# Changelog Automation

> Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.

- Skill: `nous-hermeshub/changelog-automation` (Agent Skill)
- Install (CLI): `npx skillmds add nous-hermeshub/changelog-automation`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nous-hermeshub/changelog-automation/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- License: MIT
- Author: nous-hermeshub (https://skillmd.com/u/nous-hermeshub)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/nous-hermeshub/changelog-automation

---


# Changelog Automation

Patterns and tools for automating changelog generation, release notes, and version management following industry standards.

## Use this skill when

- Setting up automated changelog generation
- Implementing conventional commits
- Creating release note workflows
- Standardizing commit message formats
- Managing semantic versioning

## Do not use this skill when

- The project has no release process or versioning
- You only need a one-time manual release note
- Commit history is unavailable or unreliable

## Instructions

- Select a changelog format and versioning strategy.
- Enforce commit conventions or labeling rules.
- Configure tooling to generate and publish notes.
- Review output for accuracy, completeness, and wording.
- If detailed examples are required, open `resources/implementation-playbook.md`.

## Safety

- Avoid exposing secrets or internal-only details in release notes.

## Resources

- `resources/implementation-playbook.md` for detailed patterns, templates, and examples.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
