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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-ad-creative/SKILL.md

Quality

Content

67%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.

A well-structured, highly actionable skill with concrete specs, worked examples, and validation checkpoints across both generate and iterate modes. Its main weaknesses are redundancy — generic copywriting advice and content duplicated from the reference files — and minor validation gaps in the iteration and data-pull workflows.

Suggestions

Trim the 'Writing Quality Standards' section to a short do/don't list or move it to a reference file — it re-teaches copywriting fundamentals (benefits over features, active voice) that Claude already knows.

De-duplicate the platform spec tables and the generative-tool list against references/platform-specs.md and references/generative-tools.md, keeping only a compact summary table in the body and pointing to the references for detail.

Add an explicit validation checkpoint to the iteration workflow (re-check new creative against character limits before delivering) and either verify or remove the non-existent tools/clis/google-ads.js command path.

Dimension	Reasoning	Score
Conciseness	Sections like "Headlines That Click" re-explain copywriting basics Claude already knows ("Benefits ... over features", "Active voice ... over passive"), and the platform spec tables and generative-tool lists duplicate content that lives in the reference files, fitting the mostly-efficient-but-could-be-tightened anchor.	3 / 5
Actionability	Concrete guidance dominates: character-limit tables, a worked output example with character counts and a trimmed over-limit alternative, a CSV upload template, and a runnable CLI command — but the example command path (tools/clis/google-ads.js) is not present in the bundle and tool guidance is hedged ("Use available Google Ads integrations"), so it falls short of fully copy-paste ready.	4 / 5
Workflow Clarity	Both modes have numbered steps, a stated core loop, an explicit "Validate Against Specs" checkpoint with over-limit-to-trimmed feedback, and a quality-filter checklist; however, the iteration workflow's steps don't re-validate the new creative and the data-pull workflow has no verification step, leaving minor checkpoint gaps.	4 / 5
Progressive Disclosure	Two real, one-level-deep, clearly signaled references (references/platform-specs.md, references/generative-tools.md) with summaries of their contents, but the body inlines full platform spec tables and a tool list that duplicate those reference files, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

88%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 with a clear third-person statement of capabilities and an explicit, concrete 'Use when' trigger clause covering multiple ad formats and platforms. The only gaps are a few missing natural synonyms ('ad copy', 'ad text') and slight overlap risk with general copywriting skills.

Dimension	Reasoning	Score
Specificity	"Create, iterate, and scale" names multiple concrete actions, and the description lists the specific deliverables ("headlines, descriptions, primary text, ... large sets of ad variations") across named platforms, matching the comprehensive-coverage anchor rather than the minor-gaps anchor.	5 / 5
Completeness	It explicitly answers both what ("Create, iterate, and scale paid ad creative") and when ("Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural terms users would say are present ("headlines", "descriptions", "ad variations", platform names, "testing"), but common synonyms such as "ad copy", "ad text", or "Facebook ads" are missing, which fits the good-coverage-with-a-few-gaps anchor rather than comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The paid-ad niche is clear with named platforms, but triggers like "generating headlines, descriptions" could plausibly overlap a generic copywriting skill, matching the mostly-distinct/minor-overlap anchor rather than minimal conflict risk.	4 / 5
	Total	18 / 20 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: boisenoise/skills-collections
Path: skills/antigravity-ad-creative/SKILL.md
Commit: 7390864

Reviewed: 5 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.