ad-creative

Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization.

Quality

—

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.

The body is highly actionable with concrete specs, commands, and templates, and workflows include explicit validation checkpoints. It loses points for restating general copywriting knowledge Claude already has and for duplicating platform specs inline rather than keeping them solely in the reference file.

Suggestions

Move the per-platform character-limit tables out of the body and into references/platform-specs.md, keeping only a brief pointer plus the most-used limits inline, to remove duplication and improve progressive disclosure.

Trim the 'Writing Quality Standards' and 'Common Mistakes' sections to skill-specific operational guidance, dropping general copywriting craft (active vs. passive voice, specificity over vagueness) that Claude already knows.

Convert the inline Platform Specs summary tables into a concise cross-platform comparison (e.g., a single row of headline/primary-text limits per platform) so the body stays a true overview pointing to the detailed reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly well-organized with tables and templates, but sections like 'Writing Quality Standards' and 'Common Mistakes' restate general copywriting craft (e.g., 'Specific over vague', 'Active voice over passive') that Claude already knows, so it could be tightened.	2 / 3
Actionability	Provides concrete executable guidance throughout — exact per-platform character-limit tables, real CLI commands ('node tools/clis/google-ads.js reports get --type ad_performance --date-range last_30_days'), and copy-paste-ready output templates (CSV header, iteration log).	3 / 3
Workflow Clarity	Two modes are clearly sequenced with a core-loop diagram; 'Validate Against Specs' is an explicit checkpoint shown in action (an over-limit headline is flagged and trimmed), and batch generation includes a quality-filter step that removes over-limit, duplicate, and policy-violating items.	3 / 3
Progressive Disclosure	Both referenced files (platform-specs.md, generative-tools.md) exist and are clearly signaled one level deep, but the inline 'Platform Specs' section duplicates much of platform-specs.md — content that should live only in the reference is duplicated in the body.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 strong: it states concrete actions, names platforms, gives broad natural trigger vocabulary, and includes an explicit 'Use when' clause. The only issue is second-person voice, which costs one point on specificity per the rubric's voice guideline.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Create, iterate, and scale paid ad creative', 'generating headlines, descriptions, primary text, or large sets of ad variations') that would warrant a 3, but the description uses second-person voice ('Use when generating...') which the rubric penalizes by reducing the specificity score by one.	2 / 3
Completeness	Explicitly answers what ('Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms') and when ('Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'headlines, descriptions, primary text', 'ad variations', 'testing and performance optimization' — across multiple phrasings rather than narrow jargon.	3 / 3
Distinctiveness Conflict Risk	The paid-ad-creative niche on named platforms with performance-optimization framing is clearly distinguishable from general copywriting skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 2aaaf59

Reviewed: 2 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.