use when building agents for multi-hour/multi-day projects, implementing persistent coding...
API 接口测试工作流,使用 HTTPie 作为核心工具。当用户需要测试 API 接口、执行接口调用、生成测试报告、管理接口依赖关系、或在项目中建立标准化的接口测试流程时使用此 skill。适用于 RESTful API 测试、接口联调、回归测试...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.