Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Control cloud browser sessions via Steel.dev for web automation and computer-use agents. Use when you need to browse the web, fill forms, click elements, tak...
Control cloud browser sessions via Steel.dev for web automation and computer-use agents. Use when you need to browse the web, fill forms, click elements, tak...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Cloud browser-use via Steel.dev + Playwright Python SDK. Ideal for web automation, scraping, form filling, and AI agent browser loops.
pip install steel-sdk playwright export STEEL_API_KEY=your_key_here Get your API key at https://app.steel.dev → Settings → API Keys (free: 100 browser hours). Steel API key should be set in OpenClaw config or environment: openclaw config set env.STEEL_API_KEY "your_key"
start_session.sh saves session ID to ~/.steel_state All scripts auto-load it from there Override anytime with export STEEL_SESSION_ID=<id> Sessions persist until release_session.sh or timeout
ScriptUsageDescriptionstart_session.sh[--proxy] [--captcha] [--timeout MS]Create session; prints SESSION_ID + VIEWER_URLrelease_session.sh[SESSION_ID]Release sessionlist_sessions.sh(none)List active sessionsnavigate.shURL [--wait-until networkidle]Go to URLscreenshot.sh[OUTPUT.png] [--full-page]Take screenshotclick.shSELECTORClick by CSS/text/aria selectorclick_coords.shX Y [--right] [--double]Click at pixel coords (fallback)type.shSELECTOR "text"Fill input fieldpress_key.shKEYPress key (e.g. Enter, Control+a)scroll.shAMOUNT|--to-bottom|--to-top|SELECTORScroll pagehover.shSELECTORHover over elementselect.shSELECTOR VALUESelect dropdown optionget_content.sh[--html] [SELECTOR]Extract page text or HTMLeval_js.sh"js expression"Execute JavaScript, print resultwait_for.shSELECTOR [TIMEOUT_MS]Wait for element to appearget_url.sh(none)Print current URL and page title
Steel uses Playwright selectors — much more powerful than pixel coords: # By CSS click.sh "#submit-button" click.sh ".nav-link:first-child" # By text content click.sh "text=Sign in" click.sh "button:has-text('Continue')" # By aria label click.sh "[aria-label='Search']" click.sh "[placeholder='Email address']" # XPath click.sh "xpath=//button[@type='submit']"
SCRIPTS="skills/steel-browser/scripts" # 1. Start session (add --proxy --captcha for tough sites) source <($SCRIPTS/start_session.sh) echo "Session: $SESSION_ID" echo "Watch at: $VIEWER_URL" # 2. Navigate $SCRIPTS/navigate.sh "https://example.com" # 3. Agent loop while true; do $SCRIPTS/screenshot.sh /tmp/screen.png # Get page text for LLM context CONTENT=$($SCRIPTS/get_content.sh) # LLM decides action... ACTION=$(echo "$CONTENT" | llm_decide /tmp/screen.png) case "$ACTION_TYPE" in click) $SCRIPTS/click.sh "$SELECTOR" ;; type) $SCRIPTS/type.sh "$SELECTOR" "$TEXT" ;; navigate) $SCRIPTS/navigate.sh "$URL" ;; done) break ;; esac done # 4. Release $SCRIPTS/release_session.sh
FeatureSteel BrowserE2B DesktopSelectorsPlaywright CSS/text/aria ✅Pixel coords onlyProxy support✅ Residential proxies❌CAPTCHA solving✅ Built-in❌Non-browser tasks❌✅ Desktop apps, terminalSession viewer✅ Live URL✅ VNC stream Use Steel for web automation. Use E2B Desktop for desktop apps / full OS control.
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.