Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isola...
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot →
Stateless CLI security scanner for OpenClaw skills. The npm package runs fully offline with zero database or auth dependencies. Detects threats across 6 anal...
One-click batch processing for all files: rename, compress images, convert to PDF, auto organize. No software installation needed, runs locally, safe and ad-...
Write and execute Timeplus streaming SQL for real-time analytics. Use this skill when the user wants to create streams, run streaming queries, build material...
Public HTTP client skill exposing compute.* tools by calling a private Compute Gateway over HTTPS. Includes a starter kit to run OpenClaw preconfigured.
Offers a casual interface to list files, run commands, read files, and automate tasks in your OpenClaw workspace.
Generate images, videos, audio, and 3D models via RunningHub API (170+ endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId...
Fast local search for markdown files, notes, and docs using qmd CLI. Use instead of `find` for file discovery. Combines BM25 full-text search, vector semantic search, and LLM reranking—all running l
Build and operate a QuarkPan-based backup + restore workflow for OpenClaw workspaces, including QR login, account UID binding guard, cloud upload, dry-run re...
Lightweight local HTTP file server with plugin support. Serves static files from a webroot, mounts plugin directories at URL prefixes via config, and runs in...
Check whether OpenClaw is listening beyond localhost or running with elevated privileges, then offer a conservative lockdown fix.
Runs a backend-backed live safety check for instructions that may trigger tool execution, external calls, file edits, permission changes, destructive or irre...
Use Teleport tsh CLI with a Machine ID (tbot) identity file to SSH into Teleport-managed hosts or run remote commands through Teleport access controls. Trigg...
Access Poe.com AI models by running bash commands. Use when user mentions Poe, wants to use Poe models, or generate media via Poe. IMPORTANT: This is a bash-...
Run a structured 2-agent debate loop between ChatGPT (OpenAI API) and the user's own thoughts retrieved from Supabase Open Brain via MCP, iterating up to 3 r...
Replicate ML platform — run AI models, manage predictions, browse collections, search models. ML inference CLI.
Self-driven AI worker. Reads goals, generates tasks, executes, and logs progress. Keywords: create goal, new goal, set goal, run goals, 创建目标, 新目标, 设定目标, 执行目标.
Configure OpenClaw multi-agent routing for Feishu multi-account setups. Use when users need two or more Feishu bots (different appId/appSecret) to run on iso...
WHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves long-running agent context exhaustion problem. WHEN: (1) User requests
Stabilize no-approval node execution in OpenClaw. Use when approval timeout, noisy failure events, or node run drift appears.
Run or supervise a one-pass Codex implementation with preflight gates, stepwise plan execution, and strict QA defect loop. Use when executing approved presal...
Execute multi-step workflows via Orchestrate. Use when running complex workflows, parallel tasks, multi-model orchestration, or automating multi-step processes.
--- name: moa-debate description: Run an Oxford Union–style multi-agent debate on any motion using Mixture of Agents architecture --- # Oxford Union Multi-Agent Debate When the user wants to **deb