Agent skill

Openclaw Setup

by FerroxLabs in FerroxLabs/wayland

OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Openclaw Setup

skills CLI
$ npx skills add FerroxLabs/wayland --skill openclaw-setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install FerroxLabs/wayland openclaw-setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/FerroxLabs/wayland.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/process/resources/skills/openclaw-setup .claude/skills/openclaw-setup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openclaw-setup
GitHub stars
608
Token cost
~1.9k tokens
SKILL.md length
612 words
Files
8 (incl. references)
Skills in repo
1,194
Repo updated
First seen
Licence
AGPL-3.0

At a glance

OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant.

  • Works in 3 steps: Confirm openclaw is installed: npm list… → If installed but unresolvable, PATH is… → Workaround: use an absolute path in the…
  • Users need to install OpenClaw
  • SKILL.md covers Important: Documentation…, Step 1: Environment…, Quickly Classify the User's… and Quick Start, plus 4 more sections
  • Calls npm and node

What it does

Openclaw Setup is an agent skill from FerroxLabs/wayland. OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant. Can diagnose issues, create bots, execute automated tasks, etc. Use when users need to install OpenClaw, configure Gateway, set up Channels, create Agents, troubleshoot issues, or perform OpenClaw-related operations.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/best-practices.md`, `references/configuration.md` and `references/deployment.md`).

It sits in AI & LLM Engineering, covering Building AI agents. It works with npm. The repository describes itself as: Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves. The licence is AGPL-3.0.

When your agent uses it

  • Users need to install OpenClaw
  • Configure Gateway
  • Set up Channels
  • Troubleshoot issues

Example prompts

  • “/openclaw-setup”

Requirements

  • Node.js

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Confirm openclaw is installed: npm list -g openclaw
  2. If installed but unresolvable, PATH is missing the npm global bin directory. This is typically caused by how Wayland is launched (not from…
  3. Workaround: use an absolute path in the command, e.g. $(npm bin -g)/openclaw doctor.

What it can do on your machine

Read from SKILL.md and the folder at commit 4c030c7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.openclaw.ai
    • github.com
    • discord.gg

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openclaw Setup loads about 1.9k tokens when it runs, and up to ~7.8k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 612 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from FerroxLabs/wayland at commit 4c030c7, republished under its AGPL-3.0 licence (© FerroxLabs). 612 words, ~1,872 tokens.

Download SKILL.mdSave it as .claude/skills/openclaw-setup/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
openclaw-setup
description
OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant. Can diagnose issues, create bots, execute automated tasks, etc. Use when users need to install OpenClaw, configure Gateway, set up Channels, create Agents, troubleshoot issues, or perform OpenClaw-related operations.

OpenClaw Usage Expert

You are an OpenClaw usage expert. You help users install, deploy, configure, and use the OpenClaw personal AI assistant.

Important: Documentation Freshness

This document was written against a historical version. OpenClaw is an actively maintained open source project that ships updates regularly.

  • Prefer the latest docs: When you hit anything uncertain, check the OpenClaw GitHub repo for the current README and docs.
  • Official documentation: docs.openclaw.ai hosts the up-to-date official documentation.
  • Role of this skill: Provides baseline knowledge and common operation guides. For new features or behavior changes, consult the latest sources.

Step 1: Environment Diagnostics (run before every response)

Before answering any OpenClaw question, run the environment diagnostics to confirm the tool can be located:

bash
# 1. Inspect the PATH actually available to the Wayland worker process
node -e "console.log('PATH entries:', process.env.PATH.split(require('path').delimiter).length); console.log('First 3:', process.env.PATH.split(require('path').delimiter).slice(0,3))"

# 2. Check whether openclaw is resolvable on PATH
which openclaw 2>/dev/null || where openclaw 2>/dev/null || echo "❌ openclaw NOT found in PATH"

# 3. If not found, check the npm global install location
npm root -g && npm bin -g

Interpreting the results:

  • ✅ openclaw resolved → environment is healthy, proceed normally.
  • ❌ openclaw NOT found in PATH → environment issue. Triage as follows:
    1. Confirm openclaw is installed: npm list -g openclaw
    2. If installed but unresolvable, PATH is missing the npm global bin directory. This is typically caused by how Wayland is launched (not from a terminal).
    3. Workaround: use an absolute path in the command, e.g. $(npm bin -g)/openclaw doctor.

Quickly Classify the User's State

Based on the user's question, identify which state they are in:

  1. Not installed: User asks how to install or where to start → see references/installation.md.
  2. Installation problems: User hits install errors, services that won't start, or config issues → see references/troubleshooting.md.
  3. Installed and wants to use it: User wants to create bots, run tasks, or configure features → see references/usage.md and references/configuration.md.
  4. Wants to uninstall: User wants to remove OpenClaw → see references/uninstallation.md.

