LLM API integration

Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASEURL injected automatically and compute that runs next to your data.

neondatabase/agent-skills

Sends chat completions, streams responses, and opens an interactive REPL against any OmniRoute-routed model provider.

diegosouzapw/OmniRoute

Send inference requests through the FastLLM OpenAI-compatible gateway — chat completions, completions, embeddings, rerank, score, responses, moderations, audio speech and transcription, image…

azrtydxb/Fastllm-proxy

Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability.

internet-court/internet-court-skill

Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero.

OnlyTerp/prompt-cache-skills

启动 Blockless 本地开发栈 / bring up the local dev stack. An agent skill from FreakStudioCN/mpy-hardware-extension.

FreakStudioCN/mpy-hardware-extension

Lets MiMoCode answer questions about itself, including its modes, commands, keybindings, providers and config files, and change its own configuration without guessing schema fields.

XiaomiMiMo/MiMo-Code

Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence.

openai/openai-agents-python

Anthropic Claude API 的 Python 和 TypeScript 使用模式。涵盖 Messages API、流式处理、工具使用、视觉功能、扩展思维、批量处理、提示缓存和 Claude Agent SDK。适用于使用 Claude API 或 Anthropic SDK 构建应用程序的场景。

loulanyue/awesome-claude-notes

LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存. An agent skill from affaan-m/ECC.

affaan-m/ECC

Adds an MCP server to NanoClaw so its container agent can list and prompt local models served by the Atomic Chat desktop app.

nanocoai/nanoclaw

Installs Codex as an agent provider for NanoClaw groups, with streaming, MCP tools, server-side history and vault-only credentials, next to or instead of Claude.

nanocoai/nanoclaw

Adds an MCP server so the NanoClaw container agent can send prompts to local Ollama models, with optional tools to manage the model library.

nanocoai/nanoclaw

Installs OpenCode as an optional NanoClaw agent runtime, reaching OpenRouter, OpenAI, Google, DeepSeek and others through OpenCode's own configuration.

nanocoai/nanoclaw

Microsoft 365 Agents SDK for Python. An agent skill from microsoft/skills.

microsoft/skills

Build agentic applications with GitHub Copilot SDK. An agent skill from github/awesome-copilot.

github/awesome-copilot

Claude Code 設定 Gemini 免費 API。說「設定 Gemini」「Gemini API」時載入. An agent skill from mathruffian-dot/claude-code-lazy-packs.

mathruffian-dot/claude-code-lazy-packs

実 Claude API を叩く総合テスト（全カテゴリ）を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。

receptron/mulmoclaude

根据用户描述的故事内容，润色故事线并拆分为分镜脚本，批量生成风格一致的故事板插图。提供8种视觉风格选择，基于故事类型推荐最佳风格。调用Gemini API生成图片，保存到Obsidian图片目录。触发词："分镜故事"、"故事板"、"做个分镜"、"创建故事板"、"storyboard"、"画个故事"。

SpaceZephyr/design-buddy

Azure AI Agents Persistent SDK for .NET. An agent skill from microsoft/skills.

microsoft/skills

Azure OpenAI SDK for .NET. An agent skill from microsoft/skills.

microsoft/skills

Microsoft 365 Agents SDK for TypeScript/Node.js. An agent skill from microsoft/skills.

microsoft/skills

Specialized integration evaluator for the Evaluate-Loop. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

Ibrahim-3d/orchestrator-supaconductor

実 Claude API + Docker サンドボックスを叩く docker カテゴリの総合テストを実行する。DISABLESANDBOX を unset した状態で yarn dev が起動済みであることが前提（サンドボックス off だと全 test が test.skip で抜ける）。

receptron/mulmoclaude

A skill your agent uses when integrating Google Gemini API into projects.

sickn33/agentic-awesome-skills

A skill your agent uses when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform.

google/skills

Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion analysis…

mcncarl/yichen-skills

Help with Claude/LLM API usage, models, and integration patterns.

terrense/LilBot-agent

Cloudflare Workers patterns for Worker runtime APIs, Durable Objects, KV, R2, D1, Queues, WebSockets, streaming responses, bindings, wrangler configuration, and deployment limits.

EpicenterHQ/epicenter

One-shot chat completion against DeepSeek's deepseek-chat model via the OpenAI-compatible /v1/chat/completions endpoint.

ruvnet/ruflo

Visual quality assurance: analyze game screenshots for defects, compare against reference, check motion in frame sequences.

RandallLiuXin/GodotMaker

Python resource management with context managers, cleanup patterns, and streaming.

wshobson/agents

Expert guidance for writing Python code using the official Google GenAI SDK (google-genai) for Gemini API and Vertex AI.

cnemri/google-genai-skills

A skill your agent uses when implementing GPT chat, streaming, function calling, embeddings for RAG, images, audio or batch jobs, or troubleshooting 429 rate limits and API or TypeScript errors.

coco-research/coco

When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports.

coreyhaines31/makerskills

Reusable approval-loop pattern for fanning out lead personalization across parallel Claude Code Task sub-agents.

growthenginenowoslawski/coldoutboundskills

通用 AI 生图：文生图 / 图生图 / 图像变体。当用户说 AI 生图、AI 画图、文生图、图生图、生成图片、生成配图、图像生成、AI 出图、AI 作图、换图、改图、图像编辑、给我画一张、生成一张图 时使用。支持 OpenAI 兼容 API 与 apimart 异步 API，用户自备 API key。

ZJU-REAL/Easel

输入文字或图片，通过腾讯混元生3D TokenHub/OpenAI 兼容接口或腾讯云 SDK 生成3D模型。支持文生3D、图生3D、多视图生3D、PBR、白模、草图生3D、智能拓扑生3D；当用户要求生成或查询混元3D模型时使用。

kangarooking/kangarooking-skills

A skill your agent uses when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka).

NVIDIA/skills

Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.

Prism-Shadow/penguin-harness

Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies.

sickn33/agentic-awesome-skills

Generates a Gemini LiveAPI client service class in the user's chosen programming language.

google/skills

LLM APIの使用量のコスト最適化パターン — タスクの複雑さによるモデルルーティング、予算追跡、リトライロジック、プロンプトキャッシング。

affaan-m/ECC

TypeSafe AI（typesafe.ai）官方文档离线 Wiki，覆盖 Jev System One 模型、Choice/Score/Noul 问题原语、state 结构与置信度、架构 Patterns、Python/JavaScript SDK、HTTP API 参考与 Cookbooks 示例；用于查询 TypeSafe API/SDK 的接入、用法与示例。不用于其他 LLM 厂商…

chujianyun/skills

生图 / 生成图片 / 画图 — 用 OpenAI gpt-image-2 生成图像。支持文生图、参考图生图 (img2img)、蒙版修补 (inpainting)。当用户要求用 GPT 画图、OpenAI 生图、gpt-image-2、文+图生图、参考图片生成、img2img、inpainting 时必加载此技能。Auth 自动继承 OPENAIAPIKEY / Codex OAuth…

ninehills/skills

AI chat UI component toolkit built on shadcn/ui. An agent skill from diodeme/Gold-Band.

diodeme/Gold-Band

Claude Code documentation expert. An agent skill from mikeOnBreeze/cc-crossbeam.

mikeOnBreeze/cc-crossbeam

Integrates SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications.

secondsky/sap-skills