Agent skill

Surf

by w-winter in w-winter/dot314

Control Chrome browser via CLI for testing, automation, and debugging.

MITAuto-check: warningsProductivity & Automation

Install Surf

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add w-winter/dot314 --skill surf -a claude-code

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

GitHub CLI
$ gh skill install w-winter/dot314 surf --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/w-winter/dot314.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/surf .claude/skills/surf && 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
surf
GitHub stars
139
Used in
1 other repo
Token cost
~7.6k tokens
SKILL.md length
1,745 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Control Chrome browser via CLI for testing, automation, and debugging.

  • Works in 4 steps: Not logged in: The error "login… → Model selection failed: The UI may have… → Response timeout: Reasoning-heavy models… → …
  • The user needs browser automation
  • SKILL.md covers Native Host / Socket Notes, Remote Surf, CLI Quick Reference and Core Workflow, plus 16 more sections
  • Reaches youtube.com and google.com

What it does

Surf is an agent skill from w-winter/dot314. Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.

Its SKILL.md is about 7.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Productivity & Automation, covering Browser automation, Web search and Forms and invoices. It works with OpenAI, Perplexity and Linux. The licence is MIT.

When your agent uses it

  • The user needs browser automation
  • Page inspection
  • Network/CPU emulation
  • DevTools streaming

Example prompts

  • “/surf”

Workflow steps

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

  1. Not logged in: The error "login required" means you need to log into the service in Chrome (chatgpt.com, gemini.google.com, perplexity.ai…
  2. Model selection failed: The UI may have changed. Run surf grok --validate to check
  3. Response timeout: Reasoning-heavy models (ChatGPT o1, Grok Expert) can take 45+ seconds. AI Studio builds can take several minutes.
  4. Element not found: The service's UI changed. Check for surf-cli updates

What it can do on your machine

Read from SKILL.md and the folder at commit 0c6bbc7. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • youtube.com
    • google.com
    • other.com

    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

Surf loads about 7.6k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 1,745 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~7.6k

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: warnings

The automated check found patterns that need a careful read before installing.

  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:109
    es matching `.env*`, `*.pem`, `*.key`, `id_rsa*`, `id_ed25519*`, `*.p12`, `*.pfx`, `credentials*`, or `secrets*`. Use `-

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 w-winter/dot314 at commit 0c6bbc7, republished under its MIT licence (© w-winter). 1,745 words, ~7,554 tokens.

Download SKILL.mdSave it as .claude/skills/surf/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
surf
description
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
disable-model-invocation
true

Surf Browser Automation

Control Chrome browser via CLI or Unix socket.

Native Host / Socket Notes

For WSL2 with Windows Chrome, run surf install <extension-id> inside WSL2. Surf detects WSL2 and writes the Windows-side native messaging manifest plus a wrapper that launches the WSL host. Use surf install <extension-id> --target linux only for Linux browsers running inside WSLg.

On macOS, Chrome reads the native messaging manifest at ~/Library/Application Support/Google/Chrome/NativeMessagingHosts/surf.browser.host.json. If native messaging fails, confirm that file exists, its allowed_origins extension ID matches chrome://extensions, then rerun surf install <extension-id>, restart Chrome, reload the extension, and inspect the extension service-worker console.

If a command reports Socket connect failed, run surf doctor first, then check the Attempted socket: line. Default sockets are /tmp/surf.sock on macOS/Linux/WSL2 and //./pipe/surf on Windows. If SURF_SOCKET is set, the browser-launched host and the shell running surf must use the same value.

Remote Surf

Remote clients require a per-client credential; Tailnet reachability alone is not authorization. On the POSIX browser host, authorize the client before installing the listener:

bash
surf remote authorize agent-macbook --output ~/agent-macbook.surf-credential.json
surf install <extension-id> --listen 100.101.102.103:4321
surf remote list

Move the mode-0600 credential to the client through a secure channel. It grants full trusted Surf authority. Use it explicitly or through SURF_REMOTE and SURF_REMOTE_CREDENTIAL:

bash
surf --remote 100.101.102.103:4321 \
  --remote-credential ~/.config/surf/agent-macbook.json \
  page.read

surf remote revoke agent-macbook  # Run on the browser host

Remote paths are client-local by default. local:./file is explicit client-local syntax; only remote:/absolute/path accesses the browser host directly. Remote transfer supports one upload or ChatGPT/Gemini input and one screenshot, network-export, or Gemini image output. Limits are 256 MiB per file, 512 MiB and 32 files per connection, and 256 KiB decoded chunks. record, aistudio.build, smoke screenshot directories, directories, and multi-file inputs are not supported remotely. Successful action screenshots and failure --auto-capture diagnostics are transferred back to client-local paths.

