browser-automation

Browser Automation Skill

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "browser-automation" with this command: npx skills add ken-cavanagh-glean/fieldkit/ken-cavanagh-glean-fieldkit-browser-automation

Browser Automation Skill

Guidance for effective browser automation in Claude Code. Complements the dev-browser plugin.

Prerequisites

This skill provides guidance for using browser automation. Requires the dev-browser plugin to be installed:

/plugin marketplace add sawyerhood/dev-browser /plugin install dev-browser@sawyerhood/dev-browser

When to Use Browser Automation

Good use cases:

  • Testing local development (localhost, staging)

  • Verifying UI changes after code modifications

  • Debugging visual issues or user flows

  • Extracting data from web pages

  • Automating repetitive browser tasks

Poor use cases:

  • Tasks that require authenticated sessions you can't access

  • High-frequency scraping (use APIs instead)

  • Actions on production systems without explicit approval

Core Patterns

  1. Persistent Page Sessions

Dev-browser maintains page state across interactions. Use this for multi-step workflows:

  1. Navigate once to the page

  2. Inspect → identify elements

  3. Interact → click, type, verify

  4. Don't reload unless necessary

  5. LLM-Friendly DOM Inspection

Use DOM snapshots over screenshots when possible:

  • Snapshots are structured and searchable

  • Screenshots require visual interpretation

  • Combine both for complex debugging

Pattern:

snapshot → identify element refs → interact with refs

  1. Step-by-Step for Exploration

When exploring unknown pages:

  1. Take snapshot to understand structure

  2. Identify interactive elements

  3. Take one action

  4. Verify result with new snapshot

  5. Repeat

  6. Full Scripts for Known Flows

When you know the exact flow:

  1. Write complete interaction sequence
  2. Execute in one script
  3. Verify final state

Common Operations

Navigation

  • browser_navigate

  • Go to URL

  • browser_navigate_back

  • Go back

  • browser_snapshot

  • Get page structure (preferred)

  • browser_take_screenshot

  • Visual capture

Interaction

  • browser_click

  • Click element by ref

  • browser_type

  • Type into element

  • browser_fill_form

  • Fill multiple fields

  • browser_select_option

  • Select from dropdown

  • browser_press_key

  • Keyboard input

Waiting

  • browser_wait_for

  • Wait for text/element/time

  • Always wait after navigation or actions that trigger loading

Debugging

  • browser_console_messages

  • Check for errors

  • browser_network_requests

  • Inspect API calls

Best Practices

  1. Reference-Based Interaction

Always use element refs from snapshots, not CSS selectors:

snapshot → find ref="btn-42" → click ref="btn-42"

  1. Explicit Waits

After actions that cause page changes:

click → wait_for text="Success" → continue

  1. Error Recovery

If an action fails:

  • Take new snapshot

  • Verify page state

  • Adjust approach

  1. Form Filling

Use browser_fill_form for multiple fields:

fill_form([ {name: "email", type: "textbox", ref: "...", value: "..."}, {name: "password", type: "textbox", ref: "...", value: "..."} ])

  1. Verification Pattern

After completing a flow:

  1. Take final snapshot or screenshot
  2. Verify expected elements present
  3. Check console for errors
  4. Report success/failure with evidence

Integration with Glean Workflows

Testing Agent-Generated Content

  • Build agent in Glean

  • Navigate to Glean in browser

  • Test agent responses

  • Verify output format and accuracy

Verifying Customer Deployments

  • Navigate to customer's Glean instance (if accessible)

  • Test specific agent or search functionality

  • Document results with screenshots

Local Development Testing

  • Start local dev server

  • Navigate to localhost

  • Test changes iteratively

  • Verify before committing

Example Workflow

Testing a login flow:

  1. browser_navigate("http://localhost:3000/login")
  2. browser_snapshot() → identify form elements
  3. browser_fill_form([ {name: "email", ref: "input-1", value: "test@example.com"}, {name: "password", ref: "input-2", value: "testpass"} ])
  4. browser_click(ref: "submit-btn")
  5. browser_wait_for(text: "Dashboard")
  6. browser_snapshot() → verify logged in state
  7. Report: "Login successful - dashboard loaded"

Skill version: 1.0.0 Requires: dev-browser plugin -- Axon | 2026-01-01

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

ZeeLin Twitter/X 运营

ZeeLin 推特运营 — 蓝V互关(认证关注者回关)、回关新粉丝、写深度有趣评论、在需要涨粉的推文下自主打招呼以增加曝光与涨粉。用户自行登录 X 网页版,Agent 负责在账号 https://x.com/Gsdata5566 下执行蓝V互关/回关/评论/涨粉互动。Keywords: Zeelin, ZeeLi...

Registry SourceRecently Updated
2631Profile unavailable
Automation

AutoClaw Browser Automation

Complete browser automation skill with MCP protocol support and Chrome extension

Registry SourceRecently Updated
3640Profile unavailable
Automation

CamoFox MCP

Anti-detection browser automation MCP skill for OpenClaw agents with 41 tools for navigation, interaction, extraction, downloads, profiles, sessions, and ste...

Registry SourceRecently Updated
3190Profile unavailable
Automation

Mercado Público ChileCompra

Operate and assist across Chile's Mercado Público / ChileCompra supplier workflows using both the public API and the private supplier portal. Use when search...

Registry SourceRecently Updated
491Profile unavailable