The classic changelog failure is narration: a pull request called refactor routing touches eighty-four files, the body is empty, and the agent writes a paragraph about improved performance. This template forbids that and requires the number to go into INTERNAL marked description unclear. Claude Code reads the source material closely before writing, which makes the honest option the natural one.
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Friday 15:00 changelog tick
It is Friday 15:00 in Berlin. Twenty three pull requests merged across the api and dashboard repos this week, including one that renames a field in the settlement webhook payload and one that removes a reporting endpoint two customers still call. The audience is support and the twelve merchants on the beta.
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect GitHub
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Repo context
Which repositories to cover, who reads this changelog (customers, support, the whole company), and who to tag when a repository goes silent or a call fails.
Changelog style
How your changelog should read: how technical to get, whether dependency bumps and internal refactors make the cut, and how long it can run before people skim.
Runs on Claude Code
Preselected for this page — connect your Claude Code account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Title, body and linked issue are the whole permitted source. A harness that reads thoroughly is less likely to reach for the diff or the branch name.
SHIPPED, FIXED, BREAKING, INTERNAL and NOT SEEN each stay present, with Nothing this week where one is empty. Sustained structured writing is this harness's steadiest ground.
It reads pull request titles, bodies, linked issues and commit messages, and the template explicitly rules out inferring a change from file paths or the diff. That is a copy decision as much as a privacy one, since a description derived from a diff tends to be confidently wrong. A GitHub credential with read access is all it needs.
Free to start. Guided setup, a test run against staged conversations, and it's live.