CLI Quick Reference

bash
surf --help                    # Full help
surf <group>                   # Group help (tab, scroll, page, wait, dialog, emulate, form, perf, ai)
surf --help-full               # All commands
surf --find <term>             # Search tools
surf --help-topic <topic>      # Topic guide (refs, semantic, frames, devices, windows)

Core Workflow

bash
# 1. Navigate to page
surf navigate "https://example.com"

# 2. Read page to get element refs
surf page.read

# 3. Click by ref or coordinates
surf click --ref "e1"
surf click --x 100 --y 200

# 4. Type text
surf type --text "hello"

# 5. Full-page screenshot
surf screenshot --full-page --output /tmp/shot.png

# Inspect animation/style changes as JSON
surf animate-audit --selector ".thing" --duration 2000 --fps 10

AI Assistants (No API Keys)

Query AI models using your browser's logged-in session. Must be logged into the respective service in Chrome.

ChatGPT
bash
surf chatgpt "explain this code"
surf chatgpt "summarize" --with-page              # Include current page context
surf chatgpt "review" --model gpt-5.5             # Specify model
surf chatgpt "analyze" --file document.pdf        # With file attachment
Oracle

Use surf chatgpt for quick one-shot questions. Use surf oracle for long-running or Pro coding consults that need a durable job, explicit model and effort selection, file context, recovery, or follow-up turns. Oracle is local-only.

For agent workflows, detach after dispatch and keep the returned .id:

bash
surf oracle ask "Review this change and identify release risks" \
  --files "src/**/*.ts" --files "package.json" \
  --model gpt-5.5 --effort pro --detach --json

surf oracle status <job-id> --json
surf oracle result <job-id> --json
# Or let Surf keep polling until capture:
surf oracle result <job-id> --wait --json

status reads persisted state without touching Chrome. result attempts to harvest the answer and returns the job object with response once its state is captured. A Ctrl-C during waiting exits with status 130 and prints Recover with: surf oracle result <id>. Once the job is awaiting, the persisted ChatGPT conversation URL is its durable key, so surf oracle result <id> can recover after CLI exit, native-host restart, or Chrome restart by reopening that conversation.

Treat Pro quota as scarce. Oracle never selects Pro implicitly; request it with --model pro or --effort pro. ChatGPT model aliases include instant, thinking, pro, gpt-5.5, and gpt-5.6-sol. Accepted --effort values are light, standard, extended, heavy, and pro. Requested model and effort selections are read back before submission, and an unverifiable selection fails with model_verification_failed instead of silently continuing. Capacity is one non-terminal oracle job. A capacity error includes the in-flight job ID; poll that job or wait for it to finish rather than submitting the same consult again.

When loaded as a Pi extension, Surf also registers a surf-oracle external-job provider when the runtime exposes that bridge. The provider maps start, status, result, reattach, and follow to durable Surf Oracle jobs. It returns the conversation URL, requested and verified model and effort, prompt digest, result text, and failure details. reattach only harvests an existing job by ID; it never submits the prompt again.

Context comes from repeatable --files globs. Surf fails closed when a glob matches nothing or a matched file is unreadable, binary, or invalid UTF-8. It also blocks gitignored files and basenames matching .env*, *.pem, *.key, id_rsa*, id_ed25519*, *.p12, *.pfx, credentials*, or secrets*. Use --allow-sensitive only after intentionally reviewing those files; it overrides the block rather than redacting content. Context up to 60,000 evidence characters is inserted inline, while larger context becomes one private text attachment. The assembly manifest records each path, byte count, SHA-256, inline or bundle disposition, and deny-list outcome.

