commit
ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent trigger terms and completeness. It clearly communicates both what the skill does (Sentry-convention commits with conventional commit format) and when to use it, with explicit trigger terms. The main weakness is that the specificity of concrete actions could be slightly more detailed — e.g., mentioning specific conventional commit types or how issue references are formatted.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (committing code changes) and some actions (creates commits, conventional commit format, issue references), but doesn't list multiple concrete actions beyond commit creation — e.g., no mention of staging, amending, or specific formatting steps. | 2 / 3 |
Completeness | Clearly answers both 'what' (creates commits following Sentry conventions with conventional commit format and issue references) and 'when' (explicit trigger clause: 'Trigger on any commit, git commit, save changes, or commit message task'). Also includes a strong imperative 'ALWAYS use this skill when committing code changes.' | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'commit', 'git commit', 'save changes', 'commit message', plus contextual terms like 'code changes'. These are terms users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Sentry commit conventions with conventional commit format and issue references. The combination of 'Sentry conventions' and commit-specific triggers makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with excellent workflow clarity around the branch-checking prerequisite and clear commit formatting guidance. The content is well-structured with good examples and concrete commands. Minor improvements could be made by trimming some explanatory content Claude already knows (imperative mood, what 'refactoring' means) and potentially splitting the extensive examples into a separate reference file.
Suggestions
Consider moving the full examples section and the complete commit types table to a separate REFERENCE.md to keep SKILL.md leaner as an overview
Remove explanations of concepts Claude already knows, such as 'Refactoring (no behavior change)' descriptions and imperative mood explanations like '"Add feature" not "Added feature"'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some content Claude already knows (e.g., imperative mood explanation, basic git concepts). The commit types table is comprehensive but some entries like 'license' and 'meta' could be trimmed. The examples section is useful but four full examples plus a revert format is slightly verbose. | 2 / 3 |
Actionability | Provides concrete, executable bash commands for committing, specific commit message formats with exact syntax, a complete type table, and multiple realistic examples that are copy-paste ready. The CLI hygiene section with actual bash patterns is particularly actionable. | 3 / 3 |
Workflow Clarity | The prerequisites section establishes a clear workflow with explicit validation: check branch → create branch if on main → verify branch changed → only then commit. The 'stop — do not commit' guard is an explicit checkpoint. The commit command patterns provide clear sequencing for the actual commit step. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a fairly long single file (~150 lines of content) that could benefit from splitting detailed examples or the full type table into a reference file. It does reference the `create-branch` skill appropriately and links to external Sentry docs, but the inline content is heavy for a SKILL.md overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- getsentry/skills
- Commit
51b0238
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.