aif-commit

Create conventional commit messages by analyzing staged changes. Generates semantic commit messages following the Conventional Commits specification. Use when user says "commit", "save changes", or "create commit".

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 ./skills/aif-commit/SKILL.md

Quality

Content

71%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 highly actionable, well-sequenced workflow with strong validation and feedback loops for staging and committing. Its weaknesses are conciseness (over-explains well-known commit conventions and basic formatting) and progressive disclosure (a monolithic body with no reference files despite dense plan-resolution rules that could be split out).

Suggestions

Remove or compress the commit-type definition list and basic formatting reminders ('imperative mood', 'no period') — Claude already knows Conventional Commits; keep only project-specific conventions.

Extract the dense active-plan / ultra-bundle resolution rules (step 2) into a one-level-deep reference file (e.g. references/plan-resolution.md) and link to it from SKILL.md to improve progressive disclosure.

Tighten the plan-resolution sub-bullets into a short decision table or checklist so the branching logic is scannable rather than prose-heavy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes unnecessary explanation Claude already knows, such as the full commit-type list (feat/fix/docs/...) and basic formatting reminders ('Use imperative mood', 'No period at end of subject'); the dense plan-resolution sub-steps also could be tightened.	3 / 5
Actionability	Fully executable guidance throughout: concrete git commands (git status, git diff --cached, git add -p, git commit, git push -u origin), copy-paste AskUserQuestion blocks with exact options, and worked message examples covering the common cases.	5 / 5
Workflow Clarity	Clear numbered sequence with explicit validation checkpoints and feedback loops (disjoint-file-set checks, hunk-staging confidence checks, stop-and-ask, 'Edit message → return to step 7'); the convoluted plan-resolution logic in step 2 creates minor clarity gaps that keep it below 5.	4 / 5
Progressive Disclosure	Has clear section headers (Workflow, Format, Examples, Behavior, Important) but no bundle reference files exist, and the lengthy plan-resolution rules are inlined in SKILL.md where a one-level-deep reference would be appropriate.	3 / 5
	Total	15 / 20 Passed

Description

78%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-formed description that concretely states what the skill does and when to invoke it with natural trigger terms. It uses correct third-person voice throughout. Minor improvements are possible around specificity (the two named actions are somewhat redundant) and the slight ambiguity of 'save changes' as a trigger.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('analyzing staged changes', 'Generates semantic commit messages following the Conventional Commits specification'), but 'create'/'generates commit messages' are largely the same action, so coverage is not comprehensive enough for a 4.	3 / 5
Completeness	Explicitly answers 'what' ('Create conventional commit messages by analyzing staged changes') and 'when' ('Use when user says "commit", "save changes", or "create commit"') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ('commit', 'save changes', 'create commit') that users would actually say; a few synonyms (e.g. 'git commit', 'submit changes') are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche (conventional commit generation) with mostly distinct triggers; minor overlap risk from the generic phrase 'save changes', which could plausibly match non-git skills.	4 / 5
	Total	16 / 20 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: lee-to/ai-factory
Path: skills/aif-commit/SKILL.md
Commit: e144f95

Reviewed: 5 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.