Publisher: Sentry · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Summarize a coherent change as a conventional commit. Best for developers who already understand and have reviewed their diff, rather than asking a message generator to decide what should ship.
What input and output should you expect?
Input: Supply the intended files, full staged and unstaged diff, branch name and any verified issue references. State whether the request is message drafting or an actual commit.
Output: A concise typed subject and explanatory body; when authorized, a local Git commit. The source distinguishes references from issue-closing language.
What does it need to run?
Git and a repository with a known working-tree state. The workflow has a default-branch guard and project-specific commit conventions.
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?
- Read the pinned SKILL.md and repository LICENSE; compare project-specific conventions with your own instructions.
- Follow the publisher installation guidance for your host, retaining the full skill folder and references; begin in a disposable repository with minimal permissions.
- 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?
The executing workflow can change branches, stage content and write Git history locally. A local commit is not a push; remote publication requires a separate decision. Code context may reach the configured model.
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?
Automatic staging can capture unrelated work unless the file scope is explicit. Sentry-specific types and attribution conventions may not match another team. Never invent issue numbers or put personal information in a message.
Use a plain message draft when preserving the working tree matters; use your repository commit template when its conventions differ.
What could you ask in a small trial?
Try this with a small sample:
Draft only a commit message for the supplied retry-boundary fix and its test. Identify the changed behavior and reason. Do not stage files, change branch or commit. Use only the provided issue reference and do not mark it resolved unless the diff fully addresses it.
How would you verify the result?
- The subject describes the actual behavior change within the source length guidance.
- The body explains why, without repeating every filename or claiming tests ran.
- The working tree is unchanged in draft-only mode.
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/commit
Reviewed commit: d12f250460ffd961f549dbebf7eeb0cf4afd4c2e
SKILL.md SHA-256: 0307d3ecfe3b3e70246cbd88b19dc5853340b624b6ee3cd935c7bffc45b64279
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.