Ai Llm Services skills for AI agents
8 practitioner-grade ai llm services skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 8 skills
- Anthropic Claude API
Anthropic Claude API: messages API, tool use, streaming, vision, system prompts, extended thinking, batches, Node SDK
328 lines - Fireworks AI
Fireworks AI: fast inference, function calling, grammar mode, JSON output, OpenAI-compatible API, fine-tuning
350 lines - Google Gemini API
Google Gemini API: generateContent, multimodal (images/video/audio), function calling, streaming, embeddings, context caching
279 lines - Groq
Groq: ultra-fast inference, OpenAI-compatible API, Llama/Mixtral models, tool use, JSON mode, streaming
326 lines - OpenAI API
OpenAI API: chat completions, function calling/tools, streaming, embeddings, vision, JSON mode, assistants, Node SDK
268 lines - Replicate
Replicate: run open-source models, image generation (Flux/SDXL), predictions API, webhooks, streaming, Node SDK
284 lines - Together AI
Together AI: inference API, open-source LLMs (Llama/Mistral), chat completions, embeddings, fine-tuning, JSON mode
294 lines - Vercel AI SDK
Vercel AI SDK: unified LLM interface, useChat/useCompletion hooks, streaming, tool calling, multi-provider, RSC integration
351 lines