agentleFS
lorem-devlorem-dev/duolog/.agents/skills/check-changes/SKILL.md

check-changes

Skill4 starsChanged 16 days agoApache-2.0View on GitHub

Use when the user asks to write, update or check the changelog or CHANGES.md, or before bumping the version. Do not use to set the version; bump-version does that. Do not use to read past release notes aloud.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write files, comments and reports in English, ASCII only.

    line 13
  2. Distinctive:

    Use simple English: short sentences, common words, simple grammar.

    line 14
  3. Very specific:

    Run uv --version. If it fails, stop and ask the user to install uv: https://docs.astral.sh/uv/getting-started/installation/

    line 24
  4. Very specific:

    Read the comment at the top of CHANGES.md.

    line 32
  5. Distinctive:

    Run the check. It enforces the limits:

    line 48

≈ “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

Check the changelog

Communication

  • Reply in the language the user writes in.
  • Write files, comments and reports in English, ASCII only.
  • Use simple English: short sentences, common words, simple grammar.

Models

  • The current model does all of it. Deciding what a user would notice takes judgement, so prefer opus on Claude or gpt-6.1-sol on Codex, high effort. If a model is not available, use the current one.

Before you start

  • Run uv --version. If it fails, stop and ask the user to install uv: https://docs.astral.sh/uv/getting-started/installation/
  • A sandbox can stop uv from writing its cache. If a later uv run reports that, set the variable UV_CACHE_DIR to .cache/uv, which git ignores, and run it again. Do not call Python directly, and do not check the limits by hand instead.

Steps

  1. Read the comment at the top of CHANGES.md. Its rules decide what goes in.
  2. Find the last release: the newest commit whose message starts with release:, or the newest v* tag. List the commits since then:

    git log --oneline <last release>..HEAD
  3. For each commit, decide if a user would notice it. A fix needs an entry only if a released version had the bug: check that before you report a gap.
  4. Compare with ## Development. Report what is missing, and any entry for something that no longer exists. Add or correct entries if the user asked for that. Merge related entries instead of adding a long one.
  5. Run the check. It enforces the limits:

    uv run scripts/version/version.py check

    Example of a failure: CHANGES.md:51: bullet has 170 characters, the limit is 160. Shorten the entry or link to the docs. Never change a limit to make an entry fit.

Done when

  • version.py check exits with 0, and every commit that a user would notice has an entry in ## Development.

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.