{"id":"814797ad-25d8-421f-a579-c5145cc20f6f","entityType":"agent","slug":"clawhub-zdstudios-browser-cli","name":"browser-cli","canonicalUrl":"https://www.xpersona.co/agent/clawhub-zdstudios-browser-cli","canonicalPath":"/agent/clawhub-zdstudios-browser-cli","generatedAt":"2026-10-12T20:15:40.118Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T00:42:28.504Z","emptyReason":null},"description":"Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Skill: browser-cli Owner: zdstudios Summary: Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T03:43:10.107Z | user Initial public release of the browser-use CLI Skill. - Automate browser tasks from the command line: navigation, form filling, screenshot","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 966 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s17cm60j7xzpqzdgxp50te4ygn83ykme:browser-cli","sourceUrl":"https://clawhub.ai/zdstudios/browser-cli","homepage":"https://clawhub.ai/zdstudios/skills/browser-cli","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/zdstudios/browser-cli","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/zdstudios/skills/browser-cli","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:42:28.504Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:42:28.504Z","emptyReason":null},"stars":null,"forks":null,"downloads":966,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"966 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:42:28.491Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T00:42:28.504Z","lastCrawledAt":"2026-10-12T00:42:28.491Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T00:42:28.491Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-04-28T03:43:10.107Z","changelog":"Initial public release of the browser-use CLI Skill. - Automate browser tasks from the command line: navigation, form filling, screenshots, JavaScript execution, tab and cookie management. - Supports running locally (headless/headed), connecting to real Chrome profiles, or driving cloud browsers. - Organized commands for navigation, interaction, inspection, session management, cloud API, and tunneling local servers. - Quick installation and health checks with simple commands. - Interactive workflows with persistent daemon processes and session controls.","fileCount":3,"zipByteSize":6290}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17cm60j7xzpqzdgxp50te4ygn83ykme:browser-cli","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T20:15:40.118Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-12T00:42:28.504Z","emptyReason":null},"readme":"Skill: browser-cli\n\nOwner: zdstudios\n\nSummary: Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and...\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-04-28T03:43:10.107Z | user\n\nInitial public release of the browser-use CLI Skill.\n\n- Automate browser tasks from the command line: navigation, form filling, screenshots, JavaScript execution, tab and cookie management.\n- Supports running locally (headless/headed), connecting to real Chrome profiles, or driving cloud browsers.\n- Organized commands for navigation, interaction, inspection, session management, cloud API, and tunneling local servers.\n- Quick installation and health checks with simple commands.\n- Interactive workflows with persistent daemon processes and session controls.\n\nArchive index:\n\nArchive v1.0.0: 3 files, 6290 bytes\n\nFiles: skill-card.md (2502b), SKILL.md (13486b), _meta.json (130b)\n\nFile v1.0.0:SKILL.md\n\n# browser-use CLI Skill\n\n## What This Skill Covers\nUse this skill any time you need to automate a browser from the command line using `browser-use`. This includes navigating pages, clicking/typing/filling forms, taking screenshots, running JavaScript, managing tabs, handling cookies, driving cloud browsers, and exposing local servers via tunnels.\n\n---\n\n## Installation\n\n### Prerequisites\n| Platform | Requirements |\n|----------|-------------|\n| macOS    | Python 3.11+ |\n| Linux    | Python 3.11+ |\n| Windows  | Git for Windows + Python 3.11+ |\n\n### One-line Install (Recommended)\n```bash\n# macOS / Linux\ncurl -fsSL https://browser-use.com/cli/install.sh | bash\n\n# Windows (PowerShell)\n& \"C:\\Program Files\\Git\\bin\\bash.exe\" -c 'curl -fsSL https://browser-use.com/cli/install.sh | bash'\n```\n\n### Manual Install\n```bash\nuv pip install browser-use\nbrowser-use install   # downloads Chromium\nbrowser-use doctor    # validates setup\n```\n\n### Post-Install Health Check\n```bash\nbrowser-use doctor   # prints diagnostics + config\nbrowser-use setup    # optional interactive wizard\n```\n\n---\n\n## Core Mental Model\n\nThe workflow is always:\n1. **Open** a page → `browser-use open <url>`\n2. **Inspect** the page → `browser-use state` (returns numbered element indices)\n3. **Interact** using those indices → `browser-use click 3`, `browser-use input 1 \"text\"`\n4. **Repeat** — the daemon keeps the browser alive between commands (~50ms latency)\n\nA background daemon process starts automatically on first command and stays alive until you `browser-use close`.