Skip to content
Product · Playbook

One format, one line per change, still readable a year from now.

A changelog entry format and the entry itself, built from your changes and matched to your existing style.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Oct 22, 2026Instruction-only · verifiable

Changelogs decay. Early entries are tidy, then come paragraphs, mixed tenses, internal jargon, and a breaking change hidden in the middle. Nobody can scan it, so nobody trusts it.

Changelog Writer fixes the format once: header, four categories, one tense, one line per change. It prefixes breaking changes with a one-line migration step, merges minor fixes, and compares the new entry with the last one so the file keeps a steady shape.

What you get

What it produces.

  • →A fixed entry format you can reuse for every release
  • →The entry for this version, sorted into categories
  • →Breaking changes marked and listed first, with migration steps
  • →A consistency check against your previous entry
Who it's for
  • ✦Maintainers of libraries and small products
  • ✦Product managers who keep the changelog file
  • ✦Teams converting a messy history into a clean format
What's included
  • →changelog-writer.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →changelog-writer-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
  • →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
Delivery
Emailed within 60 seconds of payment
Compatibility
Claude, ChatGPT, Gemini, any LLM
License
One-time purchase, yours to keep
Sample output

What it does with a real question.

The brief

I'm the only maintainer of a small open-source CLI called trellis, and our CHANGELOG.md has grown to 1,400 lines of inconsistent notes since 2021. Some entries are paragraphs, others are raw commit hashes. Can you help me convert it into a short, consistent format and write the entry for v2.4.0, shipping March 12?

Don't rewrite 1,400 lines. Fix the format going forward, then convert only what people actually look up. Nobody is searching 2021 for a commit hash, so a full conversion of a solo project's history is effort with no reader. Here is what I'd do instead: freeze the old file as CHANGELOG-archive.md, start a fresh CHANGELOG.md in the new format, and link to the archive from the bottom. Then convert only the last two or three minor versions, plus any release that broke behavior, because those are the ones a user hits when an upgrade goes wrong.

The format is one line per change, past tense, under four categories (Added, Changed, Fixed, Removed), with a "Breaking:" prefix and a one-line migration step on anything that needs user action. Raw commit hashes become plain-language lines, and paragraphs get cut to the single fact a user needs.

I can't see your v2.4.0 changes, so here is the shell with placeholders for you to fill:

2.4.0 (2026-03-12) Added: Added [new thing]. Changed: Breaking: [renamed or removed behavior]. [One-line migration step.] Fixed: Fixed [symptom users saw].

Your next move: paste the raw 2.4.0 commit list and I'll sort it into this shape, merging near-duplicate fixes into single lines. Do the archive split first, so the new file starts clean and the 2.4.0 entry has a previous entry to match against.

The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.

Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.

One-time purchase
$12.99
Yours to keep
No subscription · free updates within v1.x

Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable

Questions

Before you buy.

How is this different from just asking Claude directly?

Asked cold, Claude writes friendly summaries whose style changes every time you ask. This holds one format across releases, keeps each line short, and checks the draft against your last entry.

How is this different from a Tool?

Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.

Will this work with ChatGPT, Gemini, and other LLMs?

Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.

Can I share this with my team?

It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.

What if it doesn't work for me?

If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.

More Product Playbooks

Other Playbooks.