agentleFS
amit-nayaramit-nayar/android-adb-skill/skills/android/SKILL.md

android

Skill29 starsChanged 8 months agoMITView on GitHub

General-purpose Android automation. Use for multi-step Android tasks that should be executed through the local ./tools/android command layer instead of raw adb.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use accessibility-frontend-review, android-new-module and 10 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.
  • BrowserWorksSkill

    accessibility-frontend-review

    Performs an accessibility code review of a local diff or Phabricator revision in the style of the Firefox accessibility team. Use this skill whenever the user asks to review a Phabricator patch or revision for accessibility issues, mentions a D-number (like D284142) in the context of accessibility review, asks "does this patch have any a11y issues", or wants to check a diff against accessibility guidelines. Also use it when the user says things like "can you review this for a11y", "check this patch", or "give me an accessibility review of D[number]". Invoke proactively when the user pastes a phabricator.services.mozilla.com URL or shares a revision ID alongside any accessibility concern. Invoke when questions about the following topics are raised: aria properties, aria roles, high contrast mode, forced colors, prefers contrast, focus order, screen readers, assistive technology.

    Also in 4 projects that use this

  • BrowserWorksSkill

    android-new-module

    Guide for creating new Android gradle modules in the android-components project.

    Also in 4 projects that use this

  • +10 more from BrowserWorks

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use ./tools/android as the default execution layer.

    line 8
  2. Distinctive:

    If multiple devices are attached and the user did not choose one, stop and ask.

    line 13
  3. Very specific:

    Prefer --json and reason from structured output.

    line 22
  4. Very specific:

    After every interaction, verify with ui dump, wait element, or screenshot.

    line 23

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

Use ./tools/android as the default execution layer. Read docs/command-contract.md if you need the exact command surface.

Workflow:

  1. Start with ./tools/android device list --json.
  2. If multiple devices are attached and the user did not choose one, stop and ask.
  3. Break the request into steps and route each step to the right command family:
    • screenshots: screenshot
    • UI inspection: ui dump, ui find
    • interaction: input ...
    • waits: wait element
    • scrolling: scroll find
    • app lifecycle: app ...
    • logs: debug ...
  4. Prefer --json and reason from structured output.
  5. After every interaction, verify with ui dump, wait element, or screenshot.

Fallback to raw adb only if the command layer cannot do the required operation.

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.