CtrlK
BlogDocsLog inGet started
Tessl Logo

paid-creative-ai

When the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid media with AI tools. Also use when the user mentions 'ad creative,' 'performance creative,' 'creative testing,' 'creative fatigue,' 'Meta ads,' 'Google ads,' 'TikTok ads,' 'AI ads,' 'ad budget,' 'ROAS,' 'Advantage+,' or 'Performance Max.' This skill covers AI-powered paid creative from generation through performance optimization. Do NOT use for technical implementation, code review, or software architecture.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 richly detailed, highly actionable strategy skill body with strong sequenced workflows and validation guards. Its main weaknesses are length/redundancy and underuse of the reference file for benchmark data.

Suggestions

Move Section 7 (Platform Cost Benchmarks) and other reference-grade tables into references/quick-reference.md to slim the main body and reduce token load.

De-duplicate the weekly cadence/checklist, which appears in both the body (Creative Refresh Pipeline) and references/quick-reference.md.

Add an explicit validate->fix->retry loop for the production quality filter and asset replacement steps to push workflow clarity to 5.

DimensionReasoningScore

Conciseness

Mostly efficient tables and concrete operational guidance, but the ~460-line body inlines reference-grade benchmark tables (Section 7) and a weekly cadence that partly duplicates references/quick-reference.md, so it could be tightened and offloaded.

3 / 5

Actionability

Highly concrete and executable throughout: specific budgets ($20-50/day per concept), thresholds (hook rate >25%, CTR >1%), asset limits (15 headlines x 30 char), and a day-by-day 5-step production workflow.

5 / 5

Workflow Clarity

Multiple clearly sequenced frameworks (5-step production, 3-phase testing) with explicit decision/kill rules and a 'Never kill before minimum data' validation guard, though no single validate->fix->retry loop is spelled out.

4 / 5

Progressive Disclosure

A one-level-deep reference (references/quick-reference.md) is clearly signaled, but the bulk of reference-grade content stays inline in the main file and overlaps with the reference, leaving organization gaps.

3 / 5

Total

15

/

20

Passed

Description

100%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, third-person description with explicit what/when guidance, comprehensive natural trigger terms, and a clear negative boundary. It is specific, distinguishable, and well-scoped.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid media with AI tools') spanning generation through optimization, giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what ('covers AI-powered paid creative from generation through performance optimization') and when ('When the user wants...', 'Also use when the user mentions...'), plus a negative boundary clause.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including platform names, KPIs, and product names ('ad creative,' 'Meta ads,' 'ROAS,' 'Advantage+,' 'Performance Max') that users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Clear paid-creative niche with distinct triggers and an explicit 'Do NOT use for technical implementation, code review, or software architecture' boundary that minimizes conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
Reviewed

Table of Contents

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.