commit

Smart Git commit helper that analyzes changes and creates semantic commits

Quality

57%

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 ./.clacky/skills/commit/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete commands and examples and a clear step sequence, but it is held back by heavy repetition of the same rules, a missing validation checkpoint in a batch-commit workflow, and a monolithic 400-line structure with no external references. Actionability is strong; conciseness, workflow safety, and disclosure are merely adequate.

Suggestions

De-duplicate the single-line-commit rule and the grouping guidance so each appears once in an authoritative section, removing the repetition across Process Steps, Best Practices, Anti-Patterns, and the Decision Framework.

Add an explicit validation checkpoint before committing (e.g. re-run 'git status' / 'git log --oneline' to confirm staged groups and reject empty or mis-grouped commits), turning step 6 into a validate-then-commit loop.

Move the long worked workflow example and the best-practices/anti-patterns catalog into a reference file (e.g. EXAMPLES.md) and link to it from SKILL.md to reduce the monolithic bulk.

Dimension	Reasoning	Score
Conciseness	The guidance is mostly actionable rather than explaining git basics Claude already knows, but the single-line-commit rule is repeated verbatim 6+ times and the grouping philosophy recurs across Core Philosophy, Process Step 4, Best Practices, Anti-Patterns, and the Decision Framework, so it 'could be tightened' significantly; it is not score 1 because it is not padded with generic concept explanations.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands (git status, git diff, git add, git commit -m) plus concrete good/bad commit examples and a decision tree, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	The seven steps are clearly sequenced, but there is no validation/verification checkpoint before committing, and the skill explicitly commits immediately without confirmation; the rubric caps batch/destructive operations at 2 when feedback loops are missing, so it does not reach the explicit-validation anchor of score 3.	2 / 3
Progressive Disclosure	At roughly 400 lines with no references/scripts/assets bundle, the skill is a single monolithic file; sections are well organized, but content that could be split out (long worked examples, best-practices catalogs) is inline, fitting 'some structure but content that should be separate is inline' rather than the one-level-deep reference structure of score 3.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 third-person but only middling: it states what the skill does without an explicit 'when to use it' trigger clause and with limited keyword variation. It avoids fluff but lacks the explicit trigger guidance and term coverage that would lift it to the top level.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to commit changes, write commit messages, or clean up staged work.'

Broaden natural trigger terms to include phrasings users actually say, such as 'commit message', 'write commits', and 'commit my changes'.

Name one or two more concrete actions (e.g. 'groups related changes and generates conventional commit messages') to increase specificity.

Dimension	Reasoning	Score
Specificity	It names the domain ('Git commit') and two concrete actions ('analyzes changes and creates semantic commits'), matching the 'names domain and some actions, but not comprehensive' anchor; it does not list multiple distinct actions like the score-3 example.	2 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2; it is not score 1 because the 'what' is explicit.	2 / 3
Trigger Term Quality	'Git commit', 'changes', and 'semantic commits' are relevant natural keywords, but common variations a user would actually say ('commit message', 'write commits', 'commit my changes') are missing, fitting 'some relevant keywords but missing common variations' rather than the full coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	'Smart Git commit helper' is a recognizable niche, but the short, slightly generic phrasing ('analyzes changes') could overlap with other git-oriented skills, matching 'somewhat specific but could still overlap' rather than the clearly distinct triggers of score 3.	2 / 3
	Total	8 / 12 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: clacky-ai/openclacky
Path: .clacky/skills/commit/SKILL.md
Commit: 4aea278

Reviewed: 4 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.