agentleFS
otsalomaotsaloma/agent-setup/skills/align-with/SKILL.md

align-with

Skill0 starsChanged 44 days agoMITView on GitHub

Align part of this codebase with the same part in another

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:

    Keep names that are specific to this project.

    line 28

≈ “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

Reference and scope: $ARGUMENTS — the first word is the path of the reference project, the rest names what to align, for example "Makefile" or "paths and CSS loading". If only the path is given, consider shared infrastructure: project layout, build and install, packaging, tests, AGENTS.md and modules that both projects have in some form.

The reference project shows how I currently prefer to do things. You're looking to bring this project in line with it. First read both sides end-to-end, the reference and our counterpart, including call-sites, before forming any opinion. Understand why the reference does what it does.

Adapt, don't copy. Carry over the structure, naming, conventions and idioms, but leave out what doesn't apply here, such as features, dependencies, options or build steps this project doesn't have or need. Keep names that are specific to this project. If our version does something better than the reference, say so, I might want to change the reference instead, but never edit the reference project. If the two are already aligned, say so instead of inventing differences.

Report the differences lettered A, B, etc. For each, say what differs and whether you'd adopt, adapt or skip it and why. Flag clearly any change in behaviour visible to users or packagers. Propose a series of commits numbered 1, 2, etc. One concern per commit, ordered so that each builds on the last. Wait for user input. If given the go-ahead, do the commits one-by-one reporting your progress clearly as for example "Next commit 5/7". Follow the repo's and user's commit rules exactly. If they require approval per commit, show the full message and wait each time, however many that is.

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.