Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-ab-critique-dimensions
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Passed 18 of 21 test cases with the skill, and 8 of 21 without it.
and 12 more in the full report
11 fixed8 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
In auditing `nw-refactor.md`, one high-severity dimension failed ('Template Compliance') while all other dimensions passed. What is the required review verdict?
| Checked | Without skill | With skill |
|---|---|---|
| The verdict field value is revisions_needed | Missed | Passed |
The instructions your model reads when the skill loads.
Use these dimensions when reviewing or validating agent definitions.
Does the agent follow official Claude Code format?
Check: YAML frontmatter with name and description (required) | Markdown body as system prompt | No embedded YAML config blocks | No activation-instructions or IDE-FILE-RESOLUTION sections | Skills referenced in frontmatter, not inline
Severity: High -- non-compliant agents may not load correctly.
Check: Core definition under 400 lines | Domain knowledge in Skills | Single clear responsibility | No monolithic sections (>50 lines without structure) | No redundant Claude default behaviors
Measurement: wc -l {agent-file}. Target: 200-400 lines.
Severity: High -- oversized agents suffer context rot.
Does the agent specify only what diverges from Claude defaults?
Check: No file operation instructions | No generic quality principles ("be thorough") | No tool usage guidelines | Core principles are domain-specific and non-obvious | Each instruction justifies why Claude wouldn't do this naturally
Severity: Medium -- redundant instructions waste tokens, cause overtriggering.
Check: Tools restricted via frontmatter tools field | maxTurns set | No prose-based security layers (use hooks) | No embedded enterprise safety frameworks | permissionMode set for risky actions
Severity: High -- prose safety is ineffective and token-wasteful.
Check: No "CRITICAL:", "MANDATORY:", "ABSOLUTE" language | Direct statements ("Do X" not "You MUST X") | Affirmative phrasing ("Do Y" not "Don't do X") | Consistent terminology | No repetitive emphasis
Severity: Medium -- aggressive language causes overtriggering on Opus 4.6.
test cases passed, vs 8 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.