Customer-facing release notes from an internal change list
Converts an internal list of shipped changes (ticket titles, short descriptions) into release notes customers can read: grouped by what they can now do, written in plain language, with internal-only items left out.
Prompt in Product by AISkillHub Library
What it does
Internal change lists are written for the team ("Refactor auth middleware", "FE-2231 fix modal z-index"). Customers need to know what they can now do, what got better, and whether they need to do anything. This prompt converts the internal list into customer-facing release notes and explains which items it left out.
**Use it when** you publish a changelog, a monthly product update email, or in-app "what's new" notes and you start from a list of tickets or merged work.
**What you get** - A headline item: the change most likely to matter to the stated audience. - Notes grouped into New, Improved, Fixed and Action needed (only groups with content are shown). - Each item rewritten as a user benefit or behaviour, in plain language. - A "left out" list of internal-only items and why each was excluded, so you can override. - Questions for the team where an item's user impact is unclear.
**What it will not do** - It will not describe behaviour that the change list does not describe. If a ticket title is too vague to explain to customers, it goes into the questions list. - It will not mention security vulnerabilities in detail. Security fixes are noted generically ("security improvements") unless you supply approved wording. - It will not add release dates, availability or plan restrictions that you did not provide.
This works from any plain list. You do not need a particular issue tracker; paste ticket titles and descriptions as text.
**Example** "FE-2231 fix modal z-index on Safari" becomes "Fixed: dialogs no longer appear behind other content in Safari." "Upgrade Postgres to 16" goes to the left-out list as internal-only.
How to use it
## How to use
1. Open `prompts/customer-release-notes.md` and copy everything below the title line. 2. Replace each `{{variable}}` with your own content. Paste long material (notes, transcripts, tables) directly in place of the variable; keep the surrounding tags so the model can tell inputs apart. 3. Start a new chat in ChatGPT, Claude or Gemini and paste the filled prompt as your first message. 4. Read the output against the quality checks at the end of the prompt before you use or send it.
## Variables
- `{{change_list}}`: the internal list of shipped changes: ticket IDs, titles and any descriptions. - `{{product_name}}`: the product name. - `{{audience}}`: who reads these notes, e.g. `small business owners`, `developers using our API`. - `{{format}}`: `changelog page`, `email`, or `in-app` (shortest). - `{{approved_security_wording}}`: approved wording for security fixes, or `none`.
If you do not have a value for an optional variable, write `none` rather than deleting it, so the prompt still reads correctly.
## Reusing it
To reuse it often, save the prompt (with the variables left in) as the instructions of a Claude Project, a custom GPT or a Gemini Gem, then paste only the inputs in each new chat.
Files
Save each file at the path shown, relative to your project root.