Quick Start

First-time install
bash
# Install OpenClaw
npm install -g openclaw@latest

# Run the onboarding wizard
openclaw onboard --install-daemon

Full install steps: see references/installation.md.

Check status
bash
# Check Gateway status
openclaw gateway status

# Run health check
openclaw doctor
Talk to an Agent
bash
openclaw agent --message "help me complete a task"

Documentation Map

Pick the reference doc that matches the user's need:

Install and deploy
  • references/installation.md - full installation guide

    • System requirements
    • Multiple install paths (official script, npm, source)
    • Verifying the install
  • references/deployment.md - deployment and runtime guide

    • Onboarding wizard
    • Gateway start-up and management
    • Service installation (launchd / systemd)
    • Remote Gateway deployment
Troubleshooting
  • references/troubleshooting.md - complete troubleshooting guide
    • Using the doctor command
    • Diagnosing common issues (Gateway won't start, auth failures, channel connection failures, etc.)
    • Troubleshooting workflow
    • How to read the logs
Show full SKILL.md (256 more words)Show less
Usage guides
  • references/usage.md - usage guide
    • Creating and managing Agents
    • Talking to Agents
    • Sending messages
    • Channel management
    • Workspace management
    • Automated tasks (Cron, Webhooks)
    • Updates and upgrades
Configuration management
  • references/configuration.md - configuration guide
    • Configuration file locations
    • Configuration commands (get / set / configure)
    • Examples of common config entries
    • Multi-instance configuration
    • Configuration file permissions
Best practices
  • references/best-practices.md - best practices and special scenarios
    • Best practices when helping users
    • Special scenarios (purpose-built bots, automation, multi-Agent routing, remote Gateway)
    • Security recommendations
    • Performance tuning
Uninstall guide
  • references/uninstallation.md - full uninstall guide
    • Stopping services and processes
    • Removing the npm global package
    • Deleting config files and directories
    • Removing system services (launchd / systemd)
    • Cleaning up environment variables and logs
    • Verifying the uninstall

Command Cheat Sheet

bash
# Install and configure
openclaw onboard --install-daemon    # Onboarding wizard
openclaw configure                    # Reconfigure
openclaw setup                        # Set up workspace

# Service management
openclaw gateway status               # Check status
openclaw gateway start                # Start
openclaw gateway stop                  # Stop
openclaw gateway install              # Install as a service

# Diagnostics
openclaw doctor                       # Health check
openclaw doctor --repair             # Auto-repair
openclaw channels status              # Channel status

# Agent operations
openclaw agents list                  # List Agents
openclaw agent --message "..."       # Talk to an Agent
openclaw message send --to ...       # Send a message

# Configuration
openclaw config get <key>             # Read a config value
openclaw config set <key> <value>     # Write a config value

Reference Resources

Standard flow for handling a user request
  1. Classify the user's state: Based on the question, decide whether they are not yet installed, hitting install issues, installed and using it, or removing it.

  2. Open the matching doc:

    • Not installed → references/installation.md
    • Install problems → references/troubleshooting.md
    • Wants to use it → references/usage.md and references/configuration.md
    • Wants to uninstall → references/uninstallation.md
  3. Provide a solution:

    • Run openclaw doctor first to diagnose.
    • Give concrete steps based on the diagnostics output.
    • When sensitive information is involved, hand control back to the user.
  4. Verify and follow up:

    • Verify the result after each step.
    • If the issue persists, point the user at the latest GitHub documentation.

Remember: When anything is uncertain, the GitHub repo is the source of truth - check its latest docs and README first.

© FerroxLabs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in src/process/resources/skills/openclaw-setup of FerroxLabs/wayland.

  • SKILL.md
  • references/best-practices.md
  • references/configuration.md
  • references/deployment.md
  • references/installation.md
  • references/troubleshooting.md
  • references/uninstallation.md
  • references/usage.md

Open the folder on GitHubat commit 4c030c7

Compare with similar skills

Openclaw Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Openclaw Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openclaw Setup this skillFerroxLabs/wayland608—~1.9kAutomated safety check: PassAGPL-3.0
Olakai Agent Project Setupandrewyng/context-hub14k—~5kAutomated safety check: PassMIT
Langgraph Project Setupsoba-labs/langchain-agent-skills107—~2.4kAutomated safety check: NotesMIT
Integrate Hub Agentamd/gaia1.6k—~2.1kAutomated safety check: PassMIT
Update Integrations PRslangchain-ai/docs424—~1.7kAutomated safety check: PassMIT
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Olakai Agent Project Setup

    andrewyng/context-hub

    Builds a new AI agent with Olakai monitoring from the start: CLI login, SDK integration, per-agent KPI configuration and an end-to-end check that data flows.

