ads-creative

Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, scores creative diversity for Andromeda Entity-ID retrieval, and provides production priorities. Use when user says creative audit, ad creative, creative fatigue, creative diversity score, ad variation audit, ad copy, ad design, or creative review.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, highly actionable creative audit skill with specific thresholds, clear check IDs, and well-structured platform-by-platform guidance. The workflow is well-sequenced with validation checkpoints. Main weaknesses are moderate verbosity (some content Claude already knows, like basic ad copy principles) and the fact that the body inlines substantial reference material that the referenced external files (platform-specs.md, benchmarks.md, scoring-system.md) should presumably contain, creating potential duplication.

Suggestions

Move the detailed per-platform specs, format diversity matrix, and fatigue thresholds into the referenced files (platform-specs.md, benchmarks.md) and keep only summary-level guidance in SKILL.md to improve progressive disclosure and reduce token cost.

Remove the 'Ad Copy Principles' section — these are universal marketing basics Claude already knows and don't add audit-specific value.

Dimension	Reasoning	Score
Conciseness	The skill is fairly dense with useful reference tables and thresholds, but includes some unnecessary explanatory content (e.g., 'Ad Copy Principles' like 'Lead with benefit, not feature' and 'Include clear CTA' are things Claude already knows). The Andromeda section includes citation links and explanatory context that could be trimmed. Overall mostly efficient but not maximally lean.	2 / 3
Actionability	Provides highly specific, concrete thresholds (e.g., CTR declining >20% over 14 days = FAIL, frequency >5.0 prospecting), exact platform specs (9:16 1080x1920, safe zone X:40-940 Y:150-1470), minimum creative counts, scoring weights with percentages, and clear check IDs with severity levels. This is copy-paste-ready audit criteria.	3 / 3
Workflow Clarity	The Process section provides a clear numbered sequence with two explicit validation checkpoints (step 5: confirm data exists before proceeding; step 8: verify fatigue signals reference actual performance trends). The fatigue detection table includes clear threshold-to-action mappings, creating implicit feedback loops for remediation.	3 / 3
Progressive Disclosure	The skill references external files (platform-specs.md, benchmarks.md, scoring-system.md) which is good progressive disclosure design, but no bundle files are provided to confirm these exist. The SKILL.md itself is quite long (~200+ lines) with detailed tables and platform specs that could arguably be split into referenced files rather than inlined, particularly the per-platform assessment details and format diversity matrix.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 is a strong skill description that clearly defines its domain (cross-platform creative quality auditing), lists specific concrete actions (fatigue detection, compliance evaluation, diversity scoring, production priorities), and provides explicit trigger guidance with natural user terms. The inclusion of domain-specific terminology like 'Andromeda Entity-ID retrieval' adds distinctiveness, though it may be slightly jargon-heavy for some users.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: detects creative fatigue, evaluates platform-native compliance, scores creative diversity, provides production priorities, and covers ad copy/video/image/format diversity.	3 / 3
Completeness	Clearly answers both 'what' (cross-platform creative quality audit with specific capabilities like fatigue detection, compliance evaluation, diversity scoring) and 'when' (explicit 'Use when user says...' clause with multiple trigger terms).	3 / 3
Trigger Term Quality	Includes a strong set of natural trigger terms users would say: 'creative audit', 'ad creative', 'creative fatigue', 'creative diversity score', 'ad variation audit', 'ad copy', 'ad design', 'creative review'. These cover common variations well.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche in creative/ad auditing. The specific domain terms like 'creative fatigue', 'Andromeda Entity-ID retrieval', 'platform-native compliance', and 'creative diversity score' make it unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: AgriciDaniel/claude-ads
Commit: 283d9d4

Reviewed: about 1 month 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.