agentleFS
torisKRtorisKR/toris-agent/skills/ship-small/SKILL.md

ship-small

Skill2 starsChanged 4 months agoApache-2.0View on GitHub

Land the smallest change that fully solves the problem, with proof it works.

2 other projects use a version of this.

Adopted by

Most recently taken up by

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:

    Prove it: Run the project's tests. If nothing covers the change, add one test that fails before your edit and passes after.

    line 19

≈ “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

Ship small

A solo developer has no reviewer and no QA. Size is the only safety net you get.

Procedure

  1. Locate before you write. Find the exact file and function that owns the behaviour. Read it. If you cannot name the file, you are not ready to edit.
  2. State the seam. In one sentence: what changes, what stays. If that sentence needs an "and also", split the work.
  3. Change one thing. Touch the fewest files that make the sentence true. Resist tidying unrelated code in the same pass.
  4. Prove it. Run the project's tests. If nothing covers the change, add one test that fails before your edit and passes after.
  5. Report the diff honestly. Say which files changed and what you did not do.

Stop conditions

  • The change needs a new dependency → ask first. Dependencies are forever.
  • The change touches more than ~5 files → stop, propose a plan instead.
  • Tests were already failing before you started → say so, do not "fix" them silently.

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.