    14k GitHub stars~5k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed
  • Langgraph Project Setup

    soba-labs/langchain-agent-skills

    Initialize and configure LangGraph projects with proper structure, langgraph.json configuration, environment variables, and dependency management.

    107 GitHub stars~2.4k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes
  • Embeds one of this repo's pre-built hub agents (under hub/agents/) into a developer's own application.

    1.6k GitHub stars~2.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Update Integrations PRs

    langchain-ai/docs

    Official

    Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override).

    424 GitHub stars~1.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed
  • Official

    Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.

    3.1k GitHub starsUsed in 6 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed

More from FerroxLabs/wayland

All 1,194 skills in this repo
  • Star Office Helper

    FerroxLabs/wayland

    Install, start, connect, and troubleshoot visualization companion projects for Aion/OpenClaw, with Star-Office-UI as the default recommendation.

    608 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: notes
  • Tvcontrol Setup

    FerroxLabs/wayland

    Set up TVControl end to end: install the connector, start TradingView Desktop with its control port open, load a watchlist export, add the indicators they use, and leave a working chart.

    608 GitHub stars~5.7k tokensUpdated yesterday
    Auto-check passed
  • Ab Testing Specialist

    FerroxLabs/wayland

    End-to-end guide for designing, running, and analyzing A/B tests including experiment design, statistical significance, sample size calculation, common pitfalls, and advanced testing patterns.

    608 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Academic Writer

    FerroxLabs/wayland

    Complete academic writing guide covering thesis and dissertation structure, journal article format using IMRaD, literature review methodology, citation management, the peer review process, and…

    608 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed
  • Accessibility Auditor

    FerroxLabs/wayland

    Web accessibility expertise covering WCAG 2.2 conformance, audit methodology, ARIA patterns, keyboard navigation, screen reader testing, focus management, form accessibility, and automated vs manual…

    608 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed
  • Organizational accessibility culture building expertise covering champion network design, accessibility training curricula, audit cadence and methodology, KPI definition and tracking, executive…

    608 GitHub stars~3.9k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Openclaw Setup

What does Openclaw Setup do?

OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant. Openclaw Setup is an agent skill from FerroxLabs/wayland. OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant.

When should I use Openclaw Setup?

Openclaw Setup fits situations like: users need to install OpenClaw; configure Gateway; set up Channels; troubleshoot issues.

How do I install Openclaw Setup in Claude Code?

Run `npx skills add FerroxLabs/wayland --skill openclaw-setup -a claude-code`. Or copy the skill folder (src/process/resources/skills/openclaw-setup in FerroxLabs/wayland) into .claude/skills/openclaw-setup in your project. Claude Code loads it when a task matches its description.

How do I install Openclaw Setup in Codex?

Run `npx skills add FerroxLabs/wayland --skill openclaw-setup -a codex`. Or copy the skill folder (src/process/resources/skills/openclaw-setup in FerroxLabs/wayland) into .agents/skills/openclaw-setup in your project. Codex loads it when a task matches its description.

Can I use Openclaw Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FerroxLabs/wayland --skill openclaw-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openclaw-setup, .gemini/skills/openclaw-setup, .github/skills/openclaw-setup and .opencode/skills/openclaw-setup in your project.

What does Openclaw Setup need to run?

Going by SKILL.md and its folder, Openclaw Setup needs the command-line tools its instructions call (npm and node). Our summary lists: Node.js.

Does Openclaw Setup access the network?

SKILL.md names 3 domains. As links in the text: docs.openclaw.ai, github.com and discord.gg. This is read from the text; nothing was executed.

Is Openclaw Setup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Openclaw Setup use?

Openclaw Setup is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openclaw Setup use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6k tokens, read only when the agent opens those files.

What are the alternatives to Openclaw Setup?

Skills that share tags, products or a category with Openclaw Setup: Olakai Agent Project Setup (andrewyng/context-hub, 14k stars), Langgraph Project Setup (soba-labs/langchain-agent-skills, 107 stars), Integrate Hub Agent (amd/gaia, 1.6k stars) and Update Integrations PRs (langchain-ai/docs, 424 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openclaw Setup?

FerroxLabs (a GitHub user) maintains it in FerroxLabs/wayland, which has 608 GitHub stars. The repository holds 1,194 skills in this directory. The repository was last updated on October 6, 2026.

Source: FerroxLabs/wayland on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.