Enhanced meta-orchestration for selecting and combining reasoning patterns. Now includes 9 methodologies (ToT, BoT, SRC, HE, AR, DR, AT, RTR, NDF) with weighted multi-dimensional selection, feedback loops, uncertainty propagation, and validated confidence aggregation. Use when facing complex problems requiring optimal reasoning strategy selection.
This skill exists to create new skills via the bundled CLI workflow.
The master skill for analyzing, designing, and standardizing the creation of new AI skills (Skill 72).
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 a codebase - Preparing context for subagent delegation - Recovering from session compaction - Handoff between agents needs structured context Do NOT use for: - Simple file reads (use Read tool directly) - Small projects that fit in context easily - Questions about specific files (just read them)
OpenAI official SDK usage (Python, Node.js). Use when: writing code that calls OpenAI API, implementing chat/embeddings/images/audio features, handling streaming responses, async patterns, error handling with SDK. For raw HTTP/REST calls, see `openai-api` skill.
Build LLM applications using Dify's visual workflow platform. Use when creating AI chatbots, implementing RAG pipelines, developing agents with tools, managing knowledge bases, deploying LLM apps, or building workflows with drag-and-drop. Supports hundreds of LLMs, Docker/Kubernetes deployment.
Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.
Complete guide to using Sequential Thinking MCP server with Claude Code
Expert Python developer specializing in modern Python 3.11+ with deep expertise in type safety, async programming, testing, and production-grade code. Invoke for Pythonic patterns, type hints, pytest, async/await, dataclasses.
Generate a project-specific CLAUDE.md file by auto-detecting tech stack and asking clarifying questions. Use when starting work on a new project or when a project lacks a CLAUDE.md.
Best practices for writing AGENTS.md, agent configs, and skill files based on industry research
Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers tool design, authentication, Docker deployment, and evaluation creation. NOT when consuming existing MCP servers (use the server directly).
Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations
Guide for distinguishing Claude Code features (Commands, Skills, Agents, Hooks, Rules) and selection criteria. Use when decomposing context files, deciding where to add new features, or customizing Claude Code.
Process learning resources from markdown files, extract content, identify clusters, and create Ship-Learn-Next learning paths
Add MCP servers to Claude Code configuration at user level (~/.claude). Supports stdio, HTTP, and SSE transports with environment variable prompting. Use when "add mcp server", "install mcp", "configure mcp server", "new mcp", or "setup mcp server".
Sync Azure Codex fork with OpenAI Codex upstream while preserving Azure features
Handle vision/image tasks (read, describe, analyze images) by calling Gemini CLI or Qwen Code CLI from the shell. Use for requests to interpret or describe images, extract visible text, or summarize visual content; prefer Gemini and fall back to Qwen if Gemini fails or is too generic.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
Core rules for Alfred SuperAgent - 3-Layer Architecture, 4-Step Workflow, Agent-First
Use this skill when users want to generate images using OpenAI's image generation API (DALL-E or gpt-image-1), or extract text from images using OCR. Invoke when users request AI-generated images, artwork, logos, illustrations, visual content from text prompts, or need to extract text/data from images.
Patterns for building AI-powered chatbot backends using OpenAI Agents SDK with MCP (Model Context Protocol) server integration in FastAPI applications. Supports both standalone MCP servers and function tools.
Design patterns for building autonomous AI agents that can reason, plan, and execute tasks.
