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 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 specific git workflow domain, the lack of actionable descriptions and explicit trigger guidance makes it very weak as a skill selector.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Guides creation of atomic commits, enforces PR size limits, and manages stacked PRs for cleaner code review workflows.'

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about splitting commits, keeping PRs small, stacking pull requests, or following commit best practices.'

Include natural language variations users might say, such as 'split PR', 'break up a large PR', 'small commits', 'commit hygiene', or 'pull request best practices'.

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 explicit 'Use when...' clause and no description of actions performed—only a list of related concepts.	1 / 3
Trigger Term Quality	Terms like 'atomic commits', 'stacked PRs', and 'PR size limits' are relevant keywords a user might mention, but they are somewhat technical and miss common natural variations like 'split PR', 'break up commits', 'small pull requests', or 'commit best practices'.	2 / 3
Distinctiveness Conflict Risk	The terms are somewhat specific to git workflow practices, which provides some niche, but 'atomic commits' and 'PR size limits' could overlap with general git or code review skills without clearer boundaries.	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 highly actionable, executable content with concrete thresholds, scripts, and git commands, which is its primary strength. However, it is severely bloated—much of the content explains concepts Claude already understands (atomic commits philosophy, why small PRs are better, commit message conventions) and uses decorative ASCII boxes that waste tokens. The monolithic structure with no file references makes it poorly suited for efficient context window usage.

Suggestions

Cut the content by 60%+: remove the Core Philosophy ASCII boxes, the 'Don't Wait For' list, the good/bad commit examples, the research findings section, and commit message conventions—Claude already knows all of this. Focus on the thresholds table, the scripts, and the stacked PR commands.

Extract the pre-commit hook script and the check-commit-size.sh script into separate referenced files (e.g., scripts/pre-commit-hook.sh) and link to them from a concise overview.

Replace ASCII art boxes with simple markdown headers or bold text to save significant token budget.

Add an explicit feedback loop to the workflow: after splitting commits, verify each commit independently compiles/passes tests before proceeding to the next.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. The ASCII box art is decorative waste. Concepts like 'atomic commits,' 'commit early commit often,' PR size guidelines, and commit message conventions are well-known to Claude. The 'PR Size vs Defect Rate' research summary, the 'Don't Wait For' list, and extensive good/bad commit examples all explain things Claude already knows. Much of this could be condensed to thresholds + scripts.	1 / 3
Actionability	Provides fully executable bash scripts (pre-commit hook, size check script), concrete git commands, specific numeric thresholds, and copy-paste ready stacked PR workflows with gh CLI commands. The partial staging commands and commit message format are immediately usable.	3 / 3
Workflow Clarity	The commit triggers and thresholds are clear, and the stacked PR creation sequence is well-ordered. However, there's no explicit validation/feedback loop for the overall workflow—e.g., after splitting and committing, there's no 'verify the split was clean' 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	Monolithic wall of text with no references to external files. Everything is inline—the pre-commit hook script, the check script, the stacked PR guide, the commit message format—all of which could be split into separate referenced files. For a skill this long, the lack of any structural decomposition is a significant weakness.	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: 65efb33

Reviewed: 6 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.