Engineering Advanced ChangelogReleasesGit

Changelog Generator

Generate structured changelogs from conventional commits.

$skillfish add ~skills/changelog-generator

Real Conversations

See how the Changelog Generator skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

I have a git range v1.3.0..HEAD with 47 commits — feat, fix, refactor, and two breaking changes: removed GET /v1/users/search and changed the auth token format. I want a proper CHANGELOG.md entry.

Agent

This skill includes executable scripts — I'll need your permission before running them.

The script to run:

python3 scripts/generate_changelog.py \
  --from-tag v1.3.0 \
  --to-tag HEAD \
  --next-version v2.0.0 \
  --write CHANGELOG.md

Based on your breaking changes, the script will determine a major bump (v1.3.0 → v2.0.0) and produce:

## [2.0.0] — 2026-03-09

### Breaking Changes
- **Removed** `GET /v1/users/search` — use `GET /v1/users?q=` instead ([migration guide](docs/migration-v2.md))
- **Changed** auth token format — Bearer tokens are now JWTs; opaque v1 tokens expire 2026-04-09

### Added
- [feat: commits rendered here]

### Fixed
- [fix: commits rendered here]

### Changed
- [refactor: commits rendered here]

SemVer logic: feat!: or BREAKING CHANGE: footer in any commit → major bump. Non-breaking feat: → minor. Everything else → patch.

Before I run: confirm commits use Conventional format. Pre-check with:

python3 scripts/commit_linter.py --from-ref v1.3.0 --to-ref HEAD --format text

Shall I run the linter first to validate all 47 commits, then generate the changelog entry?

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best
Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2
Good
Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only
32K+ Skill + conversation
100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Changelog Generator?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/changelog-generator
← Browse all 169 skills