Continue a captured consult with follow. Use the ID returned by each turn for the next turn:

bash
surf oracle follow <job-id> "Challenge your recommendation. What could invalidate it?" --detach --json
surf oracle result <follow-job-id> --wait --json
surf oracle follow <follow-job-id> "Give the final decision and concrete next steps." --detach --json
Gemini
bash
surf gemini "explain quantum computing"
surf gemini "summarize" --with-page               # Include page context
surf gemini "analyze" --file data.csv             # Attach file
surf gemini "a robot surfing" --generate-image /tmp/robot.png
surf gemini "add sunglasses" --edit-image photo.jpg --output out.jpg
surf gemini "summarize" --youtube "https://youtube.com/..."
surf gemini "hello" --model gemini-3.5-flash      # Models: gemini-3.1-pro (default), gemini-3.5-flash, gemini-3.1-flash-lite
surf gemini "wide banner" --generate-image /tmp/banner.png --aspect-ratio 16:9
Perplexity
bash
surf perplexity "what is quantum computing"
surf perplexity "explain this page" --with-page   # Include page context
surf perplexity "deep dive" --mode research       # Research mode (Pro)
surf perplexity "latest news" --model sonar       # Model selection (Pro)
Grok (via x.com - requires X.com login in Chrome)
bash
surf grok "what are the latest AI trends on X"    # Search X posts
surf grok "analyze @username recent activity"     # Profile analysis  
surf grok "summarize this page" --with-page       # Include page context
surf grok "find viral AI posts" --deep-search     # DeepSearch mode
surf grok "quick question" --model fast           # Models: auto, fast, expert, grok-4.20-beta

For exhaustive, multi-angle X research with categorized findings and full post-URL traceability, use the deep-x-research skill (skills/deep-x-research/) instead of a single Grok query.

Grok Validation & Troubleshooting:

bash
# Validate Grok UI and check available models (no query sent)
surf grok --validate

# If models changed, save discovered models to surf.json config
surf grok --validate --save-models
AI Studio (via aistudio.google.com - requires Google login in Chrome)
bash
surf aistudio "explain quantum computing"
surf aistudio "redteam this" --with-page          # Include current page context
surf aistudio "quick answer" --model gemini-3-flash-preview  # Model selection
surf aistudio "analyze" --timeout 600             # Custom timeout (default: 300s)

Why AI Studio over Gemini? AI Studio gives access to less restricted Gemini models. For Gemini 3 Pro the difference can be significant with certain prompts. Downside: aggressive per-day rate limits on Pro and Flash models.

Model selection is best-effort: Pass any AI Studio model id (e.g. gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-flash-lite-latest). If the model isn't found, AI Studio uses whatever model was last selected in the UI.

AI Studio App Builder
bash
surf aistudio.build "build a portfolio site"
surf aistudio.build "todo app" --model gemini-3.1-pro-preview   # Model override
surf aistudio.build "crm dashboard" --output ./out              # Extract zip to directory
surf aistudio.build "game" --keep-open --timeout 600            # Keep tab open, 10min timeout

Automates AI Studio's App Builder at aistudio.google.com/apps. Types your prompt, clicks Build, waits for completion, downloads the generated zip, and optionally extracts it.

  • --output <dir> extracts the zip to a directory
  • --model <id> overrides the model in Advanced Settings
  • --timeout <seconds> build timeout (default: 600s)
  • --keep-open leaves the AI Studio tab open after completion

Returns zipPath, extractedPath, model, buildDuration, and tookMs.

AI Tool Troubleshooting

When AI queries fail, check these common issues:

  1. Not logged in: The error "login required" means you need to log into the service in Chrome (chatgpt.com, gemini.google.com, perplexity.ai, x.com, or aistudio.google.com)
  2. Model selection failed: The UI may have changed. Run surf grok --validate to check
  3. Response timeout: Reasoning-heavy models (ChatGPT o1, Grok Expert) can take 45+ seconds. AI Studio builds can take several minutes.
  4. Element not found: The service's UI changed. Check for surf-cli updates

Debugging workflow for agents:

bash
# 1. Check if the service is accessible and UI is valid
surf grok --validate

