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

Drives a real browser or desktop app to test, check or automate anything that needs a real interface - opening pages, clicking through flows, filling forms, taking screenshots, confirming a feature works. Also checks the agent's own work in the real interface after a change, when the user asks it to or the testing skill needs it. Uses browser-use (the user's own Chrome) first, then agent-browser (a separate, clean Chrome), then agent-desktop for desktop apps only after asking. Use when the user asks to automate a web or desktop task, test or check something in the browser, verify or check your own work, click through a flow, reproduce a UI bug, take a screenshot of a page, or fill a form. Not for writing test files that run again (use testing), proving a change against an answer key before a push (use prove), or fetching a public page or API that a plain request can read.

  • 4 files
  • 13.4 KB
  • Updated 3 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/avik-creator/agent-skills/automation

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈224 tokens for metadata: the name and description. ≈1k when used: this file. ≈2.2k more on demand in 3 files.

Description uses 11.2% 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 ≈897 characters, or 11.2%.

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.

Automation

Use it to automate a task in a real interface, or to check your own work there when the user asks: open the page or app, do what a person would do, and report what happened. A plain request is cheaper: if curl or a fetch tool can read it, don't open a browser.

Which tool, in order

  1. browser-use - attaches to the user's own Chrome, with their sign-ins. With no usable local Chrome, or for tasks that must run in parallel, it can start a Browser Use Cloud browser, after asking. See browser-use.md.
  2. agent-browser - opens its own clean Chrome. Use it when browser-use is missing or can't connect. See agent-browser.md.
  3. agent-desktop - for native apps, or when neither browser tool works. Always ask first: "Do you want me to control apps on your desktop? I can see and click anything on screen, but I won't take over your mouse unless I ask again." Ask every task. A yes doesn't carry over to the next one. Ask again before --headed (real mouse and keyboard). See agent-desktop.md.

Say why each time you move down the list: "browser-use can't reach Chrome, so I'm switching to agent-browser."

Missing tool

Don't install anything. Show the command, and let the user run it if they want:

Tool Install
browser-use uv tool install --python 3.12 --upgrade browser-use, then browser-use skill install
agent-browser npm i -g agent-browser && agent-browser install
agent-desktop npm install -g agent-desktop, then agent-desktop permissions --guide on macOS

If they'd rather not, move to the next tool.

Limits

The user's Chrome holds their real accounts: email, code hosting, cloud consoles. Act as a careful guest in it.

  • Your tabs only. Open your own tabs, never touch or close one you didn't open, and close yours when done.
  • Stop at sign-ins. Hand over at any password, two-factor code, consent screen or "which account?" choice. Using a sign-in Chrome already has is fine.
  • Ask before it counts. Before anything that sends, posts, buys, deletes, merges, invites, or changes settings or data, say what you're about to do and wait for a yes. This includes submitting a form on a real site. Why: these can't be taken back, and a click is enough to do them.
  • Production is read-only. On a live site, look but don't change anything unless the user says otherwise for this task. Make changes on localhost or staging.
  • Ask before anything that costs money, such as starting a cloud browser.
  • Private content stays private. Screenshots and page text can show messages and personal data. Don't paste them into public places (issues, pull requests, shared logs).

Each yes covers that one action. Ask again for the next one.

Report

Keep it short, in chat:

  • Result: what was checked, and whether it passed or failed, one line each.
  • Each failure: the step, what you expected, what you saw, one screenshot, and any console errors.
  • Tool: which one you used, and why you moved down the order if you did.
  • Leftovers: test data you created, or anything you couldn't close or undo.

Screenshots are for failures only. Why: screenshots of passing steps cost tokens and bury the one that matters.

When checking your own work, test what the user will do, not only the line you changed. A dead click, a silent no-op or a stuck spinner is a failure, even when the code "works".

Example

User: "Check the signup form I just fixed."

  1. browser-use --doctor reports that Chrome isn't reachable. Say so, and switch to agent-browser.
  2. Open http://localhost:3000/signup, submit it empty, then with a bad email, then with valid details.
  3. Report: "Empty: shows 'Email is required' - pass. Bad email: no message, button stays disabled - fail (screenshot). Valid: account created - pass. Used agent-browser because browser-use couldn't reach Chrome. Left behind: test account test+1@example.com."

Replies

Talk to the user in simple English: short sentences, everyday words, and a technical term only where it is needed, explained the first time it appears.

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.

No third-party reports yet.

Signed by skilld at a0324a3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 3 weeks ago

README badge

README badge for avik-creator/agent-skills/automation