agentleFS
munnam77munnam77/claude-for-solopreneurs/skills/changelog-human/SKILL.md

changelog-human

Skill0 starsChanged 7 months agoMITView on GitHub

Write a changelog entry for humans using the product, not developers reading the code. Plain language, grouped by what changed for the user. Use when the user says "write the changelog", "update changelog for users", "customer changelog", or invokes /changelog-human.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    If they give you raw commits, read them, then write for users.

    line 18
  2. Distinctive:

    Every developer-facing item gets translated:

    line 45
  3. Distinctive:

    Never include internal refactors, dependency bumps, or CI changes unless they affect the user.

    line 62
  4. Distinctive:

    Never write "various bug fixes and improvements." It's the most disrespectful changelog entry in the world.

    line 63
  5. Distinctive:

    Never use version-control terms (merge, rebase, squash) — users don't speak git.

    line 64
  6. Distinctive:

    Never write a changelog longer than one screen unless there was genuinely that much user-visible change.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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-human

You are writing for a user who opened the changelog at 9am on Monday. They want to know in 30 seconds: what can I do today that I couldn't do on Friday, and did anything break?

What you do

1. Gather input

User will give you:

  • A diff, a list of commits, or a verbal description of what shipped
  • (Optional) The version number / release date

If they give you raw commits, read them, then write for users.

2. Output this structure

# <Version> — <Date>

## What's new
<One paragraph, 2–4 sentences. What can users do today that they couldn't yesterday? Lead with the user outcome.>

## Changes
- <User-facing change 1 — verb first, in plain language>
- <User-facing change 2>
- <User-facing change 3>

## Fixes
- <Fix 1 — describe what was broken for the user, not what line of code changed>
- <Fix 2>

## Breaking
<Only if breaking. Name what broke, how to migrate.>

---

3. Translation rules

Every developer-facing item gets translated:

Developer-speakHuman-speak
"Refactored auth module"(drop it — users don't care)
"Updated dependencies"(drop it)
"Fixed race condition in worker queue""Exports no longer duplicate when clicked twice quickly."
"Added /api/v2 endpoint"(drop unless it affects API users; then name what's different)
"Improved performance""The dashboard loads about 3x faster." (be specific)
"Better error handling""Clearer error messages when you upload an invalid file."

4. Ordering

Most important first. "What's new" = features users will notice. "Fixes" below. "Breaking" last, because it's the section they skim past when checking for upgrades.

What you never do

  • Never include internal refactors, dependency bumps, or CI changes unless they affect the user.
  • Never write "various bug fixes and improvements." It's the most disrespectful changelog entry in the world.
  • Never use version-control terms (merge, rebase, squash) — users don't speak git.
  • Never write a changelog longer than one screen unless there was genuinely that much user-visible change.

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.