agentleFS
Sign inStart free
diegopachecodiegopacheco/agent-skills/changelog-skill/SKILL.md

changelog-skill

Skill0 starsChanged 3 months agoUnlicenseView on GitHub

When need to create or update a CHANGELOG.md for a project, use this skill to write the changelog entries. IF user mentions CHANGELOG, changelog, or release notes, use this skill.

The file

We split this skill into the rules it gives an agent

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

  • 3

    Very specific

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

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

    Start with # Changelog and one line naming what it records, then versions newest first as ## MAJOR.MINOR.PATCH - YYYY-MM-DD.

    line 9
  2. Very specific:

    Use only these sections, in this order, and only when they have entries: ### Added, ### Changed, ### Fixed, ### Verified.

    line 10
  3. Very specific:

    Every Fixed entry says what broke for the user, why it broke, then what happens now - in that order, in plain sentences.

    line 11
  4. Distinctive:

    Write what the user can observe and name only what they touch: shortcuts, buttons, commands, scripts, screens.

    line 12
  5. Distinctive:

    Read the diff or the commits /code before writing, so entries describe what the code really does and not what the task asked for.

    line 15

≈ “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

CHANGELOG.md

  • Start with # Changelog and one line naming what it records, then versions newest first as ## MAJOR.MINOR.PATCH - YYYY-MM-DD. Keep adding to the top version while it is unreleased; once it ships, leave it alone and open a new one.
  • Use only these sections, in this order, and only when they have entries: ### Added, ### Changed, ### Fixed, ### Verified.
  • Every Fixed entry says what broke for the user, why it broke, then what happens now - in that order, in plain sentences. "Fixed a bug" is never an entry.
  • Write what the user can observe and name only what they touch: shortcuts, buttons, commands, scripts, screens. No commit hashes, no issue numbers, no author names, no source file, class, or function names.
  • One bullet per change, never nested. One sentence, or up to three when the cause needs saying. No marketing words.
  • Verified lists only what was actually run and observed, with real numbers - test counts with zero skips, measured results, checked behavior. Never write a Verified line you did not run.
  • Read the diff or the commits /code before writing, so entries describe what the code really does and not what the task asked for.

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