Skip to content
Back to skills

Ad Units

ASecurity

Concept, write, produce, batch, review, and iterate paid creative in platform-native formats: static, carousel, responsive search assets, short-form vertical video, motion, creator-led, and demo units, organized by concept ID with a bounded test matrix and a performance readout. Use for ad copy, hooks, creative strategy, production briefs, and creative fatigue; use paid-media for campaign structure, budgets, and account changes.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
ai-agentsperformance

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 24, 2026

npx -y skills add MTEnt/special-skills --skill ad-units --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ad Units?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ad Units
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mtent-ad-units/badge)](https://www.skillsdirectory.com/skills/mtent-ad-units)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ad-units
description: Concept, write, produce, batch, review, and iterate paid creative in platform-native formats: static, carousel, responsive search assets, short-form vertical video, motion, creator-led, and demo units, organized by concept ID with a bounded test matrix and a performance readout. Use for ad copy, hooks, creative strategy, production briefs, and creative fatigue; use paid-media for campaign structure, budgets, and account changes.
license: MIT
metadata:
  version: "2.0.0"
  author: MTEnt
---

# Ad Units

Develop materially different concepts before multiplying variants. A crop, color, or opening synonym is not a new strategic idea.

If `.agents/marketing-context.md` exists, read it first; it is the truth file every skill in this hub shares, and its evidence states are constraints. Read [creative-system.md](references/creative-system.md) for grounded inputs, the concept model, hooks, formats, production specs, batching, iteration, and review. Read [format-blueprints.md](references/format-blueprints.md) when the request needs production-ready units.

## Operating contract

1. Inspect product behavior, customer language, objections, offer, proof, organic work, current ads, permitted competitor libraries, landing pages, and performance by concept.
2. Verify current placement, asset, text, disclosure, and policy specifications from official platform sources.
3. Define concept, audience, promise, mechanism, proof, CTA, visual device, and format before writing variants.
4. Produce complete platform-ready copy and production specifications with IDs, rights, disclosure, accessibility, and destination.
5. Build the smallest test matrix that can answer the decision, then read results at the concept level with attribution limits preserved.

Do not fabricate product states, testimonials, results, documentary scenes, identities, or platform eligibility, or impersonate a private message format.

## Return

Research summary, concept territories, selected hypotheses, complete copy, production briefs, asset matrix and manifest, review presentation, rights state, test plan, QA, and learning record.

Files in this skill

  • SKILL.md2.1 KB
  • agents/openai.yaml241 B
  • references/creative-system.md4 KB
  • references/format-blueprints.md3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…