crap

Rank functions by CRAP score (complexity × lack of real test coverage) on the current branch, then propose either a refactor or missing tests for the worst offender. Use when the user runs /crap or asks to find risky, complex, poorly-tested code.

Quality

86%

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

Quality

Content

85%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 workflow is exceptionally actionable and clearly sequenced with strong validation feedback loops. The main weakness is progressive disclosure: the skill leans on detectors.md, refactor-playbook.md, and crap.py, but no bundle files ship with the skill.

Suggestions

Ship the referenced bundle: create references/detectors.md and references/refactor-playbook.md (and the crap.py script under scripts/) so the load-on-demand pointers resolve to real files.

If crap.py is intentionally external, state where it comes from / how it is installed instead of referencing it as a bundled ${CLAUDE_SKILL_DIR} artifact.

Consider inlining a minimal detectors quick-reference (the 2-3 most common languages) so the workflow is usable even before the referenced files are loaded.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, command-driven content; the CRAP formula and Savoia-deviation notes earn their place as domain context Claude lacks, with only minor trims possible.	4 / 5
Actionability	It provides copy-paste-ready commands (crap.py lizard/filter/cache-split/score), concrete config YAML, JSON shapes, and exit codes that cover the common cases end to end.	5 / 5
Workflow Clarity	Nine explicitly sequenced steps include validation checkpoints (empty scope exits, empty survivors skip to step 8, missing tools stop) and a tests-first guardrail with an AskUserQuestion confirmation before applying changes.	5 / 5
Progressive Disclosure	The body is well sectioned and signals one-level-deep load-on-demand references (detectors.md, refactor-playbook.md) and a crap.py script, but none of those bundle files actually exist in references/ or scripts/, so the disclosure is broken.	3 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong description that crisply states a distinctive purpose and gives an explicit, natural-language trigger clause. Minor gains are possible by enumerating a few more concrete actions or synonyms.

Dimension	Reasoning	Score
Specificity	"Rank functions by CRAP score" and "propose either a refactor or missing tests for the worst offender" name several concrete actions, though the action list is focused rather than comprehensive.	4 / 5
Completeness	It explicitly answers both what (rank by CRAP score, propose refactor or tests) and when ("Use when the user runs /crap or asks to find risky, complex, poorly-tested code") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use when the user runs /crap or asks to find risky, complex, poorly-tested code" supplies natural phrasings users would say, plus the command token, but omits some synonyms.	4 / 5
Distinctiveness Conflict Risk	The CRAP-score niche and /crap command trigger give it a clear, distinct purpose with minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: belchman/claude-skills
Path: plugins/agentic-engineering/skills/crap/SKILL.md
Commit: 77a9e6b

Reviewed: 11 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.