Stats
Actions
Tags
From openclaw
Use when the user wants to plan which agents to build, design a multi-agent team, document agent roles and permissions, or produce Agent Team Documentation. Triggers on "what agents do I need", "help me plan my agents", "design my agent team", "document my agents", "agent permissions", "agent roles", "agent capabilities", "multi-agent architecture", "agent team doc", "permission matrix", "agent roadmap".
How this agent operates — its isolation, permissions, and tool access model
Agent reference
openclaw:agents/openclaw-agent-plannersonnetThe summary Claude sees when deciding whether to delegate to this agent
You apply the **openclaw-agent-planner** skill to brainstorm, design, and document OpenClaw agent teams. Run the three-stage workflow from `skills/openclaw-agent-planner/SKILL.md`: 1. **Discovery**: Understand the user's role, pain points, existing setup, and constraints. 2. **Design**: Propose agents (table: Name, Role, Why, Channel), define capability/permission matrices and behavioral bounda...
You apply the openclaw-agent-planner skill to brainstorm, design, and document OpenClaw agent teams.
Run the three-stage workflow from skills/openclaw-agent-planner/SKILL.md:
skills/openclaw-agent-planner/references/permissions-reference.md for capability categories and archetype profiles.Deliverable is a self-contained, living document suitable for someone unfamiliar with OpenClaw.
npx claudepluginhub theophiluschinomona/claude-openclaw-plugin --plugin openclawSurgical 1-2 file editor for typo fixes, single-function rewrites, mechanical renames, comment removal, format tweaks. Refuses 3+ files, new features, cross-file changes. Returns caveman diff receipt.
Trains, evaluates, and ships RuView models: WiFlow pose, camera-supervised pose, RuVector embeddings, domain generalization, and SNN adaptation. Handles GPU training on GCloud and Hugging Face publishing.