agentleFS
IgorGanapolskyIgorGanapolsky/mac-yolo-safeguards/.agents/skills/android-dev-summit-26-gate/SKILL.md

android-dev-summit-26-gate

Skill3 starsChanged 3 days agoMITView on GitHub

Review an agent diff the way Android Dev Summit '26 describes Change Review: block an emulator boot for a UI preview, keep Lightbuild off the production app, and refuse vendor speed figures as our results.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Use this before treating an agent change as finished when the work is a UI preview, a Hermes Mobile ship script, a memory fix, or a store …

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Android Dev Summit change review

Use this before treating an agent change as finished when the work is a UI preview, a Hermes Mobile ship script, a memory fix, or a store submission.

Google's 29 Oct 2026 Android Studio note and their tools write-up describe four habits: any agent can do the work, a change review runs before commit, a UI check uses a preview or a real device, and a memory fix is rechecked with a measurement. Their preview, skill, and LeakCanary timing figures stay theirs.

What this gate does

  • A preview task needs the Hermes ship skill on disk and either a connected device or a named preview command.
  • emulator -avd and xcrun simctl boot are blocked in the command, the diff, and the preview flag. A ship task may run one of the existing Hermes ship scripts, and that command has to be the script itself.
  • A review with no diff is blocked.
  • A Lightbuild line under hermes-mobile is blocked. Production stays on the current build.
  • An XR emulator install is blocked.
  • An empty diff is not an approval.
  • "Fixed the leak" or "fewer tokens" needs a measurement string and a recheck.
  • A Play or App Store submit needs a policy check flag.
  • Copy that says we are 77% faster, or that we used 3x fewer tokens, is blocked.

Commands

node tools/android-dev-summit-26-gate.js
node tools/android-dev-summit-26-gate.js --review --task "check the hermes-mobile preview" --diff "spacing" --preview "npm test"
node tests/test-android-dev-summit-26-gate.js

The status command lists devices and simulators that are already booted. It does not start one.

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.