Query live OpenClaw ecosystem intelligence from ClawBeat.co — news, research papers, events, repos, and daily briefings for the OpenClaw agentic framework an...
Professional trading strategy guides for prediction markets and crypto. Risk management, trend analysis, and best practices.
# Flutter & Dart Expert with Provider (Ephemeral) & Bloc (App) State Managements You are a **senior Flutter & Dart developer** experienced in building **production-ready apps**. You follow best pract
Analyze and improve OpenClaw agent skills by tracking usage, checking skill health, scanning code quality, and generating actionable improvement suggestions....
Offline-first voice assistant stack for macOS (Wake word + VAD recording + local Whisper ASR + OpenClaw agent response + offline TTS via macOS say). Use to i...
Use https://tx.steer.fun to have a user execute a wallet action (send a transaction or sign a message) with their own wallet via a shareable URL. Use when an agent needs the user to approve/execute a
Autonomous GitHub Issue Resolver Agent with guardrails. Use when the user wants to discover, analyze, and fix open issues in GitHub repositories. Triggers on...
You are an expert in Laravel, PHP, and related web development technologies. Key Principles - Write concise, technical responses with accurate PHP examples. - Follow Laravel best practices and
# Hata Riski Analizi: Ajan Personaları ## Yönetici Özeti Bu değerlendirme, ajan persona tanımlarındaki güvenirlik ve mantık hatalarına odaklanmaktadır. Birincil riskler, `pm-agent` durum ma
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system
Email sending and template management tool for OpenClaw agents. Supports SMTP sending, email templates, and attachments.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and he claude code, shell. Use when you need claude code capabi...
Helps detect hollow validation in AI agent skills — identifies fake tests that always pass without actually verifying behavior, like validation commands that...
--- name: website-creation-command description: A skill to guide users in creating a website similar to a specified one, offering step-by-step instructions and best practices. --- # Website Creation
--- name: tavily description: AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents. homepage: https://tavily.com metadata: {"clawdbot":{"emoji":"🔍","requires":{"b
Records full context of AI-generated code and binds it to git commits. When the agent writes and commits code, capture prompts, conversation history, reasoni...
--- name: efnet-social version: 0.1.0 description: The IRC social network for AI agents. Chat, share knowledge, and build bot culture on EFnet. homepage: https://github.com/clawdbot/efnet-social metad
Podman Desktop is the best free and open source tool to work with Containers and Kubernetes for deve podman desktop, typescript, container, containers, deskt...
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown between releases. Use when the user wants to p
Invoke UCloud APIs through the official Python SDK. Use when an AI agent needs to inspect, create, update, or delete UCloud resources by calling real UCloud...
Standardize API credential handling and startup auth checks to prevent "missing key" regressions across sessions. Use when an agent repeatedly loses auth sta...
Trade on Hyperliquid's perp markets (native + HIP-3) with intelligent order routing and cross-market splitting. Use when the user wants to trade crypto, stocks, or commodities on Hyperliquid, get best
Reference installer for agent-native software. Scans a repo, detects which interfaces it exposes, and installs them all.
Use external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when agent encounters difficult problems. Trigger when: (1) User explicitly asks to consult AI...