Index of every page on this site: llms.txt
All skills
Run it yourself

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).

Use this Skill: https://skilld.dev/gh/chromedevtools/chrome-devtools-mcp/chrome-devtools

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈73 tokens for metadata: the name and description. ≈1.1k when used: this file.

Description uses 3.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈293 characters, or 3.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Core Concepts

Browser lifecycle: Browser starts automatically on first tool call using a persistent Chrome profile. Configure via CLI args in the MCP server configuration: npx chrome-devtools-mcp@latest --help. Additional tooling can be enabled by providing the following flags:

  • For extension tooling, use the --categoryExtensions flag.
  • For memory tooling, use the --memoryDebugging flag.

Page targeting: Page-scoped tools require a pageId parameter to target a specific page. Use list_pages to see available pages and their IDs (e.g. pageId: 1), or use the ID returned when creating a page with new_page. Note: For evaluate_script, pageId is required when targeting pages. However, when --categoryExtensions is enabled, pageId is optional so you can pass serviceWorkerId instead to evaluate inside an extension background service worker. Element interaction: Use take_snapshot to get page structure with element uids. Each element has a unique uid for interaction. If an element isn't found, take a fresh snapshot - the element may have been removed or the page changed.

Workflow Patterns

Before interacting with a page

  1. Navigate: navigate_page or new_page
  2. Wait: wait_for to ensure content is loaded if you know what you look for.
  3. Snapshot: take_snapshot with pageId to understand page structure
  4. Interact: Use element uids from snapshot for click, fill, etc., passing the corresponding pageId.

Efficient data retrieval

  • Use filePath parameter for large outputs (screenshots, snapshots, traces)
  • Use pagination (pageIdx, pageSize) and filtering (types) to minimize data
  • Set includeSnapshot: false on input actions unless you need updated page state

Tool selection

  • Network mocks: mock_network and remove_network_mock require --categoryNetworkMocks at server startup.
  • Automation/interaction: take_snapshot (text-based, faster, better for automation)
  • Visual inspection: take_screenshot (when user needs to see visual state)
  • CSS & Styling inspection: Use get_css_styles to inspect computed styles, matched rules, cascade, and CSS variables (pass computedProperties for unmatched defaults). Treat the output as authoritative.
  • Additional details: Use evaluate_script for runtime DOM/JS data not available via get_css_styles or take_snapshot.
  • Runtime values: Use set_logpoints to log expressions at script or source-file lines (source maps supported) instead of editing code; read the output with list_console_messages.

Parallel execution

You can send multiple tool calls in parallel, but maintain correct order: navigate → wait → snapshot → interact.

Testing an extension

Before proceeding: Extension tools (install_extension, list_extensions, etc.) are only available when the MCP server is started with the --categoryExtensions flag. If these tools are not in your tool list, stop and ask the user to update their MCP server configuration:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["chrome-devtools-mcp@latest", "--categoryExtensions"]
    }
  }
}

After updating, the user must restart the MCP server (or their AI client) for the change to take effect.

  1. Install: Use install_extension with the path to the unpacked extension.
  2. Identify: Get the extension ID from the response or by calling list_extensions.
  3. Trigger Action: Use trigger_extension_action to open the popup or side panel if applicable.
  4. Verify Service Worker: Use evaluate_script with serviceWorkerId (omitting pageId and args) to check extension state or trigger background actions. When evaluating in a page, pass pageId (omitting serviceWorkerId).
  5. Verify Page Behavior: Navigate to a page where the extension operates and use take_snapshot to check if content scripts injected elements or modified the page correctly.

Troubleshooting

If chrome-devtools-mcp is insufficient, guide users to use Chrome DevTools UI:

If there are errors launching chrome-devtools-mcp or Chrome, refer to https://github.com/ChromeDevTools/chrome-devtools-mcp/blob/main/docs/troubleshooting.md.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warningstoday5 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    This skill integrates Chrome DevTools into the agent workflow for browser automation and debugging. It uses an official MCP server from the Chrome DevTools team. No security issues were detected.

  • Sockettoday

    No alerts

  • Snyk1d

    Risk: MEDIUM · 1 issue

  • Runlayer9mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at bdecb63. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago

README badge

README badge for chromedevtools/chrome-devtools-mcp/chrome-devtools

Provides Chrome DevTools access via Claude's MCP protocol for debugging, browser automation, and performance analysis. Includes tools for page navigation, element interaction via snapshots, network inspection, and optional extension testing when configured with the --categoryExtensions flag.

Generated from the current SKILL.md.

Does this skill work with headless Chrome?
Yes. The skill uses Chrome DevTools via MCP and starts a persistent Chrome browser automatically on first tool call. The browser lifecycle is managed through CLI configuration flags.
How do I enable extension testing tools?
Extension tools are only available when the MCP server is started with the `--categoryExtensions` flag in your MCP configuration. After updating the config, restart your MCP server or AI client for the change to take effect.
What's the difference between take_snapshot and take_screenshot?
take_snapshot returns text-based page structure with element UIDs, making it faster and better for automation. take_screenshot captures the visual state when you need to see what the page looks like.
Can I use this skill in slim mode?
No. This skill does not apply to `--slim` mode MCP configuration.
How do I interact with elements on a page?
First call take_snapshot to get the page structure and element UIDs, then use those UIDs with tools like click or fill to interact with elements.

Generated from the current SKILL.md. These answers refresh after source changes.