Autonomous engine that systematically evaluates and ranks agent skills across models using rubric grading, error taxonomy, and improvement feedback loops.
Setup multi-agent sandbox infrastructure with Docker, Discord, SSH, and Tailscale. Use when: (1) creating a sandboxed agent for cross-gateway collaboration,...
Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a sub
Multi-agent collaboration framework for OpenClaw. Three modes: Dispatch (one-shot tasks via spawn), Collaborate (multi-turn cross-department via persistent s...
Create and manage multi-agent teams in OpenClaw with shared workspace, budget governance, and mesh networking. Use when: (1) adding a new agent to an existin...
Real-time visual observability for Claude Code multi-agent workflows. Automatic reporting via hooks — zero agent involvement.
Cost-optimizing model router for OpenClaw. Automatically routes each request to the cheapest capable Claude model (Haiku/Sonnet/Opus) using weighted scoring....
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative
OpenClaw documentation expert with config references, errata tracking, search scripts, and decision tree navigation
Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks...
Execute multiple token swaps in sequence. Use when user wants to rebalance, swap into multiple tokens, or execute a multi-step trading plan. Each swap goes through full safety validation independently
Your personal board of AI advisors — the only skill that uses truly different AI models (not one model role-playing). Get better answers to hard questions by...
Zero-token real-time Discord monitoring dashboard for OpenClaw. Displays system health, cron jobs, sessions, and performance analytics via persistent Discord...
Use this skill any time the user wants to build a website or landing page. This includes: product pages, portfolio sites, event pages, coming soon pages, pri...
通过 HTTP API 远程操作 OpenCode 服务器。用于管理远程 OpenCode 实例的会话、监控状态和执行任务。 核心功能： 1. 管理多个"主session"（每个有独立的四词短
Write clear, concise prose for humans — documentation, READMEs, API docs, commit messages, error messages, UI text, reports, and explanations. Combines Strunk's rules for clearer prose with technica
Bridge tokens from one chain to another without swapping. Simplified cross-chain transfer where the output token is the same as the input token. Use when the user wants to move tokens between chains.
9 engineering disciplines for AI agents — TDD, debugging, code review, planning, and multi-agent coordination. Build software like it matters.
Design a Uniswap integration architecture. Use when user is building a project that needs to integrate Uniswap and wants recommendations on integration method (Trading API vs SDK vs direct contract),
Build a Uniswap V4 hook. Use when user wants to create a custom V4 hook contract. Generates Solidity code, Foundry tests, mines CREATE2 address for hook flags, and produces deployment scripts. Handles
Set up an agent wallet for Uniswap operations. Use when user needs to provision a wallet for an autonomous agent. Supports Privy (development), Turnkey (production), and Safe (maximum security). Confi
Use when optimizing existing Claude skills, checking skill quality, auditing skill compliance, or when skills have obvious issues. Triggers on skill optimiza...
Create, edit, and analyze .pptx presentation files, including slide content, layouts, comments, speaker notes, and theme details.
Clawsy is a native macOS menu bar app that gives your OpenClaw agent real-world reach — screenshots, clipboard sync, Quick Send, camera, file access via Find...