# Staging Release Notes

> Stage the release notes and update the changelog header before you tag the release. Use before tagging a release.

- Skill: `brokenrobot-xyz/staging-release-notes` (Agent Skill)
- Install (CLI): `npx skillmds@latest add brokenrobot-xyz/staging-release-notes`
- Raw SKILL.md: https://api.skillmd.com/api/skills/brokenrobot-xyz/staging-release-notes/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: brokenrobot-xyz (https://skillmd.com/u/brokenrobot-xyz)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/brokenrobot-xyz/staging-release-notes

---


# Stage release notes

Collect the entries under `changes/unreleased/`, merge them into `CHANGELOG.md` under a new
version header, and leave the working tree staged so the tagger reviews one diff.

## Steps

1. Read every file under `changes/unreleased/`. When the directory is empty, stop and tell the
   user there is nothing to release, because an empty release header misleads the tagger.
2. Group the entries by kind — Added, Changed, Fixed — and write them under a new version header
   in `CHANGELOG.md`.
3. Delete each merged entry file, so the next release starts from an empty directory.
4. Report the version header you wrote and the entry count per kind.