Notes about what changed for the customer, not what changed in the code.
Customer-readable release notes built from your commit log, tickets, or pull request titles, with breaking changes at the top.
Release notes are often a commit log with the hashes removed. 'Refactor sync queue' tells a customer nothing, and the one change that needs their action sits on line nine of a long list.
Release Notes sorts every change, drops the internal ones, and rewrites each as what you can now do or what no longer breaks. It leads with the change most users will notice, puts anything needing action first, and checks the result against the source so nothing claims more than shipped.
What it produces.
- →A lead paragraph for the change that matters most
- →A needs-attention section with dates and what to do
- →New, Improved, and Fixed lists in plain language
- →A list of what was dropped as internal, so you can overrule it
- ✦Product managers who ship every sprint or month
- ✦Engineers who write the notes because no one else will
- ✦Founders sending update emails to their users
- →release-notes.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →release-notes-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
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
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude usually restates the commit messages in friendlier words and keeps their internal vocabulary. This translates each item into its effect on the user, pulls breaking changes to the top, and compares the draft with your list so it never promises more than you shipped.
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.