openclaw

Build or optimize OpenClaw agent workspace files (SOUL, IDENTITY, AGENTS, MEMORY, GOALS) via guided interview or workspace scan

Audit agent autonomy readiness — score how well agents operate independently and suggest remediations

Backup OpenClaw configuration, credentials, and auth profiles

Manage OpenClaw messaging channels

View or edit OpenClaw configuration

Use when the user wants to create or optimize OpenClaw agent workspace files (SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, GOALS.md), set up agent personality, configure agent identity, scan or audit an existing workspace, or refine persona and goals. Triggers on "set up my agent", "configure my agent", "build SOUL", "optimize workspace", "agent persona", "agent identity", "GOALS.md", "scan my workspace", "audit agent files", "make my agent", "agent workspace files", "SOUL.md", "IDENTITY.md", "MEMORY.md".

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".

Use when the user wants to fetch, sync, update, or refresh OpenClaw documentation from upstream sources. Triggers on "fetch docs", "sync docs", "update documentation", "docs stale", "pull latest docs", "refresh openclaw docs", "crawl docs", "missing documentation", "download openclaw docs", "update crawled docs", "docs out of date", "get latest docs".

Use when the user asks about OpenClaw gateway management, channel setup, configuration, troubleshooting, node pairing, device management, AI assistant deployment, agent team design, agent operations, multi-user access, workspace sharing, automation, security, sandboxing, sessions, models, or nodes. Triggers on "check openclaw", "configure telegram", "gateway not responding", "set up whatsapp", "add agent", "restart gateway", "pair a device", "openclaw status", "openclaw not working", "connect discord", "openclaw doctor", "view openclaw logs", "memory setup", "shared memory", "bootstrap files", "MEMORY.md", "daily logs", "SCRIBE", "memory compression", "agent team", "soul.md", "agent hierarchy", "team structure", "agent best practices", "cron schedule", "multi-user", "workspace access", "user pairing", "session isolation", "share gateway", "add user", "cron job", "webhook", "heartbeat", "hook", "schedule task", "session reset", "compaction", "thread binding", "identity link", "dm scope", "change model", "model provider", "api key", "failover", "auth profile", "security audit", "harden openclaw", "rotate credentials", "incident response", "secret management", "docker sandbox", "sandbox mode", "container isolation", "bind mount", "sandbox browser", "node command", "remote execution", "exec routing", "pair device", "headless node", "exec approval", "backup openclaw", "update openclaw", "multi-agent team", "agent collaboration", "commander specialist", "agent operating system", "agent OS", "mention gating team".

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.

Full guided journey to create a complete OpenClaw agent workspace from scratch. Chains discovery, memory design, persona crafting, workspace scaffolding, and quality audit into a single orchestrated flow with checkpoints. Use when the user says "create my agent from scratch", "full agent setup", "build a complete agent", "new openclaw agent", "workspace wizard", "guided agent creation", or "walk me through creating an agent". This is the comprehensive path — for quick single-file edits use openclaw-agent-architect instead.

Create, optimize, and maintain OpenClaw agent workspace files — SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, and GOALS.md. Use this skill whenever the user mentions OpenClaw agent setup, agent personality, agent identity, agent workspace files, SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, GOALS.md, agent persona, "set up my agent", "configure my agent", "make my agent", or wants to scan/optimize/audit an existing OpenClaw workspace. Also trigger when the user wants to create a new agent from scratch, refine an agent's personality, add goals or memory structure, or review workspace files for consistency. This skill conducts targeted interviews, generates production-ready markdown files, and can scan existing workspaces to optimize them.

Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent's behavior, guardrails, autonomy model, heartbeat plan, and skill roster.

Diagnose and fix OpenClaw agent and gateway problems — heartbeats not firing, cron jobs failing, agents not responding, wrong routing, model errors, workspace issues, channel connection failures, and openclaw.json config errors. Use this skill when the user reports: agent not responding, heartbeat stopped, cron job not running, wrong agent getting messages, model errors, gateway won't start, channel disconnected, agent sending to wrong place, memory not writing, session errors, openclaw doctor errors, or any "something isn't working" situation with OpenClaw. This skill reads the openclaw.json config, interprets error patterns, walks through diagnostic steps, identifies the root cause, and produces the exact commands or file changes needed to fix it.

3 hooks across 3 events