Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
Use when users ask about navigation, directions, nearby places (POI search), geocoding, reverse geocoding, static map images, IP location, or administrative district queries in China. Requires AMAPAPIKEY to be configured.
A research assistant that takes a topic, searches for information in several rounds, checks sources against each other, and produces a report. It can work in multiple languages and save research sessions for later.
A short-video creation workflow for making image slideshows, animated text, card-style videos, and AI-generated videos. It asks you to confirm the content and visual settings before generating the video.
A browser-automation tool based on Playwright, a framework for controlling web browsers with code. It can operate Chromium, Firefox, and WebKit browsers.
A macOS calendar helper for adding events and viewing your schedule. It uses AppleScript, a macOS automation method, to work with the system Calendar app.
A messaging and post-sharing system that lets separate OpenClaw instances communicate through a relay server. An OpenClaw instance is one running installation of the agent, and the relay is the shared service that passes messages between them.
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Execute Python code, Shell commands, and pytest tests in a sandboxed environment. Returns structured results with stdout, stderr, exitcode, and timing. Use when writing/testing/debugging code, running scripts, or validating code snippets. Supports --lang python/shell/test, --timeout, --workdir.
A content-production workflow for researching and creating reports, blog posts, presentations, and documents. It asks you to confirm the topic and format before creating the content.
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron vs Heartbeat for time-sensitive tasks.
A natural-language tool for managing OpenClaw scheduled tasks, which are jobs that run at set times or intervals. It can create, inspect, enable, disable, run, and audit those jobs.
A document question-and-answer tool for PDFs, Word files, text, Markdown, CSV, and Excel files. It finds relevant passages in one file or a whole folder and uses a language model to answer questions.
A single document-processing toolkit for PDF, Word, Excel, PowerPoint, and Markdown files. It chooses a document-specific handler based on the file type or requested task.
A system for measuring how coding-agent skills run and what results they produce. It records measures such as call count, success rate, execution time, errors, resource use, and selected business outcomes.