CtrlK
BlogDocsLog inGet started
Tessl Logo

ads-creative-development

How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.

71

Quality

87%

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

The canonical home for this skill is ads-creative-development in rampstackco/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%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, actionable tactical playbook with excellent progressive disclosure and concrete numeric guidance throughout. The main drag is mild repetition (the hook thesis restated) and a few workflows whose checkpoints are implicit rather than explicit.

Suggestions

Trim the Closing section and the repeated 'hook is the whole game' framing — the point is made once in the Hook patterns section — to recover token budget.

Make the fatigue-refresh and testing-waterfall checkpoints explicit (e.g., 'advance a hook only after it reaches 50+ conversions or 1M+ impressions') in the main body rather than deferring all thresholds to references.

Add one ready-to-paste variation naming example per platform to the Variation systems section so producers can act without opening the reference.

DimensionReasoningScore

Conciseness

Dense tactical content where most tokens earn their place, but with minor padding — 'the hook is the whole game' is restated in the Hook patterns section and again in the Closing section, which largely repeats earlier points.

4 / 5

Actionability

Highly concrete guidance — the 0-15s pacing table, 1×5×4×3×2=120 variation math, a naming-convention example, per-stage variant counts, fatigue thresholds (frequency >4-5, CTR decline 30%+), and platform character limits — with only minor gaps where ready-to-ship copy templates live in references rather than inline.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced (5-stage sequential testing waterfall, 10-consideration framework) with a decision gate ('ship as planned, revise the plan, or stop because a precondition is missing') and a fatigue decision tree; no destructive/batch validation cap applies, but a few checkpoints are implicit.

4 / 5

Progressive Disclosure

Clear overview in SKILL.md with seven well-signaled one-level-deep reference links, all of which resolve to real files in ./references/, plus a consolidated 'Reference files' index — content is appropriately split and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

96%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, comprehensive description that covers specific capabilities, natural trigger terms, and explicit what/when guidance in third-person voice. Only marginal overlap risk with closely related paid-media or brand-voice skills keeps distinctiveness just below the top anchor.

DimensionReasoningScore

Specificity

Lists multiple specific concrete capabilities — 'Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment ... and platform-specific creative norms' — giving comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly answers both what ('How to produce ad creative that converts at performance scale' plus enumerated capabilities) and when ('Triggers on ...', 'Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting').

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage with synonyms and platform variants: 'ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, ... creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (performance ad creative production) with distinct triggers and minimal conflict risk; minor overlap risk with adjacent paid-media/brand-voice skills, which are named separately as out of scope.

4 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rampstackco/claude-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.