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.

referencesagent-browser.md

≈549 tokens on demand. Your agent reads this file only when SKILL.md points to it.

agent-browser

Read when using agent-browser (step 2): a separate, clean Chrome that it opens itself.

Load its guide first

Before the first command in a session, load the guide that ships with the installed version, and follow it:

agent-browser skills get core          # workflows, common patterns, troubleshooting
agent-browser skills get core --full   # adds the full command reference and templates

Why: the CLI serves instructions that match its version. Anything copied here goes out of date with the next release, so this file holds only when to use what.

The loop

Take a snapshot of the page, act on an element by its @eN reference, then take a snapshot again to check the result. Why: references come from the accessibility tree, so clicks don't depend on screen coordinates or pixel matching. The exact commands and flags are in skills get core.

Specialised guides

Load one when the task fits it:

Task Command
An Electron desktop app (VS Code, Slack, Discord, Figma and similar) agent-browser skills get electron
Exploratory testing, QA, or a bug hunt agent-browser skills get dogfood
Recording network traffic to build an API client for a site agent-browser skills get derive-client
Slack workspace automation agent-browser skills get slack
A protected Vercel deployment agent-browser skills get protected-vercel-deployments
Running inside Vercel Sandbox, or AWS Bedrock AgentCore cloud browsers agent-browser skills get vercel-sandbox, agent-browser skills get agentcore

agent-browser skills list shows everything the installed version has.

Notes

  • Its Chrome starts clean: none of the user's sign-ins. For a site that needs one, use its sessions or saved state as skills get core describes, and stop for passwords and two-factor codes as SKILL.md says.
  • An Electron app is a web app inside a desktop window. Try skills get electron before falling back to desktop control.
  • Its dashboard runs on port 4848 (https://dashboard.agent-browser.localhost when proxied). Stay on the dashboard's address; it proxies the session tabs, so session ports don't need exposing.

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