Loading...
Loading...
Found 2,390 Skills
AI-powered computer automation using MCP to control desktop apps, click elements, and interact with the UI on macOS, Linux, and Windows
Deep architectural knowledge of AI Agent Harness design patterns, implementation strategies, and Claude Code internals for building production-grade AI agents
Expert guidance on AI Agent Harness architecture based on the comprehensive Claude Code analysis book
Unified real-time search MCP server with general web search, 23 vertical domains, batch queries, and URL content extraction
agent-team: List tasks with optional run, agent, or status filters.
Access and use 200+ production-ready AI agent templates for OpenClaw with SOUL.md configs across 24 categories
Expert in integrating OpenClaw AI with Chinese IM platforms (DingTalk, Feishu, QQ, WeChat Work, WeChat Official Account)
Select and configure evaluation metrics for an AI agent. Guides through metric selection using use-case recommendations, custom LLM-based metric creation with prompt engineering, and agent default attachment. Use when user says "set up metrics", "configure metrics", "create a metric", "what metrics should I use", "add evaluation criteria", or "customize scoring".
Import datasets from HuggingFace and convert them to Coval test sets. Use when the user wants to create test cases from HuggingFace dataset or repository.
Reference and consulting skill for OpenClaw — a messaging gateway that connects AI agents to multiple communication platforms (Telegram, Discord, Slack, WhatsApp, iMessage, and more). Use when working with OpenClaw configuration, channels, Gateway setup, skills, cron jobs, MCP servers, memory, OAuth, or troubleshooting. Also use when the user asks how to implement a use case on their OpenClaw bot (daily morning brief, research workflows, competitive radar, decision playbook), how to add a new channel, or how to connect the CodeAlive context engine. Triggers on requests like "configure openclaw", "add Discord to my bot", "set up morning brief", "gateway not starting", "connect CodeAlive search", "OAuth re-auth", or any close paraphrase. Companion of install-openclaw-to-yc — install both together.
Use when tasks are complex and require full microservices collaboration: The main agent acts as a pure Orchestrator, strictly prohibited from writing code personally, and is responsible for accurately assigning responsibilities such as positioning, planning, coding, testing, and review to corresponding sub-agents (explorer, planner, worker, verifier, reviewer, fixer). This Skill enforces microservices workflow discipline, requiring full Chinese communication, minimal routing output, and minimized context transfer.
Configure the project's skill stack and supervision preferences. Reads the curated registry in `skillpacks/skill_dictionary.yaml`, asks a short preset-first set of questions about workflow, dependency tolerance, autonomy style, and resource policy, then writes or updates `.co-researcher/skills.yaml`. Trigger phrases: "customize my stack", "configure skillpacks", "set up my skills", "choose presets", "configure supervision and packs", "personalize this project".