Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Expert FastAPI backend development for building high-performance REST APIs with Python. Use when building APIs, creating endpoints, implementing CRUD operations, integrating databases (SQL/NoSQL), adding valida...
Expert database design, queries, and optimization for both SQL (Neon serverless PostgreSQL) and NoSQL (MongoDB) databases. Use when designing database schemas, writing queries, creating migrations, optimizing p...
Use when building multi-agent systems with Microsoft Agent Framework. Triggers: "microsoft agents", "agent framework", "semantic kernel", "autogen", "agent graph". NOT for: Simple single-agent scenarios or non-...
Mise configuration and runtime management expert. Use when: - Installing programming language runtimes (node, python, go, rust, etc.) - Configuring tool versions globally or per-project - Questions about mise.t...
Use when implementing different agent types in Microsoft Agent Framework. Triggers: "ChatAgent", "BaseAgent", "WorkflowAgent", "A2A agent", "custom agent class". NOT for: Non-Microsoft agent frameworks or simpl...
Use when coordinating multiple AI agents for parallel work. Triggers: "multi-agent", "parallel agents", "agent coordination", "QuantumDAG", "conflict-free". NOT for: Single-agent operations or basic jj commands...
Use when building web interfaces for Microsoft Agent Framework agents. Triggers: "AG-UI", "agent UI", "agent web interface", "SSE streaming", "human-in-the-loop UI". NOT for: CLI-only agents or backend-only imp...
Use when implementing self-learning agent workflows. Triggers: "agent learning", "trajectory", "pattern recognition", "AgentDB", "self-learning agent". NOT for: Basic agent operations without learning requireme...
Use when building multi-agent workflows with Microsoft Agent Framework. Triggers: "workflow builder", "sequential workflow", "concurrent agents", "handoff", "group chat", "magentic". NOT for: Single-agent scena...
Tiered context management for multi-agent workflows. Use when: - Starting a new session and need to load project context - Context window approaching capacity (>70% usage) - Switching between different parts of...
Instructions for starting the MCP Synth server (FastAPI) for synthetic data generation and tools.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Reviews conversation context to identify learnings and patterns that should be captured in skills. Use when the user asks to review the session for skill creation or updates.
Use this skill for [purpose]. Triggers when user mentions [keywords]. Provides guidelines, templates, and standards for [domain].
Use this skill for client issue triage, bug resolution, and troubleshooting. Triggers when user mentions client issue, bug, support ticket, problem, or troubleshooting. Provides response templates, severity ass...
Use this skill when the conversation requires integrating AI services (such as image analysis, text generation, intelligent recognition, etc.) to generate integration code based on AI gateway or API
Generate a recap of recent Claude Code sessions with summaries of what was discussed and accomplished
Use this skill when the user wants to call different LLM models through OpenRouter's unified API, compare model responses, track costs and response times, or find the best model for a task. Triggers include req...
ONLY trigger this skill when the user EXPLICITLY asks for MCP-based testing: **Required triggers (ALL must mention "MCP" explicitly):** - "test connector with mcp" - "test mcp connector" - "test [provider] wit...
This skill provides API route patterns and conventions for the fitness app. Use when creating or modifying API routes, handling authentication, validating requests, or implementing error handling.
Guide users through a structured workflow for co-authoring articles, blog posts, personal essays, or informal longform writing; help gather context, iterate on structure, and reader-test tone and clarity. Use w...
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
Project-specific architectural patterns and tribal knowledge. Copy this skill to your project's .claude/skills/ and customize with your team's conventions, decision trees, and critical pitfalls.
Generate structured Game Design Documents for prototypes through interactive Q&A. Use this when the user wants to document a game concept, create a prototype GDD, or formalize their design ideas.
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.