commit-hygiene

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

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/commit-hygiene/SKILL.md

Quality

Content

77%

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, concrete commands, and clear sequenced workflows backed by validation feedback loops. Its main weaknesses are token-inefficient redundancy (thresholds and ASCII art repeated) and a monolithic structure with no progressive disclosure into bundle files.

Suggestions

De-duplicate the size thresholds: keep a single canonical table and remove the repeated ASCII boxes and Quick Reference restatements to reclaim tokens.

Move the check-commit-size.sh and pre-commit hook scripts into a scripts/ directory and reference them from the body, enabling progressive disclosure and reducing inline bulk.

Trim explanations of concepts Claude already knows (e.g., the commit-message type table and atomic-commit rationale) down to skill-specific thresholds and commands.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful and actionable, but it restates size thresholds three times (ASCII box, warning table, Quick Reference), uses decorative ASCII-art boxes, and explains commit-message conventions Claude already knows, fitting 'Mostly efficient but includes some unnecessary explanation or could be tightened.'	2 / 3
Actionability	It provides complete, executable bash scripts (check-commit-size.sh, pre-commit hook) and copy-paste-ready git/gh commands (git add -p, gh pr create --base), matching 'Fully executable code/commands; specific examples; copy-paste ready.'	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced (stacked PRs merge in order, splitting strategies), with explicit checklists and a pre-commit validation script that returns exit codes to block oversized commits, providing a validate-then-proceed feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a monolithic ~540-line single file with no external references; content that could be split (scripts, verbose threshold tables) is inline, fitting 'Some structure but ... content that should be separate is inline.'	2 / 3
	Total	10 / 12 Passed

Description

57%

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 a terse, specific topic list for a clear niche, but it reads as nouns rather than actions and lacks an explicit "Use when" trigger clause within the description field itself. It is adequate but would benefit from action verbs and an inline trigger clause.

Suggestions

Rewrite the description as concrete actions, e.g. "Keep commits atomic, enforce PR size limits, and split large changes into stacked PRs."

Add an explicit "Use when..." trigger clause to the description field, e.g. "Use when committing code, creating PRs, or when the change set is growing large."

Include natural keyword variations users would say (e.g. "commit messages", "pull requests", "code review size") alongside the existing terms.

Dimension	Reasoning	Score
Specificity	The description lists concrete domain items ("Atomic commits, PR size limits, commit thresholds, stacked PRs") but presents them as a noun/topic list rather than naming concrete actions, matching the anchor 'Names domain and some actions, but not comprehensive.'	2 / 3
Completeness	The description field answers "what" but contains no explicit "Use when..." trigger clause; the separate frontmatter when-to-use field provides trigger guidance elsewhere, so the description itself sits at 'Has what, but when is missing or only implied.'	2 / 3
Trigger Term Quality	Terms like "commits" and "PRs" are natural, but "commit thresholds" and "stacked PRs" lean toward jargon and common variations users would actually say are missing, fitting 'Some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	The commit/PR-hygiene niche is specific and clearly distinguishable from other skills, with distinct triggers unlikely to cause conflicts, matching 'Clear niche with distinct triggers; unlikely to conflict.'	3 / 3
	Total	9 / 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 — 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: bb6195f

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.