Changelog Gen

    2

    Automatically generate and update a professional CHANGELOG.md from your git history and Conventional Commits.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    changelog-gen

    Example session with this skill installed

    Generate a changelog for the project covering the last two releases, including our recent OAuth2 update and the breaking API change.

    • Read your context and instructions
    • Compiled the changelog-gen

    [1.2.0] - 2024-05-20

    Added

    • (auth) native OAuth2 support

    Fixed

    • memory leak in socket connection

    Breaking Changes

    • The v1/api endpoint now requires an API key

    [1.1.5] - 2024-05-12

    Changed

    • (deps) updated react to v18.3.0

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    This skill automates the tedious process of maintaining a professional changelog. It parses your git history—specifically identifying Conventional Commits—and transforms raw commit logs into a beautifully structured CHANGELOG.md formatted according to the Keep a Changelog standard.

    Why use this skill

    Manually documenting every change is error-prone and often forgotten. While basic tools can dump commit messages into a file, this skill intelligently categorizes entries into sections like "Added", "Fixed", and "Breaking Changes". It handles version tagging, date mapping, and even preserves your existing file content by prepending the latest updates. It’s significantly more sophisticated than simple prompting because it executes specific shell commands to extract precise git metadata (hashes, scopes, and dates) that a standard LLM context window might miss or hallucinate.

    Supported tools

    • Git: Comprehensive history parsing and tag identification
    • FileSystem: Intelligent reading and updating of your project root's CHANGELOG.md
    • Conventional Commits: Native support for feat, fix, docs, refactor, and breaking changes

    • Requires git repository access.
    • Accuracy depends on adherence to Conventional Commits.
    • May hit context limits on repositories with extremely large, untagged histories.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    Permissions

    Terminal / Shell
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    The skill is designed to work with any AI agent that has file system and shell execution permissions, such as AutoGPT, BabyAGI, or customized OpenInterpreter setups. It requires a local Git environment to function correctly.

    The skill relies on the Conventional Commits standard (e.g., feat:, fix:). It uses these prefixes to automatically categorize your updates into sections like "Added," "Fixed," and "Changed," ensuring a clean, readable history without manual sorting.

    No, the skill is designed to be non-destructive. It intelligently detects your existing CHANGELOG.md and prepends the newest version updates to the top of the file, preserving all your previous historical data.

    changelog-gen executes local git commands to retrieve precise metadata like commit hashes, author dates, and scopes. This prevents the "hallucinations" or missing entries that often occur when an LLM tries to summarize a long history from its internal memory alone.

    Yes, the skill is capable of identifying git tags to delineate different versions. It maps these tags to specific dates and version headers, allowing you to generate comprehensive logs for your entire project history or just the latest release.

    New in Technical Documentation