Works with the AI tools you already use

    CClaude CodeCCursorCCodex CLIGGitHub CopilotGGemini CLIVVS CodeWWindsurf+15 more

    Pull Request Description Writer

    by PubsProToolkit

    1

    AI-generated PRs are worse, because the agent rarely explains its reasoning at all.

    Secure checkout via Stripe

    0 installsSecurity scanned

    See it in action

    You say

    Write a PR description for this diff. It refactors the auth-middleware.ts to use Redis for session storage and adds a rate limiter. The ticket is Jira-402. I ran unit tests but not e2e tests yet.

    Your agent does

    Summary

    Refactors auth-middleware.ts to use Redis for session storage, replacing the in-memory store to support horizontal scaling. Addresses [JIRA-402].

    Review Guidance

    Focus on middleware/rate-limiter.ts. I am unsure if the Redis connection timeout is too aggressive for high-latency spikes.

    Testing

    • Unit tests: Passed.
    • E2E tests: Not performed.
    • Manual: Verified session persistence across server restarts.

    What you get

    Convert complex diffs into logical grouped summariesHighlight risky code sections for reviewersStandardize PR documentation across a development teamDocument testing notes, migrations, and rollback steps from the details you provideWrite clear descriptions for agent-generated PRs so human review stays efficient

    About this skill

    A pull request is a request for someone's time, and most PRs waste it: a one-line title over a 600-line diff, no why, no pointer to the risky part, no note on what was tested — so the reviewer reverse-engineers the intent from the code, slowly and often wrongly. AI-generated PRs are worse, because the agent rarely explains its reasoning at all. Pull Request Description Writer writes the description from the diff. Give it the changed files and, ideally, the ticket the work addresses, and it produces a reviewer-focused description: a summary that leads with why, the meaningful changes grouped by behavior rather than listed file-by-file, review guidance that points the reviewer to where to start and what's risky (the single biggest time-saver), an honest testing section that includes what was deliberately not covered, and risk, migration, and rollback notes where they apply. It scales the description to the change — a one-line fix gets a summary and a test note, a risky migration gets the full set — and it flags any why it had to infer for the author to confirm rather than inventing a motivation. The download includes three reference files: the PR-description template, a review-guidance checklist, and a worked sample. It writes from the diff and context you provide — it doesn't run the code or verify tests, so testing claims come from what you tell it. Works with Claude Code, Cursor, Codex CLI, Gemini CLI, and any SKILL.md agent.

    How to install

    Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 15 days ago

    Listed15 days ago

    Creator

    PubsProToolkit builds rigor-first skills for AI agents — they write your docs and content properly, then adversarially review them to catch what's wrong before it ships. The result: cleaner output and a hard quality gate in one toolkit. Built by a CMPP-certified, PhD medical writer who brings regulated-industry standards to developer docs, content, compliance, and research integrity.

    Frequently Asked Questions

    Popular in Documentation