agentleFS
woodbearywoodbeary/later-dog/.claude/skills/verify-app/SKILL.md

verify-app

Skill2 starsChanged 29 days agoApache-2.0View on GitHub

Prove a later.dog server or conversation change on a disposable fake-engine instance, never the person's running app, before saying it works.

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bughunt.

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.
  • avSkill

    bughunt

    Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    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:

    When the control tool cannot drive what you changed (Settings, drag and drop, the updater and similar renderer-only flows), use the nearest …

    line 18

“Common” is measured: kept by at least 6 in 10 of the 5 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

Verify the app

The full procedure and the per-feature recipes are in docs/verification/README.md. In short:

  1. Start a disposable instance in its own terminal, directly rather than through pnpm so that Ctrl-C reaches it: node --experimental-strip-types scripts/control-laterdog.ts launch It runs on temporary data with the fake engine only, prints its URL, PID, data directory and log path, and leaves the person's later.dog alone.
  2. Check it from a second terminal, always passing that URL: pnpm control:laterdog doctor --url http://127.0.0.1:PORT. Commands that change anything refuse to guess a port; never point them at the person's app.
  3. Drive the change with the commands on the matching recipe page (send, wait, messages, ui …). Go through control-laterdog, not hand-written HTTP calls.
  4. Keep the evidence: the JSON from wait and messages, the exact commands, and the printed log path. It must show the action and the state it produced; a passing unit test alone does not prove a user flow.
  5. Stop it with Ctrl-C. The launcher stops the one child it started and removes only its temporary data; the log stays. Never kill processes by name or delete a shared temp directory.

When the control tool cannot drive what you changed (Settings, drag and drop, the updater and similar renderer-only flows), use the nearest Electron or package smoke test and say plainly that the flow itself was not proven.

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.