Optionally checks, then commits code to the current or a new feature branch.
68
52%
Does it follow best practices?
Impact
94%
1.30xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/commit/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is brief and provides a basic sense of the skill's purpose—committing code with optional checks—but lacks explicit trigger guidance ('Use when...') and misses key natural keywords like 'git'. It would benefit from more specific actions and clear usage triggers to help Claude distinguish it from other version control skills.
Suggestions
Add a 'Use when...' clause with trigger terms like 'commit', 'git commit', 'push changes', 'save my work', 'create a branch'.
Expand the description to clarify what 'checks' means (e.g., linting, tests, pre-commit hooks) and include the keyword 'git' explicitly.
Add natural language variations users might say, such as 'commit my changes', 'check in code', 'new branch', or 'stage and commit'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (git/version control) and some actions ('checks', 'commits code', 'feature branch'), but doesn't elaborate on what 'checks' means or list comprehensive actions like staging, diffing, or creating PRs. | 2 / 3 |
Completeness | Describes what the skill does (checks and commits code) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also somewhat weak, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes some natural terms like 'commits', 'code', 'feature branch', but misses common variations users would say such as 'git', 'commit message', 'push', 'staged changes', or 'branch'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to git commit workflows with the mention of 'feature branch', but could overlap with other git-related skills (e.g., branching, code review, or general git management skills) due to lack of precise scoping. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that clearly defines a commit workflow with a useful check/force toggle. Its main weaknesses are the lack of concrete examples (e.g., a sample commit message showing the conventional format) and missing post-commit validation or error handling steps. Adding a brief example and a verification step would elevate this skill significantly.
Suggestions
Add a concrete example of a conventional commit message (e.g., 'feat(auth): add JWT token validation middleware') to make the commit message guidance more actionable.
Add a verification step after committing, such as running `git log --oneline -1` to confirm the commit was created successfully and reporting if any files remain unstaged.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what git is or how conventional commits work conceptually. The skill assumes Claude knows git and focuses on the specific workflow steps and constraints. | 3 / 3 |
Actionability | Provides specific git commands and clear instructions, but lacks executable code examples (e.g., exact git commands with arguments for branch creation, or a concrete commit message example). The guidance on conventional commits is described rather than demonstrated with a concrete input/output example. | 2 / 3 |
Workflow Clarity | Steps are clearly sequenced and the check/force argument provides good branching logic. However, there's no validation checkpoint after the commit (e.g., verifying the commit succeeded, checking nothing was accidentally left unstaged) and no error recovery guidance if git add or git commit fails. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (Arguments, Steps) and appropriate inline detail. No bundle files are needed. | 3 / 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.
a3eff0e
Table of Contents
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.