agentleFS
Sign inStart free
svyatovsvyatov/supermatt/skills/what-would-you-do/SKILL.md

what-would-you-do

Skill20 starsChanged 53 days agoMITView on GitHub

Explain the question you just asked and recommend an answer, with the case for and against each option.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    No open question in this session: say so and stop.

    line 11
  2. Distinctive:

    Do the legwork the answer needs: read the code, config, docs, or output the question touches.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

"What would you do?" The user answers a question you asked with this one, most often because they do not yet understand the problem well enough to choose. Take the most recent question or decision you put to them in this session; the arguments, if any, name another one, or the part they do not follow.

  1. No open question in this session: say so and stop.
  2. Do the legwork the answer needs: read the code, config, docs, or output the question touches. Done when every claim you make about an option rests on something you read or ran in this session.
  3. Explain the problem in plain words: what is being decided, why it came up, and what changes in the project with each answer. Define every term from the question the user may not know.
  4. List the options as O1, O2, and so on: the ones you offered, plus any better one the legwork turned up. For each: what it does, why pick it, and why not (cost, risk, what it rules out later, how hard it is to reverse).
  5. Recommend one in so many words ("I recommend O2") and give the deciding reason. When the answer hinges on something only the user knows (a preference, a deadline, a plan), name it and say which option each answer leads to.
  6. Hard question: the options stay close after the legwork and a wrong pick is costly to reverse. Give your lean anyway, then offer a jury: one ready-to-run /jury <question> line for Claude linked installs or Cursor, /supermatt:jury <question> from the Claude plugin, $jury <question> in Codex, or /skill:jury <question> in OMP. State the question, options, and constraints in full, so the panel needs nothing from this session. The user runs it.
  7. End on the recommendation. The user decides; act only on their answer.

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