commit-hygiene

Atomic commits, PR size limits, commit thresholds, stacked PRs

Quality

32%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/commit-hygiene/SKILL.md

Quality

Discovery

22%

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

This description is essentially a keyword list with no verbs, no explanation of what the skill does, and no guidance on when to use it. While the terms themselves are somewhat relevant to a git workflow niche, the lack of actionable descriptions and trigger clauses makes it very weak for skill selection purposes.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Enforces atomic commit practices, splits large PRs into stacked PRs, and monitors commit thresholds to keep changes reviewable.'

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about breaking up large pull requests, creating stacked PRs, keeping commits small, or managing PR size.'

Include common natural-language variations like 'pull request', 'split PR', 'small commits', 'breaking up changes', 'reviewable PRs' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description lists only noun phrases and concepts ('atomic commits', 'PR size limits', 'commit thresholds', 'stacked PRs') without describing any concrete actions. There are no verbs indicating what the skill actually does.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of actions performed and no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	Terms like 'atomic commits', 'stacked PRs', and 'PR size limits' are somewhat natural keywords a developer might use, but they are fairly specialized and miss common variations like 'pull request', 'split PR', 'small commits', or 'breaking up changes'.	2 / 3
Distinctiveness Conflict Risk	The terms are somewhat specific to git workflow practices, which provides some distinctiveness, but 'commits' and 'PRs' are broad enough to overlap with general git or code review skills.	2 / 3
	Total	6 / 12 Passed

Implementation

42%

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

The skill is highly actionable with executable scripts and concrete thresholds, but is severely undermined by extreme verbosity and redundancy. The same thresholds and guidelines appear 3-4 times in different formats (tables, ASCII boxes, checklists, quick reference). The content would benefit enormously from being split into a concise overview with references to detailed sub-files, and from eliminating the decorative ASCII art and repeated information.

Suggestions

Reduce to ~80-100 lines by eliminating duplicate threshold tables, ASCII box art, and the research findings section — keep one threshold table and one quick reference, remove the rest.

Split into multiple files: SKILL.md as a concise overview with thresholds and key commands, a separate SCRIPTS.md for the pre-commit hook and check script, and STACKED-PRS.md for the stacked PR workflow.

Remove explanatory content Claude already knows (why small PRs are better, what atomic commits are conceptually) and focus purely on the actionable thresholds, commands, and patterns.

Add an explicit validation step to the workflow: after splitting commits, verify each commit independently passes tests/builds before proceeding.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. The ASCII box art is decorative waste. Thresholds are repeated multiple times (commit size thresholds table, ideal commit box, quick reference, checklist, Claude integration table). The 'PR Size vs Defect Rate' research box and many of the 'good/bad commit' examples explain concepts Claude already understands about software engineering best practices. The same information could be conveyed in under 100 lines.	1 / 3
Actionability	Provides fully executable bash scripts (pre-commit hook, size check script), concrete git commands, specific threshold numbers, and copy-paste ready commit message examples. The partial staging workflow and stacked PR creation commands are directly usable.	3 / 3
Workflow Clarity	The commit triggers and checklists are clear, and the stacked PR workflow has a good sequence. However, there's no explicit validation/feedback loop for the core workflow — e.g., after splitting a large change into commits, there's no 'verify each commit builds/passes independently' step. The 'Claude Integration' section describes when to advise but doesn't sequence it into a clear development workflow with checkpoints.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. All content — quick reference, detailed scripts, stacked PR patterns, commit message conventions, PR guidelines — is inlined into a single massive document. The quick reference at the bottom duplicates earlier content rather than being the primary entry point with links to detailed sections elsewhere.	1 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (553 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: alinaqi/claude-bootstrap
Commit: d4ddb03

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.