Find the best skills for |

Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.

AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations

Searches Google and extracts full page content from every result via trafilatura. Returns clean readable text, not just snippets. Use when the user needs web search, research, current events, news, factual lookups, product comparisons, technical documentation, or any question

Set up a complete OpenClaw personal AI assistant from scratch using Claude Code. Walks through AWS provisioning, OpenClaw installation, Telegram bot creation, API configuration, Google Workspace integration, security hardening, and all power features. Give this to Claude Code

OpenClaw 小白养成手册。从零开始搭建多 Agent AI 助手系统的完整指南，包含免费起步方案（Qwen 零成本）、进阶方案（MiniMax Coding Plan ¥49/月）、旗舰外援（SiliconFlow/NewCLI 按需调用）。涵盖模型策略、Fallback 链设计、额度管理、常见故障排查。适合首次部署 OpenClaw 或想优化模型成本的用户。当用户说\

Comprehensive diagnostic, error-fixing, and skill recommendation tool for OpenClaw

Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.

Bridge between OpenWork UI and OpenCode runtime

This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to \

Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables.\n\nExamples:\n- user: \

Creates universal OpenCode orchestrator folder structure with specialized agent that can manage swarm servers via curl commands

Reference OpenCode docs when implementing skills, plugins, MCPs, or config-driven behavior.

Diagnose and resolve common OpenEvidence API errors.\nUse when encountering error codes, debugging failed requests,\nor implementing error handling for clinical queries.\nTrigger with phrases like \

Execute OpenEvidence clinical query workflow for point-of-care decisions.\nUse when implementing real-time clinical decision support,\nbuilding EHR-integrated evidence lookups, or point-of-care queries.\nTrigger with phrases like \

Create a minimal working OpenEvidence clinical query example.\nUse when starting a new OpenEvidence integration, testing your setup,\nor learning basic clinical query patterns.\nTrigger with phrases like \

Install and configure OpenEvidence API authentication.\nUse when setting up a new OpenEvidence integration, configuring API credentials,\nor initializing OpenEvidence in your healthcare application.\nTrigger with phrases like \

Configure OpenEvidence across development, staging, and production environments.\nUse when setting up multiple environments, managing environment-specific configurations,\nor implementing environment promotion strategies for clinical AI applications.\nTrigger with phrases like \

Apply OpenEvidence security best practices for HIPAA compliance and PHI protection.\nUse when securing API keys, implementing PHI handling,\nor auditing OpenEvidence security configuration.\nTrigger with phrases like \

Control Philips Hue lights/scenes via the OpenHue CLI.

Fetch SEC Form 4 insider trading data (Directors, CEOs, Officers) from OpenInsider. Use this to track corporate insider buying/selling signals.

Enable AI agents to make micropayments via x402 protocol. Use when purchasing browser sessions on Browserbase, scraping with Firecrawl, or any x402-compatible API. Handles wallet creation, funding, and automatic payment flows.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

OpenRouter API - Unified access to 400+ AI models through one API

Implement audit logging for OpenRouter compliance. Use when meeting regulatory requirements or security audits. Trigger with phrases like 'openrouter audit', 'openrouter compliance log', 'openrouter security log', 'audit trail'.

Implement response caching for OpenRouter efficiency. Use when optimizing costs or reducing latency for repeated queries. Trigger with phrases like 'openrouter cache', 'cache llm responses', 'openrouter redis', 'semantic caching'.

Execute diagnose and fix common OpenRouter API errors. Use when troubleshooting failed requests. Trigger with phrases like 'openrouter error', 'openrouter not working', 'openrouter 401', 'openrouter 429', 'fix openrouter'.

Execute conduct security and compliance review of OpenRouter integration. Use when preparing for audits or security assessments. Trigger with phrases like 'openrouter security review', 'openrouter compliance', 'openrouter audit', 'security assessment'.

Execute set up comprehensive logging and debugging for OpenRouter. Use when investigating issues or monitoring requests. Trigger with phrases like 'openrouter debug', 'openrouter logging', 'openrouter trace', 'monitor openrouter'.

Configure model fallback chains for high availability. Use when building fault-tolerant LLM systems. Trigger with phrases like 'openrouter fallback', 'openrouter backup model', 'openrouter redundancy', 'model failover'.

Implement function/tool calling with OpenRouter models. Use when building agents or structured outputs. Trigger with phrases like 'openrouter functions', 'openrouter tools', 'openrouter agent', 'function calling'.

Create your first OpenRouter API request with a simple example. Use when learning OpenRouter or testing your setup. Trigger with phrases like 'openrouter hello world', 'openrouter first request', 'openrouter quickstart', 'test openrouter'.

Implement advanced model routing with A/B testing. Use when optimizing model selection or running experiments. Trigger with phrases like 'openrouter a/b test', 'model experiment', 'openrouter routing', 'model comparison'.

Execute work with multiple providers through OpenRouter. Use when comparing providers or building provider-agnostic systems. Trigger with phrases like 'openrouter providers', 'openrouter multi-model', 'compare models', 'provider selection'.

Configure OpenRouter as an OpenAI API drop-in replacement. Use when migrating from OpenAI or using OpenAI-compatible libraries. Trigger with phrases like 'openrouter openai', 'openrouter drop-in', 'openrouter compatibility', 'migrate to openrouter'.

Optimize OpenRouter performance and latency. Use when reducing response times or improving throughput. Trigger with phrases like 'openrouter performance', 'openrouter latency', 'speed up openrouter', 'openrouter optimization'.

Execute understand OpenRouter pricing and cost estimation. Use when budgeting or optimizing costs. Trigger with phrases like 'openrouter pricing', 'openrouter costs', 'openrouter budget', 'openrouter token pricing'.

Execute pre-launch production readiness checklist for OpenRouter. Use when preparing to deploy to production. Trigger with phrases like 'openrouter production', 'openrouter go-live', 'openrouter launch checklist', 'deploy openrouter'.

Implement intelligent model routing based on request characteristics. Use when optimizing for cost, speed, or quality per request. Trigger with phrases like 'openrouter routing', 'model selection', 'smart routing', 'dynamic model'.

Implement streaming responses with OpenRouter. Use when building real-time chat interfaces or reducing time-to-first-token. Trigger with phrases like 'openrouter streaming', 'openrouter sse', 'stream response', 'real-time openrouter'.

Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).

Create and render OpenSCAD 3D models. Generate preview images from multiple angles, extract customizable parameters, validate syntax, and export STL files for 3D printing platforms like MakerWorld.

OpenSpec 中文版规范助手 - 规范驱动的 AI 编程开发，帮助初始化、创建提案、编写规格、校验格式并归档变更。触发条件： 当用户提及 openspec、规范文档、需求管理、变更提案、spec-driven development 等关键词时主动调用。

实现 OpenSpec 变更中的任务。当用户想要开始实现、继续实现或处理任务时使用。

归档实验性工作流中已完成的变更。当用户想要在实现完成后最终确定并归档变更时使用。

一次归档多个已完成的变更。用于归档多个并行变更。

通过创建下一个产出物继续处理 OpenSpec 变更。当用户想要推进其变更、创建下一个产出物或继续其工作流程时使用。

进入探索模式 - 一个用于探索想法、调查问题和澄清需求的思考伙伴。当用户想要在进行更改之前或期间深入思考某事时使用。

快速创建实现所需的所有产出物。当用户想要快速创建实现所需的所有产出物，而不是逐个创建时使用。