dev-browser
Drive the user's dedicated Chrome AI window with the dev-browser CLI to open sites, click, fill forms, read pages, take screenshots and check a live app while signed in. Use when the user says browse, open a site, click, fill a form, screenshot, scrape, test my site, or check som
Install
npx skills add https://github.com/Melvynx/ai-maxxing-skills/tree/main/skills/dev-browser
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install melvynx-ai-maxxing-skills@llmmart
git clone https://github.com/Melvynx/ai-maxxing-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole melvynx/ai-maxxing-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Do every browser task in Chrome AI, the user's dedicated Chrome window (profile ~/.chrome-ai-profile, port 9333) where they are already signed in to their tools. Start it first (it does nothing if it is already open), then connect to it on every run:
If you got this skill from a link instead of a local folder, install nothing else from the repo: download a file it links only when a step needs it, with curl -fsSL https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/dev-browser/<path> -o <scratch>/<file> (for example references/api-reference.md), and read another skill it names only when you reach it, from https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/<skill-name>/SKILL.md.
chrome-ai start
dev-browser --connect http://127.0.0.1:9333 <<'JS'
const page = await browser.getPage("stripe-sales");
await page.goto("https://dashboard.stripe.com");
console.log(JSON.stringify({ title: await page.title(), url: page.url() }));
JS
If chrome-ai or dev-browser is missing, stop and tell the user to run /setup-dev-browser; never fall back to a standalone Playwright script or the user's own Chrome. If CHROME_AI_PORT is set, connect to that port instead of 9333 (chrome-ai url prints the address).
- Give each task its own page name (
browser.getPage("lumail-campaign")) so parallel agents never share a tab, reuse that name across runs to keep the page state, and close it withbrowser.closePage(name)when the task is done. Never close or navigate a tab you did not open. - Write small scripts that do one thing and end by logging the state as JSON (url, title, what you found). Scripts run in a sandbox, not Node: no
require,fs,fetchorprocess. - Before clicking, read the page with
await page.snapshotForAI()and target elements withpage.getByRole,getByTextorgetByLabel. Open references/api-reference.md before using a method you are not sure exists. - Files only go to
~/.dev-browser/tmp/: pass a bare file name tosaveScreenshotorwriteFileand use the path it returns. Look at the screenshot before saying a page looks right. - If a site asks to sign in, stop and ask the user to sign in in the Chrome AI window, then continue; the session stays saved. Never type passwords, codes or card numbers, and never solve a captcha.
- Ask the user before any click that sends, publishes, pays, deletes or accepts terms.
- For a clean signed-out check (how a visitor sees the site), run without
--connectand with--headless, and say so. - When a script fails, the page stays where it was: reconnect, take a screenshot, log the url and title, then continue from there.
Reply with what you saw or did, the final URL, and the screenshot path when it helps.
Files (ai-maxxing-skills)
-
references
-
api-reference.md 2.7 KB
Loading…
-
-
SKILL.md 3.1 KB
--- name: dev-browser description: Drive the user's dedicated Chrome AI window with the dev-browser CLI to open sites, click, fill forms, read pages, take screenshots and check a live app while signed in. Use when the user says browse, open a site, click, fill a form, screenshot, scrape, test my site, or check something on the web. allowed-tools: - Bash(dev-browser *) - Bash(chrome-ai *) --- Do every browser task in Chrome AI, the user's dedicated Chrome window (profile `~/.chrome-ai-profile`, port 9333) where they are already signed in to their tools. Start it first (it does nothing if it is already open), then connect to it on every run: If you got this skill from a link instead of a local folder, install nothing else from the repo: download a file it links only when a step needs it, with `curl -fsSL https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/dev-browser/<path> -o <scratch>/<file>` (for example `references/api-reference.md`), and read another skill it names only when you reach it, from `https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/<skill-name>/SKILL.md`. ```bash chrome-ai start dev-browser --connect http://127.0.0.1:9333 <<'JS' const page = await browser.getPage("stripe-sales"); await page.goto("https://dashboard.stripe.com"); console.log(JSON.stringify({ title: await page.title(), url: page.url() })); JS ``` If `chrome-ai` or `dev-browser` is missing, stop and tell the user to run `/setup-dev-browser`; never fall back to a standalone Playwright script or the user's own Chrome. If `CHROME_AI_PORT` is set, connect to that port instead of 9333 (`chrome-ai url` prints the address). - Give each task its own page name (`browser.getPage("lumail-campaign")`) so parallel agents never share a tab, reuse that name across runs to keep the page state, and close it with `browser.closePage(name)` when the task is done. Never close or navigate a tab you did not open. - Write small scripts that do one thing and end by logging the state as JSON (url, title, what you found). Scripts run in a sandbox, not Node: no `require`, `fs`, `fetch` or `process`. - Before clicking, read the page with `await page.snapshotForAI()` and target elements with `page.getByRole`, `getByText` or `getByLabel`. Open [references/api-reference.md](references/api-reference.md) before using a method you are not sure exists. - Files only go to `~/.dev-browser/tmp/`: pass a bare file name to `saveScreenshot` or `writeFile` and use the path it returns. Look at the screenshot before saying a page looks right. - If a site asks to sign in, stop and ask the user to sign in in the Chrome AI window, then continue; the session stays saved. Never type passwords, codes or card numbers, and never solve a captcha. - Ask the user before any click that sends, publishes, pays, deletes or accepts terms. - For a clean signed-out check (how a visitor sees the site), run without `--connect` and with `--headless`, and say so. - When a script fails, the page stays where it was: reconnect, take a screenshot, log the url and title, then continue from there. Reply with what you saw or did, the final URL, and the screenshot path when it helps.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.