generating-conventional-commits
Generates conventional commit messages using AI. It analyzes code changes and suggests a commit message adhering to the conventional commits specification. Use this skill when you need help writing clear, standardized commit messages, especially after making code changes and preparing to commit. Trigger with terms like "create commit", "generate commit message", or "write commit".
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill generating-conventional-commits64
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
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 well-structured skill description that clearly communicates its purpose and includes explicit trigger guidance. The main weakness is that the capability description could be more specific about the concrete actions performed (e.g., analyzing staged changes, formatting commit types, handling scopes). Overall, it provides sufficient information for Claude to select this skill appropriately.
Suggestions
Expand specificity by listing concrete actions like 'analyzes git diffs, formats commit type/scope/description, handles breaking change footers'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (commit messages) and some actions ('analyzes code changes', 'suggests a commit message'), but doesn't list multiple concrete actions like reviewing diffs, formatting headers, or handling breaking changes. | 2 / 3 |
Completeness | Clearly answers both what ('Generates conventional commit messages using AI, analyzes code changes') and when ('Use this skill when you need help writing clear, standardized commit messages... Trigger with terms like...'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'create commit', 'generate commit message', 'write commit', plus contextual terms like 'code changes', 'commit messages', and 'conventional commits'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on conventional commit message generation with distinct triggers; unlikely to conflict with general code review or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is overly verbose and lacks actionable guidance. It spends most of its tokens explaining concepts Claude already understands (Git, conventional commits, why good commit messages matter) rather than providing concrete templates, examples of commit message formats, or executable commands. The examples describe what the skill does rather than showing actual input/output pairs.
Suggestions
Replace the verbose explanations with a concrete conventional commit format template showing type(scope): description structure with all valid types (feat, fix, docs, style, refactor, test, chore)
Add actual example commit messages showing input (diff summary) and output (formatted commit message) rather than describing what the skill does
Remove the 'Overview', 'How It Works', 'When to Use', and 'Best Practices' sections - Claude knows these concepts; focus on the specific format and examples
Include the actual command or invocation pattern to generate a commit message (e.g., git diff --staged output format expectations)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with unnecessary explanations Claude already knows (what conventional commits are, why consistency matters, what Git staging is). The 'How It Works' and 'When to Use' sections explain obvious concepts rather than providing actionable guidance. | 1 / 3 |
Actionability | No concrete code, commands, or executable examples. The examples show vague descriptions ('The skill will analyze...') rather than actual commit message formats, templates, or the specific conventional commit types/scopes to use. | 1 / 3 |
Workflow Clarity | Steps are listed but extremely high-level and lack specifics. No actual commands shown (e.g., how to stage, how to invoke the skill, what the output format looks like). The workflow describes what happens conceptually rather than what to do. | 2 / 3 |
Progressive Disclosure | Content is organized into sections, but everything is inline in one file when much of it is unnecessary padding. References to other skills at the end are appropriate, but the main content doesn't warrant the length. | 2 / 3 |
Total | 6 / 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
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.