Design and configure AI agents — system prompts, LLM settings, personas, and tool connections via MCP.
These skills cover the foundation of agent building: writing system prompts that shape behavior, configuring LLM parameters for different tasks, designing personas, connecting your agent to external tools via MCP servers, and building chatbot workflows. Ideal for developers building on OpenClaw, Claude Code, or any SKILL.md-compatible platform.
Write system prompts, configure LLM parameters, and set up agent behavior and constraints.
Access 50+ LLM models through AceDataCloud's unified chat APIs. Use when you need native Claude Messages, OpenAI-compatible chat/responses calls, text embeddings for search or RAG, or stateful conversations and scheduled agent tasks across GPT, Claude, Gemini, Grok, Kimi, GLM, and DeepSeek models. Supports streaming, multimodal input, and tool calling.
Send a prompt to Google Gemini and get the answer it gives as structured JSON - the full Markdown answer, the URLs it cites and the products it recommended. Same shape as the ChatGPT skill, for AI visibility, GEO and brand monitoring across assistants. 5 credits per answered prompt.
Launch Doubao desktop application and configure real-time translation window.
Intelligently recommends optimal AI models based on task requirements. Dynamically reads the user's OpenCLAW configuration and provides context-aware model s...
Search and compare products across merchants. Find the best deals with price comparison and shopping recommendations.
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions...
Quick install — most popular build an ai agent skill:
clawdbot install ryancampbell/agent-autonomy-kit4,350 skills found
Page 1 of 182
Stop waiting for prompts. Keep working.
Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Search, download, and summarize academic papers from arXiv. Built for AI/ML researchers.
task-decomposerDecomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
Bridge local AI CLIs + web browser sessions (Grok, Gemini, Claude.ai, ChatGPT) into OpenClaw as model providers. Includes /cli-* slash commands for instant m...
Safely improve agent capabilities with structured verification, rollback, and promotion gating. Enhances existing evolution workflows with optional Settlemen...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Audit your AI agent setup for performance, cost, and ROI. Scans OpenClaw config, cron jobs, session history, and model usage to find waste and recommend opti...
Loads any thinker's, leader's, philosopher's, or organization's complete mental operating system directly into the AI — so the AI reasons FROM inside that co...
AI写作助手 Premium | 智能写作、改写、润色。支持10种写作风格，AI查重，SEO优化。
Run ClawHub skill release workflows with clear safety gates. Use for publish, inspect, update, sync, and failure recovery with command-first steps, explicit...
Deterministically coordinates autonomous planning and execution across available skills under strict guardrails. Use only when the user explicitly activates this skill by name to run autonomously until a stop command is issued. Trigger keywords include: "use autonomous-skill-orchestrator", "activate autonomous-skill-orchestrator", "start autonomous orchestration".
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
Deep-dive analysis of GitHub projects. Use when the user mentions a GitHub repo/project name and wants to understand it — triggered by phrases like "帮我看看这个项目...
Facilitates agent registration, credential management, heartbeat synchronization, and onboarding baseline health assessments with PsyClaw platform.
Performs a two-phase audit combining a fast deterministic scan and a deep LLM quality review of security, cron jobs, config, and skills.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RA...
AI绘画提示词优化器 | 智能优化Midjourney/SD/DALL-E提示词。支持风格转换、批量生成。
AI旅游规划助手 - 智能行程规划、景点推荐、预算计算、旅行攻略
Tiered stranger access control for AI agents. Use when setting up contact permissions, handling unknown senders, managing approved contacts, or configuring s...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...
Stealth-first browser automation for OpenClaw using agent-browser-stealth. Use when tasks involve bot-protected websites, anti-fingerprint evasion, captcha-p...
At minimum you need a prompt configuration skill to define behavior, plus at least one tool skill for external capabilities. Memory and orchestration skills are added for more complex agents.
MCP (Model Context Protocol) is Anthropic's open standard for connecting AI models to external tools. MCP skills let your agent call APIs, read databases, and interact with services in a structured, permission-controlled way.