What do I need to use Changelog For Humans?

The raw changes; The readers; The action items; The channel.

Is Changelog For Humans free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Changelog For Humans

Q: How do I know the Changelog For Humans output is good?

The skill verifies itself against its own quality checks: Every entry states a reader-visible so-what or lives in the plumbing line; Breaking/action-needed leads, with steps and dates; Claims carry their numbers and their limitations; The reader is the grammatical subject throughout.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

Write changelogs and release notes readers actually benefit from — changes translated to so-whats, grouped by reader impact (breaking first, gifts second, plumbing last), with the upgrade path stated and the marketing kept honest. Use when asked write the release notes, turn this commit list into a changelog, announce this update to users, or why does nobody read our changelogs. Produces the impact-grouped changelog, the so-what translations, the breaking-changes block with migration steps, and the two-audience split when needed.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The raw changes — commits, PR titles, the team's list; translation needs the source material and the *actual* user-visible effect of each (ask when a commit's impact is unclear — guessing so-whats manufactures lies)

▸The readers — end users? admins? API consumers? Their vocabulary and their stakes decide the grouping and whether the split applies

▸The action items — anything readers must *do* (migrate, re-auth, update configs) — these outrank everything and need deadlines

▸The channel — in-app note (three lines), email (skimmable), docs page (complete) — the same release ships different depths

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every entry states a reader-visible so-what or lives in the plumbing line

✓Breaking/action-needed leads, with steps and dates

✓Claims carry their numbers and their limitations

✓The reader is the grammatical subject throughout

✓Channel versions all retain the breaking block

⚠️ What it refuses to do

Do not publish the commit list with a header — that's the team's diary, not the reader's news

Do not bury action-needed under features — excitement doesn't file the migration for them

Do not overclaim improvements — the number or a modest verb

Do not hide fixed bugs in vague language — the people who hit them are searching for exactly those words

Do not write one changelog for two audiences with different stakes — split it or lose both

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="changelog-for-humans"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Changelog For Humans is one of 749 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog