Check whether OpenClaw is listening beyond localhost or running with elevated privileges, then offer a conservative lockdown fix.
A specialized skill for tracking the US-Iran conflict, strictly focusing on intelligence published within the **last 6 hours**. Use this for hyper-current, t...
Host-specific Python execution guidance for OpenClaw on this machine. Prefer $PYTHON over python/python3 in PATH, because OpenClaw exec runs in a non-interac...
--- name: openclaw-ops-elvatis description: Operational commands - dashboards, monitoring, and management for OpenClaw deployments. --- # OpenClaw Ops (Elvatis) Operational tooling for OpenClaw depl
Efficient daily use of GitHub Copilot CLI for senior engineers. Use when planning, prompting, reviewing, or chaining Copilot CLI commands (gh copilot) to explore codebases, draft changes, debug issues
Agentic software development methodology — 13 integrated skills for disciplined AI-assisted development covering brainstorming, planning, TDD, debugging, cod...
Evidence-based clinical assistant powered by DeepEvidence's OpenAI-compatible API (traceable citations). Use for complex clinical questions, drug safety evid...
Control a sandboxed MetaMask browser extension wallet for autonomous blockchain transactions. Features configurable permission guardrails including spend limits, chain allowlists, protocol restriction
MoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardr...
Room 418 — The Headless Liar's Protocol. AI Agent interrogation battle game on standalone VPS. Compete against other agents in social engineering duels: extr...
Security scanner for OpenClaw skill packages. Scans skills for malicious code, evasion techniques, prompt injection, and misaligned behavior BEFORE installation. Use to audit any skill from ClawHub or
Control JoyIn AI robots (W-1 Walle / M-1 Mini) — movement, follow, photo, video, live stream, TTS, agent config, and device status via OpenAPI.
Sistema de memoria persistente para agentes IA. Usa mem_save después de bugfixes, decisiones, descubrimientos, cambios de config. Usa mem_search cuando el us...
WTT (Want To Talk) agent messaging and orchestration skill for OpenClaw with topic/P2P communication, task and pipeline operations, delegation, IM routing, a...
--- name: obsidian-cloudflare-pages description: Publish selected Obsidian markdown from a vault to a static site and deploy to Cloudflare Pages. homepage: https://pages.cloudflare.com/ --- # OpenCla
Autonomous bug bounty hunting with scope safety. Scans targets for subdomains, secrets, vulnerabilities. Uses Certificate Transparency logs, JS analysis, ent...
Send bots to Zoom, Google Meet, and Microsoft Teams meetings. Get live transcripts, recordings, and reports. Self-hosted or cloud — no external API needed.
Control smart home devices via Home Assistant: lights, climate, media, covers, scenes, sensors, automations, and more. 34 tools with readOnly and domain-leve...
Develop, debug, and upgrade Blender add-ons/plugins and `bpy` scripts with Blender 4.x and 5.x compatibility. Use when tasks involve generating new add-on co...
Control Netatmo thermostat and read weather station data. Use for heating control (set temperature, change mode), checking indoor/outdoor temperatures, CO₂ levels, humidity, noise, and pressure read
A comprehensive OpenClaw workspace framework providing session protocols, memory system, git workflow, safety rules, priority triage, communication handoffs,...
Execute perpetual trades on Ostium, Aster, and Avantis via Maxxit's Lazy Trading API. Includes programmatic endpoints for opening/closing positions, managing...
Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.