Changelog Generator logo

Changelog Generator

Community
borghei
changelog-generator

Generate changelogs and release notes from Conventional Commits with semver bump detection, Keep a Changelog formatting, and monorepo scopes. Use when preparing releases, enforcing commit standards, or automating release notes.

Overview

Publisherborghei
RepositoryClaude-Skills
Skill namechangelog-generator
Stars
856
Forks
154
Bundled files
6
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by borghei on GitHub. Read the source before you install it.

Installation

Install the Changelog Generator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/borghei/Claude-Skills/tree/main/engineering/changelog-generator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/borghei/Claude-Skills.git /tmp/Claude-Skills
mkdir -p .claude/skills
cp -r /tmp/Claude-Skills/engineering/changelog-generator .claude/skills/changelog-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Changelog Generator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Changelog Generator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Changelog Generator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Changelog Generator

Generate consistent, auditable changelogs and release notes from Conventional Commits. Parses commit messages, detects semantic version bumps (major/minor/patch), renders Keep a Changelog sections, supports monorepo scoped changelogs, integrates with CI for automated release notes, and enforces commit format with linting. Separates commit parsing, bump logic, and rendering so teams can automate releases without losing editorial control.

Keywords

changelog, release notes, conventional commits, semantic versioning, semver, Keep a Changelog, commit linting, release automation, monorepo changelog

Core Capabilities

  • Commit parsing — parse Conventional Commit messages into structured data (type, scope, description, body, footer); detect breaking changes from ! and BREAKING CHANGE:.
  • Semantic version detection — map commit types to bump levels (breaking→major, feat→minor, others→patch); support pre-release versions.
  • Changelog rendering — Keep a Changelog, GitHub release notes, plain markdown, and JSON output grouped by type.
  • Quality enforcement — commit message linter for CI and pre-commit hooks, strict mode, scope validation, breaking-change documentation requirements.

When to Use

  • Before publishing a release tag
  • During CI to generate release notes automatically
  • In PR checks to enforce commit message standards
  • In monorepos where package changelogs need scoped filtering
  • When converting raw git history into user-facing notes
  • As a pre-release checklist step

Clarify First

Before generating the changelog, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Commit range — since which tag or commit (defines what history is included)
  • Output format — Keep a Changelog, GitHub release notes, plain markdown, or JSON (sets changelog_formatter.py --format)
  • Version & scope — the release version, and in a monorepo which package scope to filter (sets --version and scoped filtering)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Tools

ToolPurposeCommand
commit_parser.pyParse git log (with ---COMMIT_END--- delimiters) into structured changelog entriesgit log --pretty=format:'%H%n%s%n%b%n---COMMIT_END---' --no-merges | python scripts/commit_parser.py --json
breaking_change_detector.pyScan commit messages/diffs for breaking-change indicatorspython scripts/breaking_change_detector.py -f gitlog.txt --severity high
changelog_formatter.pyFormat parsed commits into Keep a Changelog or GitHub markdownpython scripts/changelog_formatter.py -f parsed.json --version 1.4.0 --format keepachangelog

References

Load the reference that matches the task — keep this file lean and pull detail on demand:

  • references/commit-format-and-rendering.md — the Conventional Commit grammar, type→section/semver mapping table, breaking-change rules, and the Keep a Changelog and GitHub Release Notes output formats. Read when defining commit standards or output style.
  • references/generation-and-linting.md — the 4-step parse→bump→render workflow with Python code, the pre-commit hook and CI commitlint config, monorepo scoped-changelog strategy, and the release-workflow integration diagram. Read when building the pipeline or enforcing format.
  • references/quality-and-troubleshooting.md — the pre-publish quality checklist, common pitfalls, best practices, troubleshooting table, and success criteria. Read before publishing a changelog or when diagnosing an issue.

Scope & Limitations

This skill covers:

  • Parsing Conventional Commit messages into structured data for changelog generation
  • Determining semantic version bumps (major/minor/patch) from commit history
  • Rendering changelogs in Keep a Changelog, GitHub Release Notes, plain markdown, and JSON formats
  • Enforcing commit message standards via pre-commit hooks and CI linting

This skill does NOT cover:

  • Actual release publishing or deployment pipeline execution — see engineering/ci-cd-pipeline-design
  • Git tag management, branch strategies, or merge workflows — see engineering/git-workflow-automation
  • Writing or improving commit messages themselves — see standards/git/git-workflow-standards.md
  • Coordinated multi-package versioning with tools like Changesets or Lerna — referenced in monorepo strategy but not implemented here

Integration Points

SkillIntegrationData Flow
engineering/ci-cd-pipeline-designChangelog generation runs as a CI stage before release publishingParsed commits and rendered changelog feed into the release pipeline as artifacts
engineering/git-workflow-automationCommit linting hooks enforce format before commits reach the changelog generatorPre-commit validation ensures only parseable commits enter the git history
engineering/code-review-automationPR checks verify commit messages conform to Conventional Commits before mergeLinting results gate PR approval, preventing unparseable commits from reaching main
engineering/api-versioning-strategyBreaking change detection aligns API version bumps with changelog major releasesBREAKING CHANGE commits trigger both changelog entries and API version increments
project-management/release-managementRelease planning uses generated changelogs for stakeholder communicationRendered release notes flow into release checklists and stakeholder announcements
standards/git/git-workflow-standards.mdCommit format standards define the grammar this skill parsesStandard definitions are the source of truth for the commit regex pattern

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Changelog Generator AI skill do?

Generate changelogs and release notes from Conventional Commits with semver bump detection, Keep a Changelog formatting, and monorepo scopes. Use when preparing releases, enforcing commit standards, or automating release notes.

Why use Changelog Generator on TypingMind?

Because you install it once and use it with any model. Changelog Generator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Changelog Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/borghei/Claude-Skills/tree/main/engineering/changelog-generator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Changelog Generator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Changelog Generator?

As many as you like. As long as a model supports skills, you can use Changelog Generator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Changelog Generator AI skill free?

It is published on GitHub by borghei. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