agentleFS
akimisri17akimisri17/idea-to-app-kit/.agents/skills/results-check/SKILL.md

results-check

Skill0 starsChanged 40 days agoMITView on GitHub

Checks whether the app did what it was built for, and decides what happens next. Use on the "Check results on" date in doc 1 (the start-up check raises it), or when the person asks "did it work?", "is it worth it?", "what next?".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    delete rows that a test now guards.

    line 21
  2. Distinctive:

    keep AGENTS.md under ~200 lines.

    line 23
  3. Distinctive:

    Write it down: add the decision and the numbers to doc 4's decision log.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Results check

  1. Collect the numbers. For each metric (M#) in doc 1, get today's value (from the app, or ask the person to count) and set it next to its starting value and target.
  2. Decide per metric:

    • target hit → keep going;
    • partly there → fix the gaps;
    • missed badly → stop and rethink.

    Also check the bet's "we're wrong if…" signal.

  3. A short keep / stop / start with the person, at most 3 each:
    • Keep: what worked, from the app and from how you built it.
    • Stop: what wasted time or money.
    • Start: what to do next.
  4. Lessons review of docs/lessons.md:
    • merge duplicates;
    • delete rows that a test now guards;
    • fix contradictions;
    • keep AGENTS.md under ~200 lines.
  5. Write it down: add the decision and the numbers to doc 4's decision log. If the next step is new work, use the new-idea skill (or make-full).
  6. Reply in the answer-first shape: the verdict first, then the numbers, then the one decision you need from the person.

Adapted from pm-toolkit by Martin Foerster (MIT). See THIRD_PARTY_NOTICES.md.

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.