agentleFS
netanelavrnetanelavr/dotcursor/skills/kit-minimize/SKILL.md

kit-minimize

Skill6 starsChanged 27 days agoMITView on GitHub

Find the smallest useful path to an engineering outcome. Use for minimal PR, least diff, 80/20, or anti-over-engineering.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    Very specific

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

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

    Not a full design challenge (kit-challenge-design)

    line 13
  2. Very specific:

    Not ticket readings or fuzzy alignment (kit-plan)

    line 14
  3. Very specific:

    Not cleaning a diff that already exists (kit-strip-diff)

    line 15
  4. Distinctive:

    Prefer in-repo patterns over new frameworks.

    line 40
  5. Distinctive:

    If nothing small works, say so — propose a thinner outcome, don’t fake minimal.

    line 41
  6. Very specific:

    If the code is already written and the diff is fatter than the outcome, stop and use kit-strip-diff.

    line 42

≈ “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

Minimize

Ship the outcome with the smallest change. Prefer reuse over invention.

What this is NOT

  • Not a full design challenge (kit-challenge-design)
  • Not ticket readings or fuzzy alignment (kit-plan)
  • Not cleaning a diff that already exists (kit-strip-diff)

Flow

  1. Outcome — one sentence: what must be true when done (not the named implementation).
  2. 2–3 paths — smallest → largest. For each: rough files touched, risk, what you skip.
  3. Recommend the smallest that still hits the outcome. Explicit what we are not building.
  4. Stop for approval unless they already said “just do the minimal one”.
  5. Implement only the approved path. Scope creep → pause and re-ask.

Do / Don't

DoDon't
Reuse an existing helper/configAdd a new abstraction “for later”
Thin the outcome if the smallest path is still hugeQuietly expand into a platform refactor
Skip unrelated cleanup“While we’re here” drive-bys
Tests that prove the outcome (or repo-required for the touch)Speculative test matrix for untouched areas

Diff discipline

While implementing the chosen path, follow always-on kit-keep-diff: no unrelated reorders; only functional lines in the diff.

Rules

  • Prefer in-repo patterns over new frameworks.
  • If nothing small works, say so — propose a thinner outcome, don’t fake minimal.
  • If the code is already written and the diff is fatter than the outcome, stop and use kit-strip-diff.

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.