Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
92
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 that clearly articulates what the skill does (stage, commit, push with conventional commits), when to use it (explicit trigger clause with multiple natural phrases), and is distinctive enough to avoid conflicts. The inclusion of specific user phrases like 'push to github' and 'commit and push' makes it highly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Stage, commit, and push git changes with conventional commit messages' clearly describes three distinct operations plus the commit message style. | 3 / 3 |
Completeness | Clearly answers both 'what' (stage, commit, and push git changes with conventional commit messages) and 'when' (explicit 'Use when' clause with multiple trigger scenarios and exact phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'push changes', 'commit and push', 'push this', 'push to github', 'save and push their work', 'pushing to remote'. These are highly natural phrases users would actually use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to the git push/commit workflow with distinct triggers. The combination of staging, committing, and pushing with conventional commits creates a clear niche that is unlikely to conflict with a general git skill or a commit-message-only skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, actionable skill that clearly delegates the git push workflow to a script with specific invocation commands. Its main weakness is the lack of error handling guidance and validation steps for what is essentially a destructive/irreversible operation (pushing to remote). A brief note on what to do when the push fails or conflicts arise would strengthen it.
Suggestions
Add error handling guidance: what should Claude do if the script fails (e.g., merge conflicts, authentication errors, no remote configured)?
Add a brief note or link explaining the conventional commit format the script uses, so Claude can generate appropriate custom messages.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose, and there's no unnecessary explanation of git concepts or conventional commits that Claude already knows. | 3 / 3 |
Actionability | Provides exact, copy-paste-ready bash commands for both default and custom message usage. The script path is specific and the invocation is clear. | 3 / 3 |
Workflow Clarity | The workflow delegates entirely to a script, which is clear for the happy path, but there's no validation or error handling guidance—what if the script fails, there are merge conflicts, or the remote is unreachable? For a push operation (potentially destructive/irreversible), missing error recovery caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references a script but doesn't link to any documentation about what the script does internally, what conventional commit format it follows, or how to troubleshoot. For a simple skill this is mostly fine, but a brief reference to the script's behavior or a README would improve navigation. | 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.
Reviewed
Table of Contents