# 2. If models mismatch, update the local settings
surf grok --validate --save-models

# 3. Retry with explicit model name from validation output
surf grok "query" --model <model-from-validation>

# 4. If still failing, try with longer timeout
surf grok "query" --timeout 600

Tab Management

bash
surf tab.list
surf tab.new "https://google.com"
surf tab.switch 12345
surf tab.close 12345
surf tab.move 12345 --to-window 67890
surf tab.reload                # Reload current tab

# Named tabs (aliases)
surf tab.name myapp            # Name current tab
surf tab.switch myapp          # Switch by name
surf tab.named                 # List named tabs
surf tab.unname myapp          # Remove name

# Tab groups
surf tab.group                 # Create/add to tab group
surf tab.ungroup               # Remove from group
surf tab.groups                # List all tab groups

Window Management

bash
surf window.list                              # List all windows
surf resize 1280 720                         # Resize current browser window
surf resize 1280                             # Set current window width only
surf window.list --tabs                       # Include tab details
surf window.new                               # New window
surf window.new --url "https://example.com"   # New window with URL
surf window.new --incognito                   # New incognito window
surf window.new --unfocused                   # Don't focus new window
surf window.focus 12345                       # Focus window by ID
surf window.close 12345                       # Close window
surf window.resize --id 123 --width 1920 --height 1080
surf window.resize --id 123 --state maximized # States: normal, minimized, maximized, fullscreen

Multi-agent isolation:

bash
# Create a separate window for one agent and keep using its ID
surf window.new "https://example.com"
surf --window-id 123 tab.list
surf --window-id 123 go "https://other.com"

# Pin work to a specific tab, or name it for easier handoff
surf read --tab-id 456
surf tab.name agent-a --tab-id 456
surf tab.switch agent-a

Use window.new, --window-id, --tab-id, and named tabs to keep parallel agents on separate targets. Surf serializes non-streaming browser CLI requests per socket with a file-based lock, so agents sharing one native host wait instead of interleaving commands. Use --no-lock only for intentional bypasses. For hard isolation, run separate browser/profile instances with separate native hosts and SURF_SOCKET values; each socket gets its own lock. Surf does not yet have session.new, session IDs, or independent per-agent CDP sessions.

Input Methods

bash
# CDP method (real events) types at the current focus
surf type --text "hello"
surf click --x 100 --y 200

# Selector/ref targets use frame-aware DOM input
surf type "hello" --into "#input"
surf type "hello" --ref e5

# Keys
surf key Enter
surf key "cmd+a"
surf key.repeat --key Tab --count 5           # Repeat key presses

# Hover and drag
surf hover --ref e5
surf drag --from-x 100 --from-y 100 --to-x 200 --to-y 200

Page Inspection

bash
surf page.read                 # Accessibility tree with refs + page text
surf page.read --no-text       # Interactive elements only (no text content)
surf animate-audit --selector ".thing" --duration 2000 --fps 10  # JSON animation timeline
surf page.read --ref e5        # Get specific element details
surf page.read --depth 3       # Limit tree depth
surf page.read --compact       # Minimal output for LLM efficiency
surf page.read --max-bytes 2000 # Cap visible text at a UTF-8 byte boundary
surf page.text                 # Plain text content only
surf page.html --strip-scripts # Rendered HTML without scripts
surf page.save --selector "#artifact" --strip-scripts --output page.html # Save one static element
surf page.state                # Modals, loading state, scroll info
Show full SKILL.md (715 more words)Show less
Export Rendered HTML

Use page.html when the user wants a static copy of the current rendered DOM. This works for Claude artifact pages and ordinary web pages.

bash
# Save the active page as HTML.
surf page.save --output page.html

# Save a Claude artifact or other preview page after it loads, without scripts.
surf wait.dom --stable 500
surf page.html --selector "#artifact" --strip-scripts > artifact.html

Use --selector <css> to export its matching element only. A selector miss fails with an error. --strip-scripts removes scripts from exported markup without changing the page. Without --selector, page.html exports the whole document with its doctype. page.html exports the selected frame when frame.switch is active. Use page.read first when you need refs or visible text.

