Skills ad-creative

📦

ad-creative

Name: ad-creative
Author: coreyhaines31

v2.7.0 Content revision r1 High Risk ⚡ Contains scripts⚙️ External commands📁 Filesystem access🌐 Network access🔑 Env variables

Create Grounded Ad Creative at Scale

Ad teams need many platform-ready variations without losing evidence, brand fit, or review clarity. This skill creates grounded copy, concepts, test plans, and review pages.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "ad-creative" from https://skillstore.io/skills/coreyhaines31-ad-creative.md and its manifest at https://skillstore.io/api/skills/coreyhaines31-ad-creative/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/coreyhaines31-ad-creative.md Signed manifest GET /api/skills/coreyhaines31-ad-creative/manifest Signed lockfile GET /api/skills/coreyhaines31-ad-creative/lockfile

Test it

Using "ad-creative". Create Google Ads headlines for a reporting tool that saves marketing teams ten hours each week.

Expected outcome:

Automate Weekly Reports (23 characters)
Save 10 Hours Every Week (24 characters)
Reporting Without Spreadsheets (30 characters)

Using "ad-creative". Review supplied Meta results and propose the next test round.

Expected outcome:

Finding: Specific time-saved claims produced the strongest click-through rate.
Next test: Keep the time-saving angle and compare proof-led, pain-led, and action-led hooks.
Control: Preserve the current offer, audience, format, and landing page.

Using "ad-creative". Prepare three grounded concepts for client review using customer comments.

Expected outcome:

Concept one addresses the most repeated setup objection and cites the source comment.
Concept two turns an unprompted customer benefit into a proof-led carousel.
Concept three tests a new hook while keeping every product claim documented.

Security Audit

High Risk

v9 • 7/13/2026 Open versioned report

All 123 static alerts are false positives caused by escaped HTML rendering, JavaScript template literals, Markdown, relative links, and documented provider API examples. One high-severity concern remains: voice-cloning guidance does not require consent or authorization, which can enable impersonation. No prompt injection or credential exfiltration evidence was found.

Files scanned

2,683

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

references/generative-tools.md:309 references/generative-tools.md:316 references/generative-tools.md:394 references/generative-tools.md:402

Voice Cloning Lacks Consent Controls

The guide promotes cloning a brand spokesperson from short audio samples without requiring authorization. This can enable impersonation and misuse of a person's identity.

The cited lines explicitly recommend cloning a spokesperson from short recordings. The surrounding guide contains no consent or authorization requirement.

Risk Factors

⚡ Contains scripts (8)

assets/creative-review-template.html:247 assets/creative-review-template.html:267 assets/creative-review-template.html:270 assets/creative-review-template.html:275 assets/creative-review-template.html:306 assets/creative-review-template.html:355 assets/creative-review-template.html:361 assets/creative-review-template.html:390

⚙️ External commands (50)

📁 Filesystem access (8)

references/creative-review-page.md:5 references/generative-tools.md:175 SKILL.md:390 SKILL.md:394 SKILL.md:395 SKILL.md:396 SKILL.md:397 SKILL.md:78

🌐 Network access (4)

references/generative-tools.md:50 references/generative-tools.md:322 references/generative-tools.md:409 references/generative-tools.md:416

🔑 Env variables (2)

references/generative-tools.md:52 references/generative-tools.md:323

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/coreyhaines31-ad-creative/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/coreyhaines31-ad-creative/security.svg)](https://skillstore.io/skills/coreyhaines31-ad-creative?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/coreyhaines31-ad-creative?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/coreyhaines31-ad-creative/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/coreyhaines31-ad-creative.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

coreyhaines31. (2026). ad-creative security audit report (audit version 9) [Author version 2.7.0]. Skillstore. https://skillstore.io/skills/coreyhaines31-ad-creative/audits/9

BibTeX citation

@techreport{coreyhaines31-coreyhaines31-ad-creative-2026,
  author = {coreyhaines31},
  title = {ad-creative security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/coreyhaines31-ad-creative/audits/9},
  note = {Author version 2.7.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ad-creative security audit report (audit version 9)