Guide users through building a custom multi-agent team on OpenClaw — from role design to workspace files, routing bindings, channel configuration, and collab...
Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prometheus planning, background
Build high-performing, secure OpenClaw agents and multi-agent teams end-to-end. Generates required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md,...
Engineering literature survey following Academic Research methodology. Two modes (initial survey / daily reading), two-phase workflow with user checkpoints,...
调用 Claude Code CLI 进行代码开发、代码审查、bug 修复和自动化任务。当用户需要：(1) 代码审查和审查 PR，(2) 重构和性能优化，(3) 编写测试，(4) 自动修
Clean up stale OpenClaw session files. Keep the current main session and all group chat sessions; move everything else to a backup directory. Use when perfor...
Generate images via ComfyUI API (localhost:8188) using Flux2 workflow. Supports structured JSON prompts sent directly as positive prompt parameter, seed/steps customization. Async watcher via sub-agen
Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub
The God-Tier Agent Evolution Engine. 6 top skills analyzed, dissected, and rebuilt from scratch. Zero external dependencies. Battle-tested in production. Mak...
Comprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user a...
Enforces task completion: turns your goal into pass/fail criteria, runs a worker, judges the output, feeds back what's missing, and loops until every criteri...
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron v...
Todo list and task management for AI agents. Add, track, and complete tasks with autonomy levels — agents propose work, humans approve. Works in heartbeats, cron, and conversations. Persistent SQLit
System safety and control-plane skill that prevents agent deadlocks and freezes. Provides non-LLM control commands to inspect task state, flush message queues, cancel long-running work, and recover sa
Programmatically control Claude Code via MCP protocol to execute commands, manage sessions, search and edit code, and coordinate agent teams for development...
Control a GeekMagic holocube display as an AI emote system. Generate holographic sprite kits with Gemini, upload to device, and swap expressions based on agent state (idle, working, error, etc.). Use
并行回复助手 - 让 AI 回复不再等待。支持任务分类、时间预估、并行执行、进度汇报。 简单任务直接回复，中等任务执行 + 汇报，复杂任务启动子 agent
--- name: tg-voice-whisper description: Auto-transcribe Telegram voice messages (.ogg Opus) to text using local OpenAI Whisper (tiny model). Reply with transcription + auto-delete file for privacy. No
Write powerful SOUL.md files for AI agents. Use when creating, revising, or improving SOUL.md (the personality document for AI agents). Based on Anthropic's...
防遗忘防卡顿的context管理协议。自动监控水位、分区管理、压缩前存档、压缩后恢复。适用于所有OpenClaw agent和sub-agent。在heartbeat或session启动时触发。
Agent resilience patterns for surviving context loss, capturing critical details, and self-improvement. Use when: starting complex/long sessions, asked to 'r...