git commit conventional changelog
Automate Conventional Commit headers and grouped release notes from git history.
Free
Works with the AI Agents you already use
git commit conventional changelog
Example session with this skill installed
Analyze my staged changes and suggest a conventional commit message, then generate a changelog for all changes between v1.0.0 and the current HEAD.
- Read your context and instructions
- Compiled the git commit conventional
I have analyzed your staged changes and generated a release summary for the specified range.
Git Workflow Analysis
Suggested Commit Header
The staged changes involve src/auth.py and tests/test_auth.py.
{
"action": "commit",
"suggested_header": "feat(auth): update 2 files",
"type": "feat",
"scope": "auth",
"confidence": "medium",
"warnings": ["Generic description generated. Review diff for specific intent."]
}
Generated Release Notes (v1.0.0 to HEAD)
# v1.1.0 (2023-10-27)
## Features
- **auth:** implement jwt refresh token rotation [b2c3d4e]
- **api:** add health check endpoint [a1b2c3d]
## Bug Fixes
- **ui:** resolve alignment issue on mobile headers [f6g7h8i]
- **core:** handle null pointer in config parser [e5f6g7h]
## Breaking Changes
- **db:** ! migrate user schema to support multi-tenancy. Requires manual migration script execution.
## Other Changes
- initial workspace setup
Next steps
- Run
python scripts/changelog.py --action commit --desc "add jwt rotation logic" --applyto commit your changes. - Review the Other Changes section to standardize non-conforming commit messages.
- Use the
--output RELEASE_NOTES.mdflag to save the generated log to a file.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing commit history and release documentation shouldn't be a manual chore of parsing diffs and hand-writing logs. This skill automates the generation of Conventional Commit messages and structured changelogs directly from your git history.
What it does
- Commit suggestion analyzes staged changes to propose a type, scope, and plain-text description for your next commit.
- Confidence scoring labels suggestions as high, medium, or low based on file paths and content changes.
- Changelog generation parses the commit range between two tags to produce grouped release notes.
- Breaking change detection identifies
!syntax orBREAKING CHANGE:footers to highlight critical updates. - Format flexibility exports structured data as JSON or human-readable release notes in Markdown and text.
How it works
- Stage files using standard git commands before invoking the commit helper.
- Analyze diffs by running the script with the
--action commitflag to receive a suggested header. - Draft notes by specifying a range of tags or refs with the
--action changelogflag. - Apply or export results using
--applyto create a git commit or--outputto save a file.
Frameworks & tools
This tool relies on Python 3.8+ and the git CLI. It uses only the Python standard library, making it lightweight and easy to integrate into existing local environments or CI pipelines.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate commit types or miss breaking change markers in long logs. This skill uses a heuristic-driven approach combined with git's native diffing to ensure the output is grounded in actual file changes and strictly follows the Conventional Commits specification.
Use cases
- Generate standardized commit messages for staged changes.
- Create structured release notes between specific version tags.
- Audit recent repository history for non-conventional commit formats.
- Automate the grouping of features, fixes, and breaking changes for documentation.
Known limitations
Does not stage or track new files automatically. The classifier cannot determine developer intent, so low-confidence suggestions require manual review of the diff.
Requires Python 3.8+ and git CLI. Refuses to overwrite existing files without the --force flag. Only analyzes added lines and file paths for commit suggestions.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
Requires