Semantic Element Location

Find and act on elements by role, text, or label instead of refs:

bash
# Find by ARIA role
surf locate.role button --name "Submit" --action click
surf locate.role textbox --name "Email" --action fill --value "test@example.com"
surf locate.role link --all                    # Return all matches

# Find by text content
surf locate.text "Sign In" --action click
surf locate.text "Accept" --exact --action click

# Find form field by label
surf locate.label "Username" --action fill --value "john"
surf locate.label "Password" --action fill --value "secret"

Actions: click, fill, hover, text (get text content)

bash
surf search "login"                    # Find text in page
surf search "Error" --case-sensitive   # Case-sensitive
surf search "button" --limit 5         # Limit results
surf find "login"                      # Alias for search

Element Inspection

bash
surf element.styles e5                 # Get computed styles by ref
surf element.styles ".card"            # Or by CSS selector
# Returns: font, color, background, border, padding, bounding box

Scrolling

bash
surf scroll down 800           # Scroll down 800px
surf scroll up 400             # Scroll up 400px
surf scroll bottom             # Scroll to bottom
surf scroll top                # Scroll to top
surf scroll.bottom             # Dot command form also works
surf scroll.top
surf scroll.to --ref e5        # Scroll element into view
surf scroll.info               # Get scroll position

Waiting

bash
surf wait 2                    # Wait 2 seconds
surf wait.element ".loaded"    # Wait for element
surf wait.network              # Wait for network idle
surf wait.url "/success"       # Wait for URL pattern
surf wait.dom --stable 100     # Wait for DOM stability
surf wait.load                 # Wait for page load complete

Dialog Handling

bash
surf dialog.info               # Get current dialog type/message
surf dialog.accept             # Accept (OK)
surf dialog.accept --text "response"  # Accept prompt with text
surf dialog.dismiss            # Dismiss (Cancel)

Device/Network Emulation

bash
# Network throttling
surf emulate.network slow-3g   # Presets: slow-3g, fast-3g, 4g, offline
surf emulate.network reset     # Disable throttling

# CPU throttling  
surf emulate.cpu 4             # 4x slower
surf emulate.cpu 1             # Reset

# Device emulation (19 presets)
surf emulate.device "iPhone 14"
surf emulate.device "Pixel 7"
surf emulate.device --list     # List available devices

# Custom viewport
surf emulate.viewport --width 1280 --height 720
surf emulate.touch --enable    # Enable touch emulation

# Geolocation
surf emulate.geo --lat 37.7749 --lon -122.4194
surf emulate.geo --clear

Form Automation

bash
surf page.read                 # Get element refs first

# Fill by ref
surf form.fill --data '[{"ref":"e1","value":"John"},{"ref":"e2","value":"john@example.com"}]'

# Checkboxes: true/false
surf form.fill --data '[{"ref":"e7","value":true}]'

# Dropdown selection
surf select e5 "Option A"                    # By value (default)
surf select e5 "Option A" "Option B"         # Multi-select
surf select e5 --by label "Display Text"     # By visible label
surf select e5 --by index 2                  # By index (0-based)

File Upload

bash
surf upload --ref e5 --files "/path/to/file.txt"
surf upload --ref e5 --files "/path/file1.txt,/path/file2.txt"

Iframe Handling

bash
surf frame.list                # List frames with IDs
surf frame.switch "FRAME_ID"   # Switch to iframe context
surf frame.main                # Return to main frame
surf frame.js --id "FRAME_ID" --code "return document.title"

# After frame.switch, subsequent commands target that frame:
surf frame.switch "iframe-1"
surf page.read                 # Reads iframe content
surf click e5                  # Clicks in iframe
surf frame.main                # Back to main page

Network Inspection

bash
surf network                   # List captured requests
surf network --stream          # Real-time network events
surf network.get --id "req-123"   # Full request details
surf network.body --id "req-123"  # Get response body
surf network.curl --id "req-123"  # Generate curl command
surf network.origins           # List origins with stats
surf network.stats             # Capture statistics
surf network -vv --body-mode text --per-body-bytes 65536
surf network.export --har --output ./trace.har
surf network.clear             # Clear captured requests

Response-body capture supports none, text, and all modes plus per-body and per-tab-session byte caps. HAR exports carry body completeness metadata. Persistent network state is private under ~/.surf/state/network/ by default; configure SURF_NETWORK_PATH in the native host environment to change it.

