commit-hygiene

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

Quality

32%

Does it follow best practices?

Impact

—

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 list of keywords with no verbs, no explanation of what the skill does, and no guidance on when to use it. It fails to communicate concrete capabilities and lacks the explicit trigger clause needed for Claude to reliably select this skill from a pool of alternatives.

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 with trigger scenarios, e.g., 'Use when the user asks about breaking up large pull requests, creating stacked PRs, keeping commits small, or managing PR size limits.'

Include common natural-language variations users might say, such as 'pull request', 'split PR', 'small commits', 'reviewable changes', or 'breaking up changes'.

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 user might mention, but they are fairly technical 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 a git/PR workflow niche, which provides some distinctiveness, but without clear actions or triggers it could overlap with general git workflow 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 provides genuinely actionable guidance with executable scripts and concrete thresholds, which is its main strength. However, it is severely bloated — repeating the same thresholds in at least 4 different formats (tables, ASCII boxes, quick reference, checklists), explaining concepts Claude already knows (what atomic commits are, conventional commit types), and including decorative ASCII art that wastes tokens. The content should be split across multiple files with SKILL.md serving as a concise overview.

Suggestions

Cut content by at least 60%: remove ASCII box art, eliminate redundant threshold presentations (keep one table), and drop explanations of concepts Claude already knows (conventional commits, what atomic commits are, git basics).

Split into multiple files: move the pre-commit hook script to a referenced file (e.g., hooks/pre-commit-size-check.sh), the stacked PR guide to STACKED_PRS.md, and the commit message format to COMMIT_FORMAT.md. Keep SKILL.md as a concise overview with references.

Consolidate the 4+ redundant threshold sections (Commit Size Thresholds table, Ideal Commit box, Quick Reference thresholds, Checklist thresholds) into a single authoritative table.

Add an explicit feedback loop to the Claude Integration section: check size → advise → commit → verify commit size → proceed, rather than just listing when to suggest committing.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. The ASCII box diagrams are decorative padding. Research statistics, multiple redundant threshold tables, and repeated checklists all convey the same information multiple ways. Claude already understands git, atomic commits, and conventional commit formats — most of this is explaining known concepts.	1 / 3
Actionability	Provides fully executable bash scripts (pre-commit hooks, size check scripts), concrete git commands, and specific threshold numbers. The partial staging workflow and stacked PR creation commands are copy-paste ready.	3 / 3
Workflow Clarity	The commit triggers and thresholds are clear, and the stacked PR sequence is well-ordered. However, there's no explicit validation/feedback loop for the overall workflow — the 'Claude Integration' section describes when to advise but doesn't define a clear check→act→verify cycle. The checklists at the end partially compensate but are disconnected from the workflow steps.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. Content like the pre-commit hook script, the research findings, the stacked PR pattern, and the commit message format guide could each be separate referenced files. Everything is inlined, making the skill far too long for a single SKILL.md.	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 (552 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: 7e5f7a2

Reviewed: 3 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.