Comprehensive skill for installing, configuring, and managing the OpenClaw ecosystem (Gateway, Channels, Models, Automation, Nodes, and Deployment)
OpenClaw CLI wrapper — gateway, channels, models, agents, nodes, browser, memory, security, automation.
doanbactam
@doanbactam
What This Skill Does
CLI wrapper for installing, configuring, and managing the OpenClaw ecosystem including gateway, channels, models, agents, nodes, browser, memory, security, and automation. Provides local reference docs and a security-gated command router.
Replaces manual configuration and ad-hoc scripting for OpenClaw operations by providing a unified, security-gated CLI with built-in documentation.
When to Use It
- Install and set up the OpenClaw gateway for the first time
- Configure channels, models, and agents through the CLI
- Manage browser automation and memory search tasks
- Apply security policies and approve high-risk operations
- Deploy and update OpenClaw nodes across platforms
- View system health, logs, and run diagnostics
Install
$ openclaw skills install @doanbactam/openclaw-anythingOpenClaw Skill
CLI wrapper + docs companion. Does NOT contain OpenClaw runtime source.
Wraps openclaw CLI and provides local reference docs aligned to https://docs.openclaw.ai.
Prerequisites
openclawCLI inPATH(required)- Node.js (install/update flows), Playwright deps (browser), Tailscale (remote nodes) — optional
Quick Reference
| Need | File |
|---|---|
| Find a command | references/cli-full.md → search by keyword |
| Security rules | references/security-policy.md |
| Config syntax | references/config-schema.md |
| Deploy/update | references/deployment.md |
| Platform notes | references/nodes-platforms.md |
| Doc links | references/hubs.md |
Global Flags
--dev --profile <name> --no-color --json -V
Security Model
Default: least privilege. High-risk ops require explicit per-action approval.
Low-risk (default)
Status, list, health, doctor, logs, config read, docs search, memory search.
High-risk (require OPENCLAW_WRAPPER_ALLOW_RISKY=1)
Shell exec · nodes invoke/run/camera/screen/location · browser automation · cron mutate · plugin/hook install · device pairing · secrets apply · sandbox recreate · webhooks · dns setup.
Wrapper: bash scripts/openclaw.sh <command> [args]
Granular gating: plugin gates only install/enable, secrets gates only apply, sandbox gates only recreate.
Wrapper Command Routes
LOW-RISK (pass-through):
install setup doctor status reset version tui dashboard
update uninstall health logs configure completion config docs qr
channel model agent agents message sessions memory skills
security approvals system directory acp gateway service
HIGH-RISK (OPENCLAW_WRAPPER_ALLOW_RISKY=1):
cron browser webhooks dns nodes node devices pairing prose
plugin (install|enable only)
hooks (install|enable only)
secrets (apply only)
sandbox (recreate only)
Non-goals
- Not the OpenClaw runtime source
- Does not provision system packages
- Does not manage networking/VPN
- Does not authorize autonomous privileged execution
Last normalization: 2026-02-27 · Source: https://docs.openclaw.ai
Top skills in this category
Agent Browser
@matrixyHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Browser Use
@shawnpanaAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with w...
Find Skills Skill
@fangkelvinSearch and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
Playwright MCP
@spiceman161Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.
Playwright (Automation + MCP + Scraper)
@ivangdavilaAutomates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).