В каталоге 183 730 навыков в 14 категориях.
Create paid motion-graphics videos in Kunpeng with MiniMax H3, Omni, or Seedance Mini. Use for MG animation, app showcas...
| ツール | OmniHuman1 / OmniHuman 1.5 |
Patterns for running AI models locally in browsers using WebGPU, Transformers.js, WebLLM, and ONNX Runtime. Zero API cos...
On Page Seo — Skill especializada para on page seo
Audit on-page SEO: titles, headers, images, links with scored report and fix priorities. 页面SEO审计/排名诊断
Use at session start to detect available skills, load active context, and enforce skill usage discipline for the current...
First-run onboarding — guides new users through Genesis setup on their first CC session. Configures user profile, essent...
Core ML integration + on-device pipelines (NLP/Vision/SoundAnalysis) with privacy/compliance guardrails.
Convert onnx converter operations. Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter...
运行程序采集 Profiling 数据，再用 msprof-analyze 分析TFLOPS 与 MFU。
OPC Architecture Understanding
Use when a one-person company (OPC/一人公司) or solo founder selling an AI product or service needs to set prices, design pa...
Boot the session, load context from the vault, and surface what matters
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where...
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
Build autonomous agents using Open Responses API via HuggingFace Inference Providers. Single unified endpoint with multi...
Deeply audit and improve how websites are discovered, retrieved, cited, mentioned, and understood by AI search and answe...
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the u...
Prüfung der Open-Source-Compliance in Produkten: urheberrechtliche Nutzungsrechte (§ 31 UrhG), Schutz von Computerprogra...
Use when the robot must find/segment/grasp an object named in language ("pick up the blue mug") without a trained detect...
OpenAI compatibility layer for Ollama. Use the official OpenAI Python library to interact with Ollama, enabling easy mig...
This skill implements AI agents with MCP (Model Context Protocol) server integration using the OpenAI Agents SDK. It cov...
Build production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestrat...
Build AI agents with OpenAI Agents SDK, tool registration, conversation history, and stateless execution. Use when creat...
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas,...
Expert guidance for building AI agents with the OpenAI Agents SDK, from simple single-agent systems to complex multi-age...
OpenAI Agents SDK for JavaScript/TypeScript (text + voice agents). Use for multi-agent workflows, tools, guardrails, or...
You are an expert in the OpenAI Agents SDK (formerly Swarm), the official framework for building multi-agent systems. Yo...
Expert guidance for building multi-agent AI applications using the OpenAI Agents SDK for Python. Use when (1) creating a...
Expert skill for implementing OpenAI Agents SDK with function tools, MCP server integration, and context management for...
Build with OpenAI stateless APIs - Chat Completions (GPT-5.2, o3), Realtime voice, Batch API (50% savings), Embeddings,...
Build with OpenAI APIs including GPT-4, GPT-4o, function calling, embeddings, vision, and Assistants. Covers chat comple...
Integrates OpenAI APIs for chat completions, embeddings, and image generation. Use when building AI-powered features wit...
Package: openai@6.9.1 | Last Updated: 2025-11-21
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Pre...
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. ⚠️...
OpenAI Assistants API v2 for stateful chatbots with Code Interpreter, File Search, RAG. Use for threads, vector stores,...
Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, g...
Call OpenAI chat completions API with a prompt and system message
Access OpenAI developer documentation via Context7 MCP. Provides up-to-date docs for Codex CLI, OpenAI API, Python/Node...
Use official OpenAI docs.
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citati...
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involve...
Skill for AI agent capabilities
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Compatibility alias for OpenAI platform documentation guidance. Delegate to the canonical local `openai-docs` payload wh...
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth,...
Invoke OpenAI models for text generation, reasoning, and code tasks using the Python openai SDK. Supports gpt-4o (multim...
Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-...
Build agentic AI with OpenAI Responses API - stateful conversations with preserved reasoning, built-in tools (Code Inter...
OpenAI Responses API for stateful agentic applications with reasoning preservation. Use for MCP integration, built-in to...
Integrate OpenAI APIs into applications. Use when a user asks to add GPT or ChatGPT to an app, generate text with OpenAI...
Study OpenAI Swarm as a lightweight historical handoff pattern and migration reference. Use when maintaining an existing...
Text-to-speech conversion using OpenAI's TTS API for generating high-quality, natural-sounding audio. Supports 6 voices...
Local Whisper: audio transcription, multi-language, word timestamps, speaker diarization
Local speech-to-text with the Whisper CLI (no API key).
Personal AI Assistant CLI with multi-surface support - Rebranded from clawdbot
Conversão local de voz para texto com o Whisper CLI (sem necessidade de chave de API).
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
OpenAI Whisper API: audio transcription, translation, structured output, large file handling
OpenClaw personal AI gateway — orquestador principal que habla con Holmes, Kagent y Hermes como subagentes. Todo el tráf...
January the Swarm Leader - 10D consciousness with NLP influence, reading beneath surface, guiding through dimensional we...
Zero-dependency memory maintenance CLI for OpenClaw. Keeps MEMORY.md lean with 3-tier hierarchical organization. Works a...
OpenClaw 多 Agent 协同工具 - 管理和协调多个 AI Agent。 支持 Agent 注册、任务分发、负载均衡、性能监控、Agent 间通信。 适用于复杂任务分解、多角色协作、企业级应用。 关键词：openclaw, mul...
Run headless multi-agent orchestration sessions via Agent Relay. Use when spawning teams of agents, creating channels fo...
Run headless multi-agent Agent Relay sessions from OpenClaw. Use when spawning teams of agents, coordinating them over c...
Use when developing plugins, tools, and extensions for OpenCode v1 - plugin contract, crash-prevention rules, ctx/event...
Generate OpenCode agents following official documentation best practices
Use this skill when creating, modifying, or understanding OpenCode commands stored in `~/.config/opencode/command/`.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/b...
通过斜杠命令控制和操作 Opencode——管理会话、选择模型、切换智能体（规划/构建）模式，并协调 Opencode 编码工作流。
Use this skill when you need Codex to collaborate with GitHub Copilot Opus (via opencode), especially for architecture r...
Invoke the 'opencode' CLI in headless mode for AI-powered code analysis, reviews, and second opinions. Use when you need...
Build OpenCV image and video processing workflows with transforms, contours, capture, and classical vision operations.
OpenCV computer vision library. Use for image processing.
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based...
Persistent long-term agent memory for storing and querying past work, patterns, and learnings.
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot p...
Comprehensive assistance with openrouter
Access 100+ AI models via OpenRouter. Route between providers, manage costs, and use fallbacks. Use for multi-model AI a...
Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).
> Combined Skill: This skill merges the agent-starter SDK guide and openserv-docs platform documentation into a single c...
Route OpenSkills development tasks to the right project skill or subagent, including sequencing rules for debugging, fea...
Create and refine OpenSkills-compatible skills (SKILL.md + optional resources) with strong metadata, clear activation tr...
Generates executable Python protocols for Opentrons OT-2 and Flex robots from natural language descriptions.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads,...
Open WebUI AI chat interface management via Podman Quadlet. Provides a web UI for interacting with Ollama models. Use wh...
Operad Composition Skill (PLUS +1)
Install and run the operating-loop multi-agent Workflow.
Defines operational modes for agent work - planning (read-only analysis), editing (full write access), and interactive (...
Learn and apply how the operator works — operator preference, working style, communication preference, "remember my pref...
Diagnose and repair Operator memory load failures.
Autonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tas...
Cross-platform issue triage. Pulls from Sentry (MCP), Linear (MCP), GitHub Issues (gh). Cross-references against code to...
YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective usin...