claude-openclaw-plugin

Audit one or more OpenClaw agents, analyse what they require (complexity, tool use, context window, volume, autonomy, sensitivity), and recommend the best-fit OpenRouter models by pricing tier with ready-to-paste openclaw.json config snippets. Use when the user says "what model should I use", "recommend a model for my agent", "audit my agent models", "find a cheaper model", "openrouter model suggestions", "which model fits my agent", or invokes /openclaw-model-advisor.

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.

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.

Brainstorm, design, and document OpenClaw agents and multi-agent teams. Use this skill whenever the user wants to plan what agents to build, figure out what agents they need, design agent capabilities and permissions, plan a multi-agent architecture, decide how agents should work together, or create documentation for their agent team. Also trigger when the user says things like "what agents do I need", "help me plan my agents", "I want to set up multiple agents", "document my agent", "agent permissions", "agent roles", "agent team", or asks about agent capabilities, responsibilities, tool access, or inter-agent communication. This skill produces a comprehensive Agent Team Documentation package (markdown + optional .docx) covering every agent's role, persona, permissions, tools, boundaries, and team interaction rules.

Surgically update existing OpenClaw agent workspace files based on conversational change requests — without rewriting the soul, persona, or hard limits. Use this skill when the user says things like "update the agent", "tell NEXUS about the new client", "HUNTER's ICP has changed", "add this to APEX's memory", "RPS paid their invoice", "change SENTINEL's heartbeat", "update the goals", "the client list changed", "add a new cron job", "remove the stale goal", "SCRIBE needs to know about ISO 14001 scope change", or any request to change, add, remove, or refresh content in an existing agent's workspace files. Also trigger when business state changes (new client, lost client, invoice paid, tender outcome, staff change, new service, pricing update) that should be reflected in agent memory. This skill identifies which files and sections need changing, shows exactly what will change before touching anything, makes surgical edits that preserve the persona soul, and outputs ready-to-apply file patches.

Run the complete IBS OpenClaw client onboarding process — from scoping a new client's agent requirements, through designing their agent architecture, building their workspace files and openclaw.json, to producing a professional handover package. Use this skill when IBS is onboarding a new client onto OpenClaw, productising the agent deployment service, creating a client's first agent setup, or when the user says things like "onboard this client", "set up OpenClaw for a new client", "create an agent for our client", "deploy agents for [company]", or "build the OpenClaw setup for [client name]". This skill runs the full IBS OpenClaw product workflow: client interview, needs assessment, architecture design, workspace generation, openclaw.json configuration, deploy script, and professional handover documentation.

Audit, clean, and curate OpenClaw agent memory — reading daily memory logs, extracting durable facts, removing stale or contradictory entries, promoting important patterns to MEMORY.md, and keeping agent knowledge sharp and current. Use this skill when the user wants to clean up agent memory, says the agent seems to be "forgetting" things or repeating itself, wants to consolidate daily logs into long-term memory, notices the agent has stale or incorrect information, or asks to "review the agent's memory", "clean up the memory", "update what the agent knows", or "curate the memory files". Also trigger on a scheduled quarterly review or when significant time has passed since agents were last deployed (2+ months).

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 user wants to build a new OpenClaw agent with a domain-specific persona, create an AI company or multi-agent team with differentiated personalities, design a soul architecture for an agent role, or asks to "research and build an agent" for any business function. Trigger when the user mentions building agents for sales, marketing, operations, development, SHEQ, finance, HR, content, or any specialist role — even if they don't explicitly say "persona" or "soul". This skill does the full job: researches the world's best practitioners in that domain, extracts their mental models, maps those frameworks onto an agent soul, and outputs production-ready workspace files ready to deploy into OpenClaw.

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 tender agents", "build tender team", "openclaw tender setup", or wants to build an AI tendering system for a company.

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 agent", "improve my agent setup", "workspace health check", or "agent quality audit". Distinct from autonomy-audit which focuses only on autonomous operation readiness — this skill audits the full workspace quality including persona coherence, memory health, and configuration correctness.

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.

Use when the user asks about OpenClaw documentation sources, how to access crawled docs, where to find official documentation, how the documentation sync system works, or when referencing OpenClaw product docs for any task.

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.

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.

Use when the user wants to design an agent team, write SOUL.md files, set up agent hierarchy, configure agent tools and permissions, understand memory architecture, set up cron schedules for agents, or follow best practices for organizing an OpenClaw agent team.

Use when the user wants to set up memory, understand memory architecture, bootstrap files, configure shared memory, write MEMORY.md, set up daily logs, understand SCRIBE compression, fix memory retrieval, debug memory failure modes, set up team memory, configure agent memory, understand memory layers, or use memory compression patterns.

Audit and score agent autonomy readiness. Scans SOUL.md, HEARTBEAT.md, AGENTS.md, cron jobs, heartbeat config, daemon setup, error handling, and monitoring to identify gaps preventing true autonomous operation.

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 agents.

Use when the user wants to build a multi-agent team, set up agent collaboration, configure commander-specialist routing, orchestrate group chat with multiple agents, set up mention gating for agent teams, configure dual-channel multi-agent, or build an agent operating system in OpenClaw.

Use when the user wants to set up cron jobs, configure webhooks, add hooks, schedule automated tasks, configure heartbeat, set up periodic messages, automate agent actions, manage cron runs, or configure event-driven automation in OpenClaw.

Use when the user wants to change the AI model, configure model providers, set up API keys, add a custom provider, configure model failover, list available models, set up auth profiles, manage model selection, or configure image models in OpenClaw.

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 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 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 set up WhatsApp, configure Telegram, add Discord, connect Slack, pair a channel, manage OpenClaw channels, configure DM policies, set up group mention gating, or connect any messaging platform to OpenClaw.

Use when the user wants to configure OpenClaw, edit openclaw.json, change OpenClaw settings, set up gateway authentication, configure models or providers, manage environment variables, use secret references, understand OpenClaw config sections, or use the OpenClaw CLI.

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 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.

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.