\n\n---\n\n## Browser Modes\n\n```bash\n# Default: headless Chromium (invisible)\nbrowser-use open https://example.com\n\n# Visible window\nbrowser-use --headed open https://example.com\n\n# Use your real Chrome (preserves logins, cookies, extensions)\nbrowser-use connect\n\n# Use a specific Chrome profile\nbrowser-use --profile \"Default\" open https://gmail.com\n\n# Zero-config cloud browser (requires API key)\nbrowser-use cloud connect\n\n# Connect to existing browser via CDP\nbrowser-use --cdp-url http://localhost:9222 open https://example.com\nbrowser-use --cdp-url ws://localhost:9222/devtools/browser/... state\n```\n\nAfter `connect` or `cloud connect`, all subsequent commands automatically target that browser — no extra flags needed.\n\n---\n\n## All Commands\n\n### Navigation\n```bash\nbrowser-use open <url>               # Navigate to URL\nbrowser-use back                     # Go back in history\nbrowser-use scroll down              # Scroll down\nbrowser-use scroll up                # Scroll up\nbrowser-use scroll down --amount 1000  # Scroll by pixel amount\n```\n\n### Inspection\n```bash\nbrowser-use state                    # Get URL, title, and numbered clickable elements\nbrowser-use screenshot output.png    # Take screenshot to file\nbrowser-use screenshot               # Screenshot as base64 (stdout)\nbrowser-use screenshot --full page.png  # Full-page screenshot\n```\n\n### Interaction\n```bash\nbrowser-use click <index>            # Click element by index (from state)\nbrowser-use click <x> <y>           # Click at pixel coordinates\nbrowser-use type \"text\"              # Type into currently focused element\nbrowser-use input <index> \"text\"     # Click element then type (most common for forms)\nbrowser-use keys \"Enter\"             # Send keyboard key\nbrowser-use keys \"Control+a\"         # Send key combination\nbrowser-use select <index> \"value\"   # Select dropdown option\nbrowser-use upload <index> /path/to/file  # Upload file to file input\nbrowser-use hover <index>            # Hover over element\nbrowser-use dblclick <index>         # Double-click element\nbrowser-use rightclick <index>       # Right-click element\n```\n\n### Tabs\n```bash\nbrowser-use tab list                 # List all open tabs\nbrowser-use tab new                  # Open blank tab\nbrowser-use tab new https://url.com  # Open tab with URL\nbrowser-use tab switch <index>       # Switch to tab by index\nbrowser-use tab close                # Close current tab\nbrowser-use tab close <index>        # Close specific tab\n```\n\n### Cookies\n```bash\nbrowser-use cookies get                        # Get all cookies\nbrowser-use cookies get --url https://site.com # Get cookies for URL\nbrowser-use cookies set name value             # Set a cookie\nbrowser-use cookies set name val --domain .example.com --secure\nbrowser-use cookies set name val --same-site Strict   # Strict | Lax | None\nbrowser-use cookies set name val --expires 1735689600 # Unix timestamp\nbrowser-use cookies clear                      # Clear all cookies\nbrowser-use cookies clear --url https://site.com\nbrowser-use cookies export cookies.json        # Export to JSON\nbrowser-use cookies import cookies.json        # Import from JSON\n```\n\n### Waiting\n```bash\nbrowser-use wait selector \".btn\"               # Wait for element to be visible\nbrowser-use wait selector \".loading\" --state hidden  # Wait for element to disappear\nbrowser-use wait text \"Success\"                # Wait for text to appear on page\nbrowser-use wait selector \"h1\" --timeout 5000 # Custom timeout in ms\n```\n\n### Get (Information Retrieval)\n```bash\nbrowser-use get title                  # Get page title\nbrowser-use get html                   # Get full page HTML\nbrowser-use get html --selector \"main\" # Get HTML of specific element\nbrowser-use get text <index>           # Get text content of element\nbrowser-use get value <index>          # Get value of input/textarea\nbrowser-use get attributes <index>     # Get all element attributes\nbrowser-use get bbox <index>           # Get bounding box (x, y, width, height)\n```\n\n### JavaScript\n```bash\nbrowser-use eval \"document.title\"\nbrowser-use eval \"Array.from(document.querySelectorAll('a')).map(a => a.href)\"\nbrowser-use eval \"window.scrollTo(0, document.body.scrollHeight)\"\n```\n\n### Python (Persistent Session)\n```bash\nbrowser-use python \"x = 42\"              # Set a variable\nbrowser-use python \"print(x)\"            # Access variable (prints: 42)\nbrowser-use python \"print(browser.url)\"  # Access browser object\nbrowser-use python --vars                # Show all defined variables\nbrowser-use python --reset               # Clear namespace\nbrowser-use python --file script.py      # Run a Python file\n```\n\n---\n\n## Session Management\n\nEach `--session` gets its own daemon, socket, and browser instance.\n\n```bash\n# Default session (implicit)\nbrowser-use open https://example.com\nbrowser-use state\n\n# Named sessions\nbrowser-use --session work open https://example.com\nbrowser-use --session personal open https://gmail.com\nbrowser-use --session work state    # targets work browser\n\n# List all active sessions\nbrowser-use sessions\n\n# Close a specific session\nbrowser-use --session work close\n\n# Close all sessions\nbrowser-use close --all\n\n# Via environment variable\nBROWSER_USE_SESSION=work browser-use state\n```\n\n---\n\n## Cloud API\n\n### Auth\n```bash\nbrowser-use cloud login sk-abc123...    # Save API key\nbrowser-use cloud logout                # Remove API key\n# Or: export BROWSER_USE_API_KEY=sk-abc123...\n```\n\n### Cloud Browser\n```bash\nbrowser-use cloud connect              # Provision cloud browser and connect\nbrowser-use state                      # Works normally after connect\nbrowser-use close                      # Disconnect AND stop cloud browser\nbrowser-use cloud close                # Also stops cloud browser\n```\n\n### REST Passthrough\n```bash\nbrowser-use cloud v2 GET /browsers\nbrowser-use cloud v2 POST /tasks '{\"task\":\"Search for AI news\",\"url\":\"https://google.com\"}'\nbrowser-use cloud v2 poll <task-id>    # Poll until task completes\nbrowser-use cloud v3 POST /path '{\"key\":\"value\"}'\nbrowser-use cloud v2 --help            # Show all v2 API endpoints\nbrowser-use cloud v3 --help            # Show all v3 API endpoints\n```\n\n---\n\n## Tunnels (Expose Local Server to Cloud Browser)\n\n```bash\nbrowser-use tunnel 3000                # Expose localhost:3000 → public HTTPS URL\nbrowser-use tunnel list                # List active tunnels\nbrowser-use tunnel stop 3000           # Stop tunnel for port\nbrowser-use tunnel stop --all          # Stop all tunnels\n\n# Typical flow for testing local app with a cloud browser:\nnpm run dev &\nbrowser-use tunnel 3000                # → https://abc.trycloudflare.com\nbrowser-use cloud connect\nbrowser-use open https://abc.trycloudflare.com\n```\n\n---\n\n## Profile Management (Sync Chrome Cookies to Cloud)\n\n```bash\nbrowser-use profile                    # Interactive sync wizard\nbrowser-use profile list               # List detected browsers + profiles\nbrowser-use profile sync --all         # Sync all profiles to cloud\nbrowser-use profile sync --browser \"Google Chrome\" --profile \"Default\"\nbrowser-use profile auth --apikey <key>\nbrowser-use profile inspect --browser \"Google Chrome\" --profile \"Default\"\nbrowser-use profile update             # Update the profile-use binary\n```\n\n---\n\n## Global Options\n\n| Flag | Description |\n|------|-------------|\n| `--headed` | Show browser window |\n| `--profile [NAME]` | Use real Chrome profile (bare flag = \"Default\") |\n| `--connect` | Auto-discover running Chrome via CDP |\n| `--cdp-url <url>` | Connect to existing browser via CDP URL |\n| `--session NAME` | Target named session (default: \"default\") |\n| `--json` | Output as JSON |\n| `--mcp` | Run as MCP server via stdin/stdout |\n\n---\n\n## Configuration\n\n```bash\nbrowser-use config list                              # Show all config\nbrowser-use config set cloud_connect_proxy jp        # Set a value\nbrowser-use config get cloud_connect_proxy           # Get a value\nbrowser-use config unset cloud_connect_timeout       # Remove a value\n```\n\nConfig file: `~/.browser-use/config.json`\n\n---\n\n## Template Generation\n\n```bash\nbrowser-use init                          # Interactive template picker\nbrowser-use init --list                   # List all templates\nbrowser-use init --template basic         # Generate specific template\nbrowser-use init --output my_script.py    # Specify output filename\nbrowser-use init --force                  # Overwrite existing files\n```\n\n---\n\n## File Layout\n\n```\n~/.browser-use/\n├── config.json          # API key + settings\n├── bin/\n│   └── profile-use      # Managed Go binary (auto-downloaded)\n├── tunnels/\n│   ├── {port}.json      # Tunnel metadata\n│   └── {port}.log       # Tunnel logs\n├── default.state.json   # Daemon lifecycle state\n├── default.sock         # Daemon socket (ephemeral)\n├── default.pid          # Daemon PID (ephemeral)\n└── cli.log              # Daemon log\n```\n\nOverride the base dir with `BROWSER_USE_HOME`.\n\n---\n\n## Common Recipes\n\n### Fill and Submit a Form\n```bash\nbrowser-use open https://example.com/contact\nbrowser-use state\n# Output: [0] input \"Name\", [1] input \"Email\", [2] button \"Submit\"\nbrowser-use input 0 \"John Doe\"\nbrowser-use input 1 \"john@example.com\"\nbrowser-use click 2\nbrowser-use wait text \"Thank you\"\n```\n\n### Scrape Data with JavaScript\n```bash\nbrowser-use open https://news.ycombinator.com\nbrowser-use eval \"Array.from(document.querySelectorAll('.titleline a')).slice(0,5).map(a => a.textContent)\"\n```\n\n### Multi-step Python Automation\n```bash\nbrowser-use open https://example.com\nbrowser-use python \"\nfor i in range(5):\n    browser.scroll('down')\n    browser.wait(0.5)\nbrowser.screenshot('scrolled.png')\n\"\n```\n\n### Login with Saved Chrome Profile\n```bash\nbrowser-use --profile \"Default\" open https://gmail.com\nbrowser-use state\n# Gmail inbox loads already logged in\n```\n\n### Run Two Browsers in Parallel\n```bash\nbrowser-use --session a open https://site-a.com\nbrowser-use --session b open https://site-b.com\nbrowser-use --session a state\nbrowser-use --session b state\nbrowser-use close --all\n```\n\n### Test Local App via Cloud Browser\n```bash\nnpm run dev &\nbrowser-use tunnel 3000\n# Copy the printed public URL, e.g. https://xyz.trycloudflare.com\nbrowser-use cloud connect\nbrowser-use open https://xyz.trycloudflare.com\nbrowser-use screenshot check.png\n```\n\n---\n\n## Windows Troubleshooting\n\n**ARM64 Windows** — install x64 Python for emulation:\n```powershell\nwinget install Python.Python.3.11 --architecture x64\n```\n\n**Multiple Python versions** — pin the version:\n```powershell\n$env:PY_PYTHON=3.11\n```\n\n**PATH not updated** — restart terminal, or run via Git Bash:\n```powershell\n& \"C:\\Program Files\\Git\\bin\\bash.exe\" -c 'browser-use --help'\n```\n\n**Daemon won't start** — kill stale processes:\n```powershell\nwmic process where \"name='python.exe' and commandline like '%browser%use%'\" get processid\ntaskkill /PID <pid> /F\n```\n\n**Stale venv** — nuke and reinstall:\n```powershell\nwmic process where \"name='python.exe' and commandline like '%browser%use%'\" call terminate\nRemove-Item -Recurse -Force \"$env:USERPROFILE\\.browser-use-env\"\n# Re-run the installer\n```\n\n---\n\n## Quick Reference Card\n\n| Goal | Command |\n|------|---------|\n| Start + navigate | `browser-use open <url>` |\n| See elements | `browser-use state` |\n| Click element | `browser-use click <index>` |\n| Fill input | `browser-use input <index> \"text\"` |\n| Press key | `browser-use keys \"Enter\"` |\n| Screenshot | `browser-use screenshot out.png` |\n| Run JS | `browser-use eval \"js here\"` |\n| Wait for element | `browser-use wait selector \".cls\"` |\n| Get page HTML | `browser-use get html` |\n| Close browser | `browser-use close` |\n| Use real Chrome | `browser-use connect` |\n| Cloud browser | `browser-use cloud connect` |\n| Named session | `browser-use --session NAME <cmd>` |\n| Show config | `browser-use doctor` |\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn77p0ar3y9v6qqckkhj51rgd583z7p5\",\n  \"slug\": \"browser-cli\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1777347790107\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:\n\nAutomates browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and local tunneling.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[zdstudios](https://clawhub.ai/user/zdstudios)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and automation engineers use this skill to drive browser-use CLI workflows for web navigation, inspection, form interaction, screenshots, JavaScript execution, cookie and tab management, cloud browser sessions, and local app testing through tunnels.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill directs users to run remote installer code.