agentleFS
Sign inStart free
appautomatonappautomaton/webmaton/skills/chrome-devtools-cli/SKILL.md

chrome-devtools-cli

Skill20 starsChanged 3 months agoMITView on GitHub

Use when a task needs Chrome DevTools from the shell: automate a live Chrome browser with `chrome-devtools`, inspect accessibility snapshots and UIDs, click/fill/navigate pages, evaluate JavaScript, inspect console and network activity, take screenshots, run Lighthouse, capture performance traces, or connect to an existing debuggable Chrome. This is CLI mode, not MCP client setup.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use a11y-debugging.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ChromeDevToolsSkill

    a11y-debugging

    Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always act on uids from the latest snapshot.

    line 23
  2. Distinctive:

    Run tools directly; the background daemon starts implicitly on first real action and preserves browser state.

    line 27
  3. Very specific:

    Do not run start, status, or stop before every action.

    line 28
  4. Very specific:

    Use chrome-devtools <command> --help for exact syntax.

    line 30
  5. Distinctive:

    Prefer snapshots over screenshots for deciding what to click or fill.

    line 32
  6. Very specific:

    Use evaluate_script, console, and network commands when debugging runtime behavior.

    line 33
  7. Very specific:

    If this is the first time using the CLI or chrome-devtools is missing, read references/installation.md.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

chrome-devtools-cli

The package is chrome-devtools-mcp, but the action CLI is chrome-devtools. Use chrome-devtools <tool> ... for this skill. Do not use npx chrome-devtools-mcp@latest unless you are configuring an MCP server outside this skill.

Core Workflow

chrome-devtools new_page "https://example.com"
chrome-devtools list_pages
chrome-devtools take_snapshot 0
chrome-devtools click 0 "1_3"
chrome-devtools fill 0 "1_5" "search text"
chrome-devtools press_key 0 "Enter"

Two identifiers drive everything. The page id is the first positional argument of nearly every command — read it from list_pages. The element uid comes from take_snapshot, which returns accessibility-tree entries such as 1_3.

Always act on uids from the latest snapshot. Re-snapshot after navigation, reloads, or major DOM updates.

Operating Rules

  • Run tools directly; the background daemon starts implicitly on first real action and preserves browser state.
  • Do not run start, status, or stop before every action. Use them only for setup, custom launch flags, or troubleshooting.
  • Pass the page id as the first positional argument. list_pages and new_page are the exceptions that take none, and evaluate_script takes --pageId as a flag instead.
  • Use chrome-devtools <command> --help for exact syntax; this file tracks 1.8.0 and the command surface moves between minor releases. Output defaults to Markdown; add --output-format=json when structured output is useful.
  • This CLI drives its own chrome-devtools-mcp daemon. If the surrounding agent already has an MCP client connected to that same server, prefer one path or the other rather than mixing them in one session.
  • Prefer snapshots over screenshots for deciding what to click or fill. Use screenshots for visual proof, layout inspection, or reports.
  • Use evaluate_script, console, and network commands when debugging runtime behavior; use Lighthouse and performance tracing for page-quality/performance work.

Common Tasks

chrome-devtools list_pages
chrome-devtools navigate_page 0 --url "https://example.com"
chrome-devtools navigate_page 0 --type "reload" --ignoreCache
chrome-devtools evaluate_script "() => document.title" --pageId 0
chrome-devtools list_console_messages 0 --types error
chrome-devtools list_network_requests 0 --pageSize 50
chrome-devtools take_screenshot 0 --filePath page.png
chrome-devtools lighthouse_audit 0 --mode "navigation"
chrome-devtools performance_start_trace 0 --reload --filePath trace.json.gz
chrome-devtools performance_stop_trace 0

For a broader command map, read references/cli-reference.md.

Setup

If this is the first time using the CLI or chrome-devtools is missing, read references/installation.md. Installation is a one-time prerequisite, not part of the regular workflow.

References

  • references/cli-reference.md — command groups, daemon behavior, output modes, and troubleshooting commands
  • references/installation.md — global install and PATH troubleshooting

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free