- Home
- Skills
- Code Quality & Review
- PR Description Generator
PR Description Generator
Standardize pull requests with conventional titles, clear summaries, and structured change logs.
Free
Works with the AI Agents you already use
PR Description Generator
Example session with this skill installed
Generate a PR for: added stripe webhook retries to handle 504 errors from their API. tested with local tunnel and stripe-cli. scope is payments.
- Read your context and instructions
- Compiled the pr description generator
Title: fix(payments): retry stripe webhooks on 504 timeouts
Summary: Fixes dropped events caused by transient 504 errors from Stripe.
Changes:
- Added retry logic to webhook handler
- Integrated exponential backoff
Testing: Verified via stripe-cli and local tunnel.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Developers often write vague or incomplete pull request descriptions that force reviewers to hunt through the diff for context. This slows down the review cycle and leaves a poor trail of documentation in the project history.
What it does
- Identifies the correct conventional commit type (feat, fix, refactor, docs) from rough notes.
- Generates concise, 70-character titles using the type(scope): description format.
- Drafts a structured body including motivation, a bulleted list of changes, and testing notes.
- Includes risk assessments or rollback notes for broad structural changes.
Why this beats prompting it yourself
General-purpose prompts often produce overly verbose "fluff" or forget the conventional commit structure. This skill enforces strict scannability and prevents the use of vague terms like "updates" or "misc," ensuring every PR meets a high professional standard without manual editing.
Use cases
- Generating a PR draft immediately after finishing a local feature branch.
- Standardizing PR quality across a distributed engineering team.
- Explaining the "why" behind complex refactors for future maintainers.
Known limitations
It cannot invent test results or verify if a test passed; it only documents the testing process provided in the input.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Cannot verify test execution or invent data. Output quality depends on the provided change notes.
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 buying a skill.
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
3 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected