Use when the user wants to set up multiple agents, configure agent routing, understand OpenClaw bindings, add another agent, create separate workspaces, route messages to different agents, or configure per-agent sandboxing and tool policies.
Use when the user wants to share a gateway with multiple people, set up multi-user access, configure session isolation, manage user pairing, add a user to the gateway, control workspace access, or understand OpenClaw's trust model for shared deployments.
Use when the user wants to pair a device, manage companion nodes, set up remote execution, configure exec routing, control browser via node, set up headless node, connect iOS/Android/macOS devices, manage exec approvals, or run commands on remote nodes in OpenClaw.
Use when the user wants to set up an outreach agent, configure cold email prospecting, build an outreach pipeline, scaffold a BD agent workspace, understand outreach copy frameworks, configure human voice email standards, set up autonomous email response handling, or implement prompt injection protection for email…
Research, design, and build complete persona-driven OpenClaw agent workspaces from scratch — including live web research on world-class domain experts, persona mapping, soul architecture design, and full 5-file workspace generation (SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, GOALS.md). Use this skill whenever the…
Use when the user wants to configure Docker sandbox, set up sandboxed execution, configure container isolation, manage bind mounts, set up sandbox browser, debug sandbox issues, build custom sandbox images, or configure network isolation in OpenClaw.
Use when the user wants to run a security audit, harden OpenClaw, manage secrets, rotate credentials, handle a security incident, configure gateway authentication, set up Tailscale, configure reverse proxy, review file permissions, or understand OpenClaw's security model.
Use when the user wants to manage sessions, configure session resets, set up compaction, link identities across channels, configure thread bindings, understand DM scope, view session history, spawn sub-sessions, or configure session isolation in OpenClaw.
Use when the user wants to install OpenClaw, set up OpenClaw, onboard OpenClaw, get started with OpenClaw, run the OpenClaw installer, configure the OpenClaw daemon, or deploy OpenClaw on macOS, Linux, or WSL2.
Set up a multi-agent tender management workspace on OpenClaw for a construction or engineering company. Creates the full workspace structure with orchestrator agent, discovery, analysis, drafting, and compliance subagents, pre-populated with company knowledge. Use when the user says "set up tender workspace", "create…
Use when OpenClaw is not working, the gateway is not responding, the user wants to run openclaw doctor, debug OpenClaw, view openclaw logs, a channel is not responding, messages are not being delivered, the dashboard shows errors, or cron/heartbeat jobs are failing.
Comprehensive scored audit of an existing OpenClaw agent workspace. Evaluates SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, openclaw.json, and daily logs across quality dimensions with a prioritized improvement plan. Use when the user says "audit my workspace", "review my agent", "check my agent quality", "score my…
Use when the user wants to understand the OpenClaw workspace layout, inspect /.openclaw/ structure, audit agent workspaces, check workspace conventions, understand file-based orchestration, view agent directory organization, troubleshoot workspace paths, or set up a per-agent workspace.