agentleFS
Sign inStart free
fabioc-alohafabioc-aloha/Alex_ACT_ONE/skills/browser-tools/SKILL.md

browser-tools

Skill0 starsChanged 9 days agoMITView on GitHub

Use native browser capabilities first for interactive pages, screenshots, console errors, measured visual checks, local artifacts, and embedded-frame or hidden-tab input troubleshooting. Discover the active host tools; use registered alex-playwright only for missing or unsupported scenarios, with consent boundaries intact.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use web-search, skill-creator and 1 more.

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.
  • MicrosoftSkill

    web-search

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 4 projects that use this

  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer the current host's native browser tools for navigation, screenshots, accessible content, interactions, console errors, and focused …

    line 9
  2. Distinctive:

    Read console errors before judging a render.

    line 11

“Common” is measured: kept by at least 6 in 10 of the 12 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

Native-first Browser Tools

Prefer the current host's native browser tools for navigation, screenshots, accessible content, interactions, console errors, and focused Playwright code when those capabilities are available. Discover the actual tools; do not hardcode a host's API spellings.

Read console errors before judging a render. Measure suspect geometry and computed styles rather than estimating pixels or colors from a screenshot. Verify the requested behavior and report exact pages/flows, results, and limits.

For hidden-page timeouts, sandboxed frames, or input with no visible effect, load embedded-browser UAT before retrying. Diagnose readiness, visibility, and event targeting; distinguish DOM activation from trusted input and verified state changes. A returned click is not a passed test.

If a required capability is unavailable or unsupported, use the optional alex-playwright MCP fallback only when registered and permitted. Native CLI browser existence does not prove local-file, remote, console, or authentication parity. Do not install or enable integrations silently; report the missing capability if neither route works.

Respect authenticated-tab sharing and consent. Let the user enter credentials. Do not access unrelated local files, accept terms, purchase, or submit consequential actions without approval. Use disposable/attached helpers for a self-contained check and clean up only resources created for it.

Load the scenario reference only for the selected local-file, dynamic-page, authentication, or measurement case. Its old tool names are examples to map through current discovery, not guaranteed APIs. For semantic chart/prose checks use render-verify.

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