Chrome DevTools CLI for agents: drive the browser from the terminal
Script browser automation via the chrome-devtools CLI — snapshot and inspect pages, click/fill/type, navigate, emulate devices, record performance traces, inspect network and console
- What
- Script browser automation via the chrome-devtools CLI — snapshot and inspect pages, click/fill/type, navigate, emulate devices, record performance traces, inspect network and console
- Cost
- Free
- Needs
- the chrome-devtools CLI installed (one-time setup — see the repo's references/installation.md) and a Chromium-based browser it can control
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @chromedevtools's skill for the chrome-devtools-mcp CLI: write shell scripts or run shell commands to automate Chrome from your terminal. The AI workflow is Execute → Inspect → Act: list and select pages, take accessibility-tree snapshots to get element UIDs, then click, fill, type, press keys, drag, hover, handle dialogs and upload files; navigate pages, create tabs, reload, emulate network conditions, CPU throttling, geolocation, color scheme, viewport and user agent; record performance traces with insights, capture and compare heap snapshots (memory-debugging flag), list and fetch network requests and console messages, evaluate JavaScript, run Lighthouse audits, take screenshots (viewport, full-page or element), manage extensions, and install/launch PWAs. Output is Markdown-like text by default (JSON with a flag). Honest caveats: the one-time installation is a prerequisite, covered in the repo's references/installation.md — not part of the AI workflow; note the CLI defaults to full filesystem access (--allowUnrestrictedPaths=true) — pass false deliberately to sandbox it to the OS temp directory. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: the chrome-devtools CLI installed (one-time setup — see the repo's references/installation.md) and a Chromium-based browser it can control Install "Chrome DevTools CLI for agents: drive the browser from the terminal" for me. It teaches my agent @chromedevtools's CLI workflow for driving Chrome from the shell: list/select pages, snapshot the accessibility tree to get element UIDs, click/fill/type/press keys, navigate and create tabs, emulate network/CPU/geolocation/user-agent, record performance traces, capture and compare heap snapshots, inspect network requests and console messages, evaluate JavaScript, run Lighthouse audits, take screenshots, manage extensions and PWAs. Apache-2.0 licensed. Repository: https://github.com/chromedevtools/chrome-devtools-mcp/blob/main/skills/chrome-devtools-cli/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "chrome-devtools-cli". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the CLI per references/installation.md if not done; decide whether to keep full filesystem access or pass --allowUnrestrictedPaths=false). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.