create-commit

Create a safe, focused Git commit for this repository. Use when the user asks to commit completed work, prepare a commit, or choose a Conventional Commit message. Inspect the working tree, stage only intended files, validate relevant changes, and create the commit without pushing.

Quality

92%

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

Quality

Content

92%Weight 40%Scale 1-5

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

A tight, well-structured instruction skill with concrete git commands, explicit validation, and strong safety guardrails. The single improvement opportunity is adding a worked commit-message example.

Suggestions

Add one or two worked commit-message examples (input change → full 'type(scope): subject' output) alongside the format template to make the actionability fully copy-paste ready.

Optionally show how to handle the 'validation fails because of the proposed change' branch with a concrete re-stage/re-commit command sequence.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — assumes Claude knows git, never explains concepts, and every line (workflow steps, format block, safety rules) earns its place with no padding.	5 / 5
Actionability	Provides executable commands ('git status --short', 'git add <path>...', 'git commit -m', 'git log -1 --oneline') and a Conventional Commit type template, but offers only placeholder templates rather than a worked input→output example commit, leaving a minor gap.	4 / 5
Workflow Clarity	An 8-step sequenced workflow with an explicit validation checkpoint (step 6), a fix-before-commit feedback loop in the safety rules, a final staged-diff review (step 7), and a success confirmation (step 8).	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized into clear Workflow and Safety rules sections; per the simple-skill guidance this is sufficient for a top score.	5 / 5
	Total	19 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-targeted description that clearly states both capability and trigger conditions in concise third-person voice. The only minor gap is synonym coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Inspect the working tree, stage only intended files, validate relevant changes, and create the commit without pushing' — giving comprehensive coverage of the commit task.	5 / 5
Completeness	Explicitly answers both what ('Create a safe, focused Git commit... stage only intended files, validate relevant changes') and when ('Use when the user asks to commit completed work, prepare a commit, or choose a Conventional Commit message') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ('commit completed work', 'prepare a commit', 'Conventional Commit message'), but a few common synonyms like 'save changes' or 'make a commit' are missing, so it stops just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (creating commits) with distinct triggers and minimal overlap risk against other skills; third-person imperative voice is used throughout.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: DevCaress/guia-entrevistas-de-programacion
Path: .claude/skills/create-commit/SKILL.md
Commit: fb5f7af

Reviewed: 14 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.