--- name: draw-animal version: 0.1.0 description: Generate a text description of an animal picture via Python script activation: patterns: - "draw an animal" - "generate animal picture descr
YouTube 频道订阅+自动摘要+Telegraph 发布工具。用于： 1. 定时监控指定 YouTube 频道的新视频 2. 提取视频字幕（支持中英双语） 3. 生成可读性强的中文专栏
Manage Usenet downloads with SABnzbd. Use when the user asks to "check SABnzbd", "list NZB queue", "add NZB", "pause downloads", "resume downloads", "SABnzbd status", "Usenet queue", "NZB history", or
--- name: asr-claw version: 1.1.1 description: Speech recognition CLI for AI agent automation. Transcribe audio from stdin, files, or URLs. metadata: openclaw: homepage: https://github.com/llm-n
Generate images from text prompts or edit existing images with AI. Powered by Google Gemini via Maliang API. Free $6 credit on first use (~10 images). Suppor...
Generate, edit, and remix images using the Reve AI API. Use when creating images from text prompts, editing existing images with instructions, or combining/remixing multiple reference images. Requires
Analyze bank transactions, categorize spending, track monthly budgets, detect overspending and anomalies. Outputs interactive HTML report.
--- name: cron-guardrails-pack description: Lint cron entries for schedule validity, bad model names, and missing NO_REPLY discipline markers. --- # cron-guardrails-pack Author: billy-ops-agent ##
--- name: cron-guardrails-pack description: Lint cron entries for schedule validity, bad model names, and missing NO_REPLY discipline markers. --- # cron-guardrails-pack Author: Billy (SAPCONET) ##
Post tweets, replies, and quotes to X/Twitter using the official API v2. Use this instead of bird for posting. Uses API credits so only post when explicitly...
Manage environment variables, secrets, and config across agent sessions. Secure credential storage with encryption at rest.
--- name: cross-agent version: 1.0.0 description: "跨机器Agent协作 - 通过SSH连接局域网内其他OpenClaw实例，实现多机任务分发" author: OpenClaw homepage: https://docs.openclaw.a
Generate images using a local SGLang-Diffusion server (FLUX, Stable Diffusion, Qwen-Image, etc.). Use when: user asks to generate, create, draw, or render an...
ClawHub Skill 发布避坑指南。让你的 Skill 发布后能被搜索到，避免安全扫描导致隐藏。适用于需要发布 Skill 到 ClawHub 的开发者。
自动监控 OpenClaw 状态，每60秒检测并自动修复卡死、无响应和内存超限问题，确保服务稳定运行。
Generate and edit images using NVIDIA FLUX models. Use when user asks to generate images, create pictures, edit photos, or modify existing images with AI. Supports text-to-image generation and image e
Transform, format, and process text with patterns for writing, data cleaning, localization, citations, and copywriting.
File format converter. Detect formats, convert between JSON/YAML/XML/CSV/Markdown, minify and prettify code. Commands: detect, json2yaml, yaml2json, csv2md,...
Explain anything — turn ideas into podcasts, explainer videos, or voice narration. Use when the user wants to "make a podcast", "create an explainer video",...
自动在钉钉群中被@时保存群ID和群名，双写至JSON和MEMORY.md实现持久化和跨Session共享。
Manage Expo React Native apps on OpenClaw: create apps, add screens, start web previews on localhost, and check preview status safely within /home/patron/apps.
Interact with Astra's Docker container workspace by executing commands and reading or writing files at /workspace inside the astra-env container.
Set up, OAuth-authenticate, and use the Readwise MCP server (mcp2.readwise.io/mcp) via the mcporter CLI. Use when a user asks to connect/auth Readwise MCP, reset or troubleshoot OAuth login (stale red
OpenClaw 自救套件 - 网关启动包装（端口冲突防护）、看门狗监控、自动重启、配置回滚、安全加固、日志清理、Git版本管理。当用户提到 OpenClaw 网关崩