GitHub
agent-sdk-definitions
Programmatic agent definitions for the Claude Agent SDK in TypeScript and Python. Use when creating agents for SDK-based applications rather than filesystem-based Claude Code.
☆ 3View skill
tools llm ai AI Skills
Discover tools llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: tools llm ai
tools llm ai Clear filters
Browse skills
GitHub
huggingface-js
Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.
☆ 3View skill
GitHub
writing-descriptions
Examples and patterns for writing effective agent and skill descriptions. Use when crafting descriptions that serve as routing keys for Claude's invocation decisions.
☆ 3View skill
GitHub
sanity
Manages structured content with Sanity headless CMS using GROQ queries and real-time collaboration. Use when building content-driven sites with customizable schemas, live previews, and flexible data modeling.
☆ 3View skill
GitHub
agent-monitoring
Monitors background agents efficiently using local file reads instead of TaskOutput API calls. Use when running parallel background agents, checking agent progress, detecting completion status, or minimizing to...
☆ 3View skill
GitHub
replicate
Runs open-source ML models via Replicate API for image generation, LLMs, and audio. Use when calling Stable Diffusion, Llama, Whisper, or other models without infrastructure management.
☆ 3View skill
GitHub
openai-api
Integrates OpenAI APIs for chat completions, embeddings, and image generation. Use when building AI-powered features with GPT models, DALL-E, or Whisper in Node.js applications.
☆ 3View skill
GitHub
pinecone
Implements vector search with Pinecone for semantic similarity and RAG applications. Use when building embeddings-based search, recommendation systems, or retrieval-augmented generation.
☆ 3View skill
GitHub
anthropic-api
Integrates Anthropic Claude API for chat, tool use, and vision capabilities. Use when building AI-powered features with Claude models including streaming, extended thinking, and multi-turn conversations.
☆ 3View skill
GitHub
langchain-js
Builds LLM-powered applications with LangChain.js for chat, agents, and RAG. Use when creating AI applications with chains, memory, tools, and retrieval-augmented generation in JavaScript.
☆ 3View skill
GitHub
vercel-ai-sdk
Builds AI-powered applications with Vercel AI SDK including streaming responses, chat interfaces, and model integration. Use when integrating LLMs, building chat applications, streaming AI responses, or impleme...
☆ 3View skill
GitHub
duoduo
双 AI Agent 交叉审查 PR。自动判断共识、决定是否需要交叉确认和修复。当用户要求审查 PR 或提到 "duoduo review" 时触发。
☆ 3View skill
GitHub
seo-geo
Audit website for Generative Engine Optimization (GEO) - optimization for AI search engines like Perplexity, ChatGPT Search, Gemini, and Claude.
☆ 3View skill
GitHub
python-expert
Python backend expert. PROACTIVELY use when working with Django, FastAPI, Flask, Python APIs. Triggers: python, django, fastapi, flask, async python
☆ 3View skill
GitHub
lazy-agent-loader
Load agent definitions on-demand to reduce context usage. Only loads full agent when needed.
☆ 3View skill
GitHub
ai-discovery-expert
AI Discovery and LLM search optimization expert. PROACTIVELY use when optimizing for Perplexity, ChatGPT Search, Gemini, Claude, AI crawlers. Triggers: AI search, Perplexity, ChatGPT, AI discovery, LLM citation
☆ 3View skill
GitHub
stitch-design
Generate UI designs using Google Stitch AI with optimized prompts
☆ 3View skill
GitHub
sequential-thinking
Structured thinking process for complex analysis. Supports revision, branching, and dynamic adjustment.
☆ 3View skill
GitHub
task-router
Use when analyzing, researching, investigating, exploring, auditing code, reviewing architecture, planning implementation, or when prompt contains Russian words like проанализировать, исследовать, изучить, сост...
☆ 3View skill
GitHub
research-and-analysis
Use when analyzing code structure, researching codebase, investigating architecture, exploring dependencies, creating reports, auditing code quality, or when asked to проанализировать, исследовать, изучить, сос...
☆ 3View skill
GitHub
template-assistant
Generate intelligent content for PARA Obsidian vault templates. Use when asked to create new notes (project, area, resource, task, capture, daily, weekly-review, booking, checklist, itinerary, trip-research), p...
☆ 3View skill
GitHub
claude-code-docs
Answers questions about Claude Code features, configuration, and usage from local documentation synced from code.claude.com. Use when users ask about hooks, plugins, skills, MCP servers, slash commands, sub-age...
☆ 3View skill
GitHub
daily-review
Journaling partner that helps extract deeper meaning from daily logs. Use when the user wants to review their day, process logs into journal entries, or mentions "daily review".
☆ 3View skill
GitHub
inbox-processing-expert
Expert guidance for building and maintaining the Para Obsidian inbox processing system - a security-hardened automation framework for processing PDFs and attachments with AI-powered metadata extraction. Use whe...
☆ 3View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.