Console

bash
surf console                   # Get console messages
surf console --stream          # Real-time console
surf console --stream --level error  # Errors only

JavaScript Execution

bash
surf js "return document.title"
surf js "document.querySelector('.btn').click()"

Performance

bash
surf perf.metrics              # Current metrics snapshot
surf perf.start                # Start trace
surf perf.stop                 # Stop and get results

Screenshots

bash
surf screenshot                           # Auto-saves to /tmp/surf-snap-*.png
surf screenshot --output /tmp/shot.png    # Save to specific file
surf screenshot --selector ".card"        # Element only
surf screenshot --full-page               # Full page scroll capture
surf screenshot --full-page /tmp/full.png # Full page saved to path
surf screenshot --no-save                 # Return base64 only, don't save file

Zoom

bash
surf zoom                      # Get current zoom level
surf zoom 1.5                  # Set zoom to 150%
surf zoom 1                    # Reset to 100%

Cookies & Storage

bash
surf cookie list               # List cookies for current page
surf cookie list --domain .google.com
surf cookie set --name "token" --value "abc123"
surf cookie get "token"
surf cookie clear --all        # Clear all cookies
surf cookie delete "token"     # Clear one cookie

History & Bookmarks

bash
surf history --query "github" --max 20
surf bookmarks --query "docs"
surf bookmark.add --url "https://..." --title "My Bookmark"
surf bookmark.remove

Health Checks & Smoke Tests

bash
surf health --url "http://localhost:3000"
surf smoke --urls "http://localhost:3000" "http://localhost:3000/about"
surf smoke --urls "..." --screenshot /tmp/smoke

Workflows

Execute multi-step browser automation as a single command with smart auto-waits.

Inline Workflows
bash
# Pipe-separated commands
surf do 'go "https://example.com" | click e5 | screenshot'

# Multi-step login flow
surf do 'go "https://example.com/login" | type "user@example.com" --selector "#email" | type "pass" --selector "#password" | click --selector "button[type=submit]"'

# Validate without executing
surf do 'go "url" | click e5' --dry-run
Named Workflows

Save workflows as JSON files in ~/.surf/workflows/ (user) or ./.surf/workflows/ (project):

bash
# List available workflows
surf workflow.list

# Show workflow details
surf workflow.info my-workflow

# Run by name with arguments
surf do my-workflow --email "user@example.com" --password "secret"

# Validate workflow file
surf workflow.validate workflow.json
Workflow JSON Format
json
{
  "name": "Login Flow",
  "description": "Automate login process",
  "args": {
    "email": { "required": true },
    "password": { "required": true },
    "url": { "default": "https://example.com/login" }
  },
  "steps": [
    { "tool": "navigate", "args": { "url": "%{url}" } },
    { "tool": "type", "args": { "text": "%{email}", "selector": "input[name=email]" } },
    { "tool": "type", "args": { "text": "%{password}", "selector": "input[name=password]" } },
    { "tool": "click", "args": { "selector": "button[type=submit]" } },
    { "tool": "screenshot", "args": {}, "as": "result" }
  ]
}
Loops and Step Outputs
json
{
  "steps": [
    // Capture step output for later use
    { "tool": "js", "args": { "code": "return [1,2,3]" }, "as": "items" },
    
    // Fixed iterations
    { "repeat": 5, "steps": [
      { "tool": "click", "args": { "ref": "e5" } }
    ]},
    
    // Iterate over array
    { "each": "%{items}", "as": "item", "steps": [
      { "tool": "js", "args": { "code": "console.log('%{item}')" } }
    ]},
    
    // Repeat until condition
    { "repeat": 20, "until": { "tool": "js", "args": { "code": "return done" } }, "steps": [...] }
  ]
}
Workflow Options
bash
--file, -f <path>     # Load from JSON file
--dry-run             # Parse and validate without executing
--on-error stop|continue  # Error handling (default: stop)
--step-delay <ms>     # Delay between steps (default: 100, 0 to disable)
--no-auto-wait        # Disable automatic waits
--json                # Structured JSON output

Auto-waits: Commands automatically wait for completion:

  • Navigation (go, back, forward) → waits for page load
  • Clicks, key presses, form fills → waits for DOM stability
  • Tab switches → waits for tab to load

Why use do? Instead of 6-8 separate CLI calls with LLM orchestration between each, a workflow executes deterministically. Faster, cheaper, and more reliable.