\n\nMitigation: Install only when the browser-use publisher is trusted; prefer an isolated Python environment and manual installation when stronger review is needed.\n\nRisk: Browser automation can access pages, cookies, and local browser profiles.\n\nMitigation: Use a dedicated low-privilege browser profile and avoid syncing personal or work profiles.\n\nRisk: Cloud browser and tunnel workflows can expose local services or sensitive browsing state.\n\nMitigation: Avoid public tunnels for sensitive local apps, and close daemons, tunnels, and cloud browsers when work is complete.\n\nRisk: Diagnostics, screenshots, logs, and exported cookies may contain sensitive data.\n\nMitigation: Redact diagnostic output and generated files before sharing or storing them outside the trusted workspace.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/zdstudios/skills/browser-cli)\n- [Publisher profile](https://clawhub.ai/user/zdstudios)\n- [browser-use CLI installer](https://browser-use.com/cli/install.sh)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands, configuration paths, and command recipes]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include commands that start daemon sessions, use browser profiles, manage cookies, call cloud APIs, or open public tunnels.]\n\n## Skill Version(s):\n\n1.0.0 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.","readmeExcerpt":"Skill: browser-cli Owner: zdstudios Summary: Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T03:43:10.107Z | user Initial public release of the browser-use CLI Skill. - Automate browser tasks from the command line: navigation, form filling, screenshot","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"curl -fsSL https://browser-use.com/cli/install.sh | bash"},{"language":"bash","snippet":"# macOS / Linux\ncurl -fsSL https://browser-use.com/cli/install.sh | bash\n\n# Windows (PowerShell)\n& \"C:\\Program Files\\Git\\bin\\bash.exe\" -c 'curl -fsSL https://browser-use.com/cli/install.sh | bash'"},{"language":"bash","snippet":"uv pip install browser-use\nbrowser-use install   # downloads Chromium\nbrowser-use doctor    # validates setup"},{"language":"bash","snippet":"browser-use doctor   # prints diagnostics + config\nbrowser-use setup    # optional interactive wizard"},{"language":"bash","snippet":"# Default: headless Chromium (invisible)\nbrowser-use open https://example.com\n\n# Visible window\nbrowser-use --headed open https://example.com\n\n# Use your real Chrome (preserves logins, cookies, extensions)\nbrowser-use connect\n\n# Use a specific Chrome profile\nbrowser-use --profile \"Default\" open https://gmail.com\n\n# Zero-config cloud browser (requires API key)\nbrowser-use cloud connect\n\n# Connect to existing browser via CDP\nbrowser-use --cdp-url http://localhost:9222 open https://example.com\nbrowser-use --cdp-url ws://localhost:9222/devtools/browser/... state"},{"language":"bash","snippet":"browser-use open <url>               # Navigate to URL\nbrowser-use back                     # Go back in history\nbrowser-use scroll down              # Scroll down\nbrowser-use scroll up                # Scroll up\nbrowser-use scroll down --amount 1000  # Scroll by pixel amount"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"# browser-use CLI Skill\n\n## What This Skill Covers\nUse this skill any time you need to automate a browser from the command line using `browser-use`. This includes navigating pages, clicking/typing/filling forms, taking screenshots, running JavaScript, managing tabs, handling cookies, driving cloud browsers, and exposing local servers via tunnels.\n\n---\n\n## Installation\n\n### Prerequisites\n| Platform | Requirements |\n|----------|-------------|\n| macOS    | Python 3.11+ |\n| Linux    | Python 3.11+ |\n| Windows  | Git for Windows + Python 3.11+ |\n\n### One-line Install (Recommended)\n```bash\n# macOS / Linux\ncurl -fsSL https://browser-use.com/cli/install.sh | bash\n\n# Windows (PowerShell)\n& \"C:\\Program Files\\Git\\bin\\bash.exe\" -c 'curl -fsSL https://browser-use.com/cli/install.sh | bash'\n```\n\n### Manual Install\n```bash\nuv pip install browser-use\nbrowser-use install   # downloads Chromium\nbrowser-use doctor    # validates setup\n```\n\n### Post-Install Health Check\n```bash\nbrowser-use doctor   # prints diagnostics + config\nbrowser-use setup    # optional interactive wizard\n```\n\n---\n\n## Core Mental Model\n\nThe workflow is always:\n1. **Open** a page → `browser-use open <url>`\n2. **Inspect** the page → `browser-use state` (returns numbered element indices)\n3. **Interact** using those indices → `browser-use click 3`, `browser-use input 1 \"text\"`\n4. **Repeat** — the daemon keeps the browser alive between commands (~50ms latency)\n\nA background daemon process starts automatically on first command and stays alive until you `browser-use close`.\n\n---\n\n## Browser Modes\n\n```bash\n# Default: headless Chromium (invisible)\nbrowser-use open https://example.com\n\n# Visible window\nbrowser-use --headed open https://example.com\n\n# Use your real Chrome (preserves logins, cookies, extensions)\nbrowser-use connect\n\n# Use a specific Chrome profile\nbrowser-use --profile \"Default\" open https://gmail.com\n\n# Zero-config cloud browser (requires API key)\nbrowser-use cloud connect\n\n# Connect to existing browser via CDP\nbrowser-use --cdp-url http://localhost:9222 open https://example.com\nbrowser-use --cdp-url ws://localhost:9222/devtools/browser/... state\n```\n\nAfter `connect` or `cloud connect`, all subsequent commands automatically target that browser — no extra flags needed.\n\n---\n\n## All Commands\n\n### Navigation\n```bash\nbrowser-use open <url>               # Navigate to URL\nbrowser-use back                     # Go back in history\nbrowser-use scroll down              # Scroll down\nbrowser-use scroll up                # Scroll up\nbrowser-use scroll down --amount 1000  # Scroll by pixel amount\n```\n\n### Inspection\n```bash\nbrowser-use state                    # Get URL, title, and numbered clickable elements\nbrowser-use screenshot output.png    # Take screenshot to file\nbrowser-use screenshot               # Screenshot as base64 (stdout)\nbrowser-use screenshot --full page.png  # Full-page screenshot\n```\n\n### Interaction\n```bash\nbrowser-use click <index>            # Click element by index (from sta"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn77p0ar3y9v6qqckkhj51rgd583z7p5\",\n  \"slug\": \"browser-cli\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1777347790107\n}"},{"path":"skill-card.md","content":"## Description:\n\nAutomates browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and local tunneling.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[zdstudios](https://clawhub.ai/user/zdstudios)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and automation engineers use this skill to drive browser-use CLI workflows for web navigation, inspection, form interaction, screenshots, JavaScript execution, cookie and tab management, cloud browser sessions, and local app testing through tunnels.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill directs users to run remote installer code.\n\nMitigation: Install only when the browser-use publisher is trusted; prefer an isolated Python environment and manual installation when stronger review is needed.\n\nRisk: Browser automation can access pages, cookies, and local browser profiles.\n\nMitigation: Use a dedicated low-privilege browser profile and avoid syncing personal or work profiles.\n\nRisk: Cloud browser and tunnel workflows can expose local services or sensitive browsing state.\n\nMitigation: Avoid public tunnels for sensitive local apps, and close daemons, tunnels, and cloud browsers when work is complete.\n\nRisk: Diagnostics, screenshots, logs, and exported cookies may contain sensitive data.\n\nMitigation: Redact diagnostic output and generated files before sharing or storing them outside the trusted workspace.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/zdstudios/skills/browser-cli)\n- [Publisher profile](https://clawhub.ai/user/zdstudios)\n- [browser-use CLI installer](https://browser-use.com/cli/install.sh)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands, configuration paths, and command recipes]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include commands that start daemon sessions, use browser profiles, manage cookies, call cloud APIs, or open public tunnels.]\n\n## Skill Version(s):\n\n1.0.0 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Skill: browser-cli Owner: zdstudios Summary: Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T03:43:10.107Z | user Initial public release of the browser-use CLI Skill. - Automate browser tasks from the command line: navigation, form filling, screenshot","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":936,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:42:28.504Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:42:28.504Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-12T20:15:40.118Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}