CtrlK
BlogDocsLog inGet started
Tessl Logo

generating-smart-commits

Execute use when generating conventional commit messages from staged git changes. Trigger with phrases like "create commit message", "generate smart commit", "/commit-smart", or "/gc". Automatically analyzes changes to determine commit type (feat, fix, docs), identifies breaking changes, and formats according to conventional commit standards.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable and well-sequenced with concrete git commands and a clear output format, but it is somewhat redundant (duplicated type catalog), lacks an explicit validation checkpoint in the workflow, and fails to route to the bundle files that ship alongside it.

Suggestions

Link the existing bundle assets from the body — e.g., reference assets/commit_template.txt for the full template and assets/example_diff.txt as a worked input, and reference scripts/commit_analyzer.py for automated type detection — instead of inlining and duplicating that material.

Add an explicit validation checkpoint to the workflow, such as a step that verifies the generated header is under 72 characters and that the type/scope match the staged diff before finalizing the message.

De-duplicate the commit-type catalog so it appears once (either in Instructions or as a reference to commit_template.txt) to tighten token usage.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands and a compact error table, but the commit-type catalog is duplicated across the Overview and Instructions sections, and the example 'Resources'/'Examples' sections add length that could be tightened — fitting the 'mostly efficient but could be tightened' anchor rather than the lean 3.

2 / 3

Actionability

It gives concrete, copy-paste-ready git commands ('git diff --cached --stat', 'git diff --cached', 'git log --oneline -10'), an explicit output format ('type(scope): imperative description under 72 characters'), and a concrete error-handling table — fully executable guidance with no pseudocode or vague direction.

3 / 3

Workflow Clarity

The nine numbered steps form a clear sequence, but validation checkpoints are only implicit (e.g. 'Check for breaking changes', 'Check recent commit history') with no explicit verify-then-proceed gate or validate→fix→retry loop embedded in the flow; the error table provides recovery but no in-workflow checkpoint, matching the 'sequence present but checkpoints missing or implicit' anchor.

2 / 3

Progressive Disclosure

The body is organized into clear sections rather than a monolithic wall, but it never references or links to the bundle files that actually exist (assets/commit_template.txt, assets/example_diff.txt, scripts/commit_analyzer.py), and it inlines a commit-type catalog and output template that duplicate the commit_template.txt asset — fitting the 'references present but not clearly signaled; content that should be separate is inline' anchor.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, and clearly scoped to conventional-commit generation from staged changes. The only minor blemish is the awkward 'Execute use when' phrasing, but the trigger guidance is explicit and complete.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'generating conventional commit messages from staged git changes', 'analyzes changes to determine commit type (feat, fix, docs)', 'identifies breaking changes', and 'formats according to conventional commit standards' — matching the anchor that lists multiple specific concrete actions.

3 / 3

Completeness

It states both what it does (analyze, classify type, identify breaking changes, format) and when to use it via an explicit trigger clause ('Execute use when generating conventional commit messages...', 'Trigger with phrases like...'), so the 'Use when' cap at 2 does not apply.

3 / 3

Trigger Term Quality

Natural user phrasings are well covered: 'create commit message', 'generate smart commit', '/commit-smart', '/gc', plus 'staged git changes', giving good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow (conventional commits from staged git changes) with distinctive slash-command triggers ('/commit-smart', '/gc'), making it unlikely to fire for an unrelated skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.