Development · Source review 2026-10-28

Sentry PR Writer

Write a pull request around the concrete problem, resulting behavior and review evidence.

Publisher: Sentry · Editorial profile by AI Tools Ratings · Review method

What task is this skill designed for?

Convert a complete branch change into a reviewer-oriented PR description. Useful after implementation, when the reviewer needs the final scope rather than a transcript of the coding session.

What input and output should you expect?

Input: Provide base branch, full branch diff, existing PR if any, issue context and actual validation output. Separate observed test results from checks still to run.

Output: A focused title and body; the executing workflow can create a draft PR or update an existing PR description.

What does it need to run?

Git and authenticated GitHub CLI for the publication path. A local drafting trial can use supplied diffs without a GitHub write token.

Publisher documents Claude Code installation and skills.sh support for compatible agents including Cursor, Cline and GitHub Copilot. Host permissions and invocation behavior still require validation.

How should you approach installation?

  1. Read the pinned SKILL.md and repository LICENSE; compare project-specific conventions with your own instructions.
  2. Follow the publisher installation guidance for your host, retaining the full skill folder and references; begin in a disposable repository with minimal permissions.
  3. Run the suggested draft or read-only trial, review its acceptance checklist, and grant write or remote permissions only for the intended task.

Installation guide: discovery, dependencies and runtime checks

What files, accounts or data can it access?

Reads repository and PR context and can write to GitHub through gh. The description becomes visible to repository readers; remove secrets, customer data and internal-only notes before publication.

What does the skill cost?

No separate Skill purchase price is stated in the reviewed repository. The host agent subscription or model usage is separate; repository services and any authorized CI jobs may add costs. A local drafting trial does not require paid remote execution.

What are its limits and alternatives?

A useful description does not establish code quality. Comparing only the last commit can omit earlier branch changes, and updating an existing body can overwrite another contributor unless it is re-read first.

Use Sentry Commit for a single commit message, or a repository PR template when it requires specific sections.

What could you ask in a small trial?

Try this with a small sample:

Draft a PR title and description from this complete branch diff. Explain the empty-input failure and resulting behavior, include only the supplied validation evidence, and retain the repository template. Do not create or update a remote PR.

How would you verify the result?

  1. The description covers the full branch diff rather than only the latest commit.
  2. All validation statements match supplied evidence and remaining work is clear.
  3. Existing reviewer notes and user edits are preserved before any approved remote update.

Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.

Which source and license were checked?

Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder

Repository and current publisher guidance

Checked:

Apache-2.0 — repository LICENSE at the reviewed commit. License evidence

Version details and review scope

Source: getsentry/skills/skills/pr-writer
Reviewed commit: d12f250460ffd961f549dbebf7eeb0cf4afd4c2e

SKILL.md SHA-256: 785a2b1f084407e42f61661f83c7b0c621889865a483774f44c893c0cbcf57bc

Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.

Report an error, license concern or request a new review.

Compare related development workflows

Development · Codex source

OpenAI GitHub CI Fix Skill

Investigates failing GitHub Actions checks using GitHub CLI logs, summarizes the failure and proposes a repair before changes. It explicitly treats external CI providers as outside its repair scope.

Source checked 2026-10-23

Development · Codex source

OpenAI Playwright CLI Skill

Guides an agent through browser interactions using Playwright CLI and a bundled wrapper. It emphasizes inspecting a fresh page snapshot before acting, which helps keep clicks tied to the interface currently on screen.

Source checked 2026-10-23

Development · Codex source

OpenAI GitHub Review Comments Skill

Collects review threads from the pull request for the current branch, summarizes what each comment requires and lets the user choose which changes to address. It separates a review request from unrestricted code modification.

Source checked 2026-10-23

Get listed

Put your AI tool in front of people who are already comparing options.

Submit a listing for editorial review. Include a live website, current pricing and a clear use case. We may request more information before publication.

Submit a tool