Playbooks

Use surf do for a direct command sequence. Use a playbook for a reusable site capability with provenance, browser-session network execution, workflow fallback, and write-safety policy.

bash
surf playbook list
surf pb show page
surf pb ops page
surf use page read --json

Resolution order is project (./.surf/playbooks/), user (~/.surf/playbooks/), then built-in. Provider compatibility commands stay on their validated command paths until provider playbooks have real login-flow validation. A write op requires --write; Surf records semantic intent before dispatch so a timeout or concurrent retry cannot silently double-submit.

Author from redacted recent activity when it contains only read/navigation behavior, or use an explicit record for richer evidence:

bash
surf pb suggest --since 1h
surf pb save example --op read --from-recent 1h
surf pb record start example --op read --network --watch
surf pb record mark "loaded results"
surf pb record stop --draft
surf pb save --from-record <record-id>
surf pb trace export --from-record <record-id> --har ./trace.har
surf pb export example --out ./example-playbook
surf pb import ./example-playbook

Records, trace slices, receipts, and the bounded activity journal are private Surf state. Inputs and authentication headers are redacted by default. Use --include-input-values only when the saved values are necessary and acceptable.

Client projections replay a validated read endpoint and never embed captured browser credentials:

bash
surf pb client derive example --op read --from-record <record-id> --request-id <request-id> --out ./client
surf pb client export example --op read --out ./client
surf pb client verify ./client

Error Diagnostics

bash
# Auto-capture screenshot + console on failure
surf wait.element ".missing" --auto-capture --timeout 2000
# Saves to /tmp/surf-error-*.png

Common Options

bash
--tab-id <id>         # Target specific tab
--window-id <id>      # Target specific window
--json                # Raw JSON output  
--auto-capture        # Screenshot + console on error
--timeout <ms>        # Override default timeout

Tips

  1. First CDP operation is slow (~5-8s) - debugger attachment overhead, subsequent calls fast
  2. Use refs from page.read for reliable element targeting over CSS selectors
  3. JS method for contenteditable - Modern editors (ChatGPT, Claude, Notion) need --method js
  4. Named tabs for workflows - tab.name app then tab.switch app
  5. Auto-capture for debugging - --auto-capture saves diagnostics on failure
  6. AI tools use browser session - Must be logged into the service (ChatGPT, Gemini, Perplexity, Grok, AI Studio), no API keys needed
  7. Grok validation - Run surf grok --validate if queries fail to check UI changes
  8. Long timeouts for reasoning-heavy models - ChatGPT o1 and Grok Expert can take 60+ seconds. AI Studio builds default to 600s.
  9. AI Studio for unrestricted Gemini - surf aistudio gives less filtered responses than surf gemini for the same models
  10. Use surf do for multi-step tasks - Reduces token overhead and improves reliability
  11. Dry-run workflows first - surf do '...' --dry-run validates without executing
  12. Window isolation - Use window.new + --window-id or --tab-id to keep agent work separate from your browsing
  13. Request lock - Non-streaming browser CLI requests serialize per socket; use --no-lock only when you intentionally want to bypass it
  14. Native host diagnostics - If commands fail with socket/native-host errors, run surf doctor or surf doctor --browser all before guessing at reinstall steps
  15. HTML export - Use surf page.html > artifact.html to save Claude artifacts or any rendered page as static HTML
  16. Animation capture - Use surf record --duration 2000 --fps 10 --output /tmp/anim.gif when the agent needs to see motion; use animate-audit for numeric timelines and perf-audit for jank/layout-shift snapshots
  17. Hard isolation - Use separate browser/profile instances plus separate SURF_SOCKET values when agents must not share a host or target
  18. Semantic locators - locate.role, locate.text, locate.label for more robust element finding
  19. Frame context - Use frame.switch before interacting with iframe content

Socket API

For programmatic access:

bash
echo '{"type":"tool_request","method":"execute_tool","params":{"tool":"tab.list","args":{}},"id":"1"}' | nc -U /tmp/surf.sock

© w-winter, MIT. 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 1 other file in skills/surf of w-winter/dot314.

  • SKILL.md
  • LICENSE

Open the folder on GitHubat commit 0c6bbc7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in w-winter/dot314, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Surf 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.

