commit

Create a git commit with a summary of changes

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/commit/SKILL.md

Quality

Content

100%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 body is an efficient, actionable workflow with a clear sequence and an explicit guard for the empty-staging case. It is appropriately concise for a simple, single-purpose skill.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept re-explanation Claude already knows; each line (the three commands, the staged-files guard, the argument note) earns its place.	3 / 3
Actionability	It provides concrete, executable commands (`git diff --staged`, `git status`, `git commit -m "<message>"`) and the instructional step is actionable, matching the executable-guidance anchor.	3 / 3
Workflow Clarity	The three steps are clearly sequenced with an explicit guard ("If no files are staged, tell the user to stage files first"); commit is not a destructive/batch operation, so the simple-skill carve-out applies.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references, and the content is well-organized under a heading, satisfying the guideline for scoring 3 without external files.	3 / 3
	Total	12 / 12 Passed

Description

50%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 concise and names a concrete action, but it lacks explicit trigger guidance and the natural user phrasings (e.g., "commit message") that would make it score higher. All dimensions land at the middle anchor.

Suggestions

Add an explicit "Use when..." clause, e.g., "Use when the user asks to commit changes, write a commit message, or save staged work."

Include natural trigger terms users actually say, such as "commit message," "commit my changes," and "make a commit," alongside "git commit."

Consider naming multiple concrete actions (e.g., reviewing staged changes, drafting the message, and creating the commit) to lift specificity.

Dimension	Reasoning	Score
Specificity	"Create a git commit with a summary of changes" names a concrete domain and action, but it describes a single action rather than listing multiple specific concrete actions as the anchor 3 example does.	2 / 3
Completeness	It clearly answers what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	It includes "git commit" and "summary of changes" but omits common natural variations a user would actually say, most notably "commit message," so keyword coverage is partial.	2 / 3
Distinctiveness Conflict Risk	"git commit" is a specific niche, but the terse description lacks distinguishing trigger context and could overlap with other git-related skills, matching the "somewhat specific but could still overlap" anchor.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Windy3f3f3f3f/claude-code-from-scratch
Path: .claude/skills/commit/SKILL.md
Commit: 0b45236

Reviewed: ~1 month 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.