commit-hygiene

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

Quality

65%

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 ./skills/commit-hygiene/SKILL.md

Quality

Content

71%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 is highly actionable with executable scripts and concrete thresholds, but it is verbose due to heavy threshold repetition and ASCII decoration, and it is a long monolithic file with no progressive disclosure into bundle files.

Suggestions

Deduplicate thresholds: state them once in the size-guidelines table and have other sections (quick reference, checklist) reference it rather than re-listing the numbers.

Move the check-commit-size.sh and pre-commit hook scripts into a scripts/ bundle and reference them, trimming the SKILL.md body.

Replace the decorative ASCII-art boxes with compact bullet lists to cut tokens without losing the message.

Dimension	Reasoning	Score
Conciseness	Mostly useful and it assumes git competence, but the same thresholds are restated four times (table, ASCII boxes, quick reference, checklist) and the decorative ASCII-art boxes add tokens without information.	3 / 5
Actionability	Fully executable, copy-paste-ready bash scripts (check-commit-size.sh, pre-commit hook) plus specific git commands and concrete numeric thresholds cover the common cases.	5 / 5
Workflow Clarity	Clear check-status → assess-against-threshold → commit-or-split flow with checklists and explicit commit triggers; minor validation gaps but no destructive/batch operation requiring a validate-fix-retry loop.	4 / 5
Progressive Disclosure	Well-sectioned but a single ~540-line monolithic file with executable scripts inlined that would be better as bundle files, and no one-level-deep references to separate materials.	3 / 5
	Total	15 / 20 Passed

Description

58%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 is specific and well-scoped to commit hygiene, but it is a noun-phrase capability list rather than a full sentence and omits explicit "when to use" trigger guidance from the description field itself.

Suggestions

Add an explicit "Use when..." trigger clause to the description (e.g., "Use when committing code, creating PRs, or when a change set is growing large") so it answers both what and when.

Expand trigger terms with synonyms users actually say — "git", "pull requests", "diff", "change set" — to improve keyword coverage.

Reword as a third-person sentence ("Keeps commits atomic and PRs reviewable...") rather than a comma-separated noun list.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — "Atomic commits, PR size limits, commit thresholds, stacked PRs" — naming the domain and multiple specific items, with only minor coverage gaps.	4 / 5
Completeness	The "what" is clear from the capability list, but the description lacks an explicit "Use when..." trigger clause; the when-guidance lives in a separate when-to-use field, capping completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms like "commits" and "PRs" but misses common variations/synonyms a user might say ("git", "pull requests", "diff", "changes").	3 / 5
Distinctiveness Conflict Risk	Scoped to commit/PR hygiene with distinct triggers (atomic commits, stacked PRs), mostly distinct with only minor overlap risk against general git skills.	4 / 5
	Total	14 / 20 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 — 13 / 16 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/commit-hygiene/SKILL.md
Commit: abc600e

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.