GitHub
evolve
自我進化 Agent：給定目標，自主學習並迭代改進直到完成。
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
create-plan
Create structured Plan.md files for complex multi-step tasks. Analyzes task requirements, breaks them down into actionable steps with estimates, identifies dependencies between steps, flags steps requiring huma...
GitHub
opencode-docs
OpenCode + OhMyOpenCode configuration reference - agents, tools, MCP, skills, commands, hooks, permissions, providers, and Sisyphus orchestration patterns
GitHub
memory-contract
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional.
GitHub
total-recall
Search past conversations for relevant context
GitHub
langgraph-v1
Use when writing or refactoring Python code for LangGraph v1.x + LangChain v1: Graph API + Functional API import paths, checkpoint/store usage, and migrations off deprecated prebuilts (create_react_agent -> lan...
GitHub
mcp-server-dev
Patterns for building Model Context Protocol (MCP) servers including tools, resources, prompts, and transport handling. Use when creating MCP servers to extend AI assistant capabilities.
GitHub
claude-code-plugins
Patterns for building Claude Code plugins including commands, agents, hooks, MCP servers, and plugin marketplaces. Use when creating extensions for Claude Code or distributing plugins to teams.
GitHub
vercel-ai-sdk
Patterns for building AI applications with Vercel AI SDK including streaming LLM responses, tool calling, structured outputs, and multi-provider support. Use when integrating LLMs into applications.
GitHub
project-pipeline
Orchestrates the complete lifecycle of a new software project. Use this skill to initiate a new project from a vague idea, guiding it through architectural brainstorming, component definition, and detailed PRD...
GitHub
skill-best-practices
Guides creation of Anthropic-compliant Claude skills. Triggers on: create skill, new skill, skill guidelines, skill best practices, write a skill.
GitHub
claude-agent-sdk
Development guide for Claude Agent SDK integration in IPA Platform. Use when: - Building autonomous AI agents with Claude - Implementing agents that need to make independent decisions - Creating agents with to...
GitHub
claude-api-reference
Claude API development reference guide. Use when developing Claude API applications for Messages API, Vision, PDF processing, Tool Use, Streaming, and more. Triggers: (1) Claude API integration development, (2)...
GitHub
ask
ユーザーに質問を投げかけるアシスタント。AskUserQuestionツールを使って選択肢付きの質問を提示します。
GitHub
ai-image-tools
Generate and edit images using either OpenAI GPT Image 1.5 or Google's Nano Banana Pro (Gemini 3 Pro Image). Use when the user asks to generate/create/edit/modify images. Supports image-to-image editing for bot...
GitHub
git-hygiene
How to track our work through commits, pull-requests, and pushes. Maintain proper git hygiene in our chaotic, multi-agent environment through atomic commits, with the option to have code reviewed by AI agents w...
GitHub
langfuse-cli
This skill should be used when the user asks to "query Langfuse traces", "show sessions", "check LLM costs", "analyse token usage", "view observations", "get scores", "create score", "add score to trace", "quer...
GitHub
eval-design
This skill should be used when the user asks "what evals can we create", "how do I evaluate this", "design an eval", "create evals for", "how do I know if my LLM is working", "measure quality", or mentions eval...
GitHub
langgraph
LangGraph patterns for AI agents and workflows. Use when: building ReAct agents, multi-agent systems, human-in-the-loop, state machines. Do not use for: simple LLM calls (use langchain directly). Workflow: Stan...
GitHub
gemini-cli
Use the Google Gemini CLI to get a second opinion on code, architecture, and UI/UX work. Trigger when a user asks to consult Gemini, wants an external critique, or requests UI feedback, design alternatives, or...
GitHub
requirements-elaboration
Transform vague requirements into concrete decisions by exploring the decision space. Use when high-level asks spawn implicit decisions, when defaults need challenging, or when you need systematic discovery of...
GitHub
framework-to-mastra
Convert operating-frameworks skills into deployed Mastra+Hono agents with APIs, workflows, and persistent memory. Use when deploying a framework as an API, creating agent versions of diagnostic skills, or build...
GitHub
skill-builder
Build new agent skills. Use when creating diagnostic frameworks, CLI tools, or data-driven generators that follow the established skill patterns.
GitHub
gentle-teaching
Guide AI-assisted learning that empowers learners while maintaining appropriate boundaries. Use when teaching, explaining concepts, or helping someone who is struggling to understand.
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.