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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is actionable and well-sequenced with concrete git commands, a precise output format, and a helpful error-handling table, but it redundantly defines basic commit types Claude already knows and fails to surface the bundled template, example diff, and analyzer script.

Suggestions

Replace the step-3 definitions of basic commit types with a pointer to the Conventional Commits spec (already linked in Resources) or to scripts/commit_analyzer.py, keeping only project-specific classification guidance inline.

Reference the bundle from the body — e.g. point to assets/commit_template.txt for the output scaffold and scripts/commit_analyzer.py for automated type/breaking-change detection — so progressive disclosure is one level deep and clearly signaled.

Add a brief validation checkpoint (e.g. confirm at least one staged file before classifying) to turn the linear flow into a feedback loop, matching the error-handling guidance already present.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean bullet/table formatting and inline `!`-command context gathering, but step 3 re-explains basic commit-type meanings ('feat: new functionality visible to users', 'fix: bug correction') that Claude already knows.	2 / 3
Actionability	Provides concrete executable git commands (`git diff --cached`, `git log --oneline -10`), a precise output format ('type(scope): imperative description under 72 characters'), and a copy-paste-ready message template.	3 / 3
Workflow Clarity	Nine clearly sequenced steps paired with an Error Handling table that gives cause/solution feedback for recovery; the task is non-destructive (message generation), so the destructive-validation cap does not apply.	3 / 3
Progressive Disclosure	The body is organized into clear sections, but bundled files exist (assets/commit_template.txt, assets/example_diff.txt, scripts/commit_analyzer.py) and are never referenced or signaled from the body, leaving content that could be split out inline.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 conveys a clear, distinctive niche with strong natural trigger terms, but its trigger guidance is awkwardly phrased ('Execute use when', 'Trigger with phrases like') rather than a clean 'Use when...' clause, and the capability list is only partially comprehensive.

Suggestions

Rewrite the opening into a clean declarative sentence plus an explicit 'Use when...' clause, e.g. 'Generate conventional commit messages from staged git changes. Use when the user asks to create or generate a commit message, mentions smart commits, or invokes /commit-smart or /gc.'

Make the capability list comprehensive or drop the partial type enumeration ('feat, fix, docs') to avoid implying the skill only handles those three types.

Lead with the skill's purpose in third person and keep the trigger terms as a natural 'Use when...' sentence rather than a separate 'Trigger with phrases like' fragment.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('determine the commit type', 'identifies breaking changes', 'formats according to conventional commit standards'), but the type list '(feat, fix, docs)' is partial and not comprehensive.	2 / 3
Completeness	Clearly states what the skill does, but the opener 'Execute use when generating...' is a malformed trigger clause and the 'Trigger with phrases like' phrasing is not a clean explicit 'Use when...' guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	Covers natural phrases a user would actually say ('create commit message', 'generate smart commit') plus slash commands ('/commit-smart', '/gc').	3 / 3
Distinctiveness Conflict Risk	A clear niche (conventional commit message generation from staged git changes) with distinct triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Commit: 3022dd3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.