Surf compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Surf this skillw-winter/dot3141391 repos~7.6kAutomated safety check: WarnMIT
Council Executionhex/claude-council848—~824Automated safety check: PassMIT
Scrapingbee CLIScrapingBee/scrapingbee-cli108—~3.2kAutomated safety check: NotesMIT
Conversation Archivegarrytan/gbrain31k—~5.6kAutomated safety check: PassMIT
Browse Nownowledge-co/community185—~619Automated safety check: PassNone
Browser NavigationFactory-AI/factory-plugins110—~2.7kAutomated safety check: PassNone

Similar skills

  • Council Execution

    hex/claude-council

    Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of…

    848 GitHub stars~824 tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Scrapingbee CLI

    ScrapingBee/scrapingbee-cli

    Fetch and read any web page, search the web, crawl a site, or pull structured data out of pages.

    108 GitHub stars~3.2k tokensUpdated today
    Productivity & AutomationAuto-check: notes
  • Conversation Archive

    garrytan/gbrain

    Import AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the…

    31k GitHub stars~5.6k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Browse Now

    nowledge-co/community

    Control the user's actual browser through the browse-now CLI when a task needs authenticated pages, dynamic interaction, form filling, screenshots, or other browser automation that web search cannot…

    185 GitHub stars~619 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Browser Navigation

    Factory-AI/factory-plugins

    Automate browser interactions for web testing, form filling, screenshots, and data extraction.

    110 GitHub stars~2.7k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Geo Content Research

    onvoyage-ai/gtm-engineer-skills

    Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the…

    1.3k GitHub stars~6.8k tokensUpdated 4 mo ago
    Marketing & SEOAuto-check passed

More from w-winter/dot314

  • Refresh RepoPrompt tool guidance when the CLI/MCP surface changes.

    139 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Deep X Research

    w-winter/dot314

    Deep, exhaustive research on a topic across X (Twitter) by driving Grok (x.com/i/grok) through surf.

    139 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Text Search

    w-winter/dot314

    Search indexed text corpora with qmd. An agent skill from w-winter/dot314.

    139 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Prose Review

    w-winter/dot314

    Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing…

    139 GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • Rp

    w-winter/dot314

    Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace.

    139 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Xcodebuildmcp

    w-winter/dot314

    Build/test Xcode projects via the XcodeBuildMCP MCP server using a local CLI wrapper for pi (no MCP support).

    139 GitHub stars~196 tokensUpdated today
    Auto-check passed

Questions about Surf

What does Surf do?

Control Chrome browser via CLI for testing, automation, and debugging. Surf is an agent skill from w-winter/dot314. Control Chrome browser via CLI for testing, automation, and debugging.

When should I use Surf?

Surf fits situations like: the user needs browser automation; page inspection; network/CPU emulation; devTools streaming.

How do I install Surf in Claude Code?

Run `npx skills add w-winter/dot314 --skill surf -a claude-code`. Or copy the skill folder (skills/surf in w-winter/dot314) into .claude/skills/surf in your project. Claude Code loads it when a task matches its description.

How do I install Surf in Codex?

Run `npx skills add w-winter/dot314 --skill surf -a codex`. Or copy the skill folder (skills/surf in w-winter/dot314) into .agents/skills/surf in your project. Codex loads it when a task matches its description.

Can I use Surf 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 w-winter/dot314 --skill surf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/surf, .gemini/skills/surf, .github/skills/surf and .opencode/skills/surf in your project.

What does Surf need to run?

SKILL.md names no scripts, command-line tools or credentials: Surf is instructions for the agent only.

Does Surf access the network?

SKILL.md names 3 domains. In commands or code: youtube.com, google.com and other.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Surf safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Surf use?

Surf is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Surf use?

About 7.6k tokens (SKILL.md is roughly 30k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Surf?

Skills that share tags, products or a category with Surf: Council Execution (hex/claude-council, 848 stars), Scrapingbee CLI (ScrapingBee/scrapingbee-cli, 108 stars), Conversation Archive (garrytan/gbrain, 31k stars) and Browse Now (nowledge-co/community, 185 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Surf?

w-winter (a GitHub user) maintains it in w-winter/dot314, which has 139 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: w-winter/dot314 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.