gerrit-commit-message-review

Proofreads and suggests structural improvements for Git commit messages to ensure style guide compliance, completeness, and accuracy.

Quality

35%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./configs/skills/gerrit_commit_message_review/SKILL.md

Quality

Content

32%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.

The body contains thorough, accurate commit-message standards with good Do/Don't examples, but it is verbose, monolithic, and lacks a sequenced review workflow with validation checkpoints. Splitting reference material into bundle files and tightening the prose would substantially improve it.

Suggestions

Collapse the repetitive Rule/What/Why/Trap scaffolding into concise rule statements with one example pair each; remove the marketing-style Executive Summary and Summary tables that restate the rules.

Add an explicit numbered review workflow with validation checkpoints (e.g., parse title -> check length/verb -> check 72-char wrap -> verify footer preservation -> emit revised message only if violations found).

Move the per-rule detailed examples and tracker-format catalogs into reference files under references/ and link to them one level deep, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: an 'Executive Summary' with marketing-style framing ('definitive engineering reference', 'essential to ensuring commit log histories remain clean'), heavily padded Rule/What/Why/Trap scaffolding, and repeated restatements of the same guidance inflate the token budget well beyond what Claude needs.	2 / 5
Actionability	Concrete Do/Don't commit-message examples and explicit thresholds (60-char title, 72-char wrap) provide usable guidance, but the content is rule-prose and examples rather than copy-paste-ready commands Claude executes, leaving some gaps.	3 / 5
Workflow Clarity	Rules are grouped into chapters with rough sequence (title -> body -> footers -> review feedback), but there is no explicit review workflow with validation checkpoints or a feedback loop for the destructive/batch operation of rewriting a commit message, which the rubric caps at 3 absent validation and this falls below that bar.	2 / 5
Progressive Disclosure	The skill is a single ~500-line monolithic SKILL.md with no references/, scripts/, or assets/ bundle and no signaled one-level-deep links; detailed rule catalogs that belong in separate reference files are inlined, giving minimal structure.	2 / 5
	Total	9 / 20 Passed

Description

38%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.

The description clearly states what the skill does with concrete actions, but omits any 'Use when...' activation trigger and uses generic rather than natural user keywords. Adding an explicit trigger clause and Gerrit-specific terms would materially improve activation.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when reviewing a Git/Gerrit commit message, or when the user asks to proofread or fix commit message formatting.'

Include natural trigger terms and synonyms a user would actually say ('commit message', 'commit message review', 'commit message formatting', 'Gerrit COMMIT_MSG', 'Change-Id').

Name Gerrit explicitly in the description to sharpen distinctiveness and reduce overlap with generic git skills.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ('Proofreads and suggests structural improvements' for 'style guide compliance, completeness, and accuracy'), naming the domain and multiple specific review activities with only minor coverage gaps.	4 / 5
Completeness	It gives a clear 'what' (proofreads and suggests improvements for commit messages) but has no 'when/Use when...' trigger clause telling Claude when to activate it, capping completeness per the rubric.	2 / 5
Trigger Term Quality	It uses generic phrasing ('Git commit messages') and lacks the natural trigger phrases a user would say ('commit message', 'commit message review', 'proofread my commit', Gerrit-specific triggers), missing common synonyms.	2 / 5
Distinctiveness Conflict Risk	The Gerrit/commit-message niche is reasonably specific and unlikely to trigger for unrelated skills, but the description never names Gerrit explicitly, leaving moderate overlap risk with generic git skills.	3 / 5
	Total	11 / 20 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
skill_md_line_count	SKILL.md is long (503 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: GerritCodeReview/gerrit
Path: configs/skills/gerrit_commit_message_review/SKILL.md
Commit: 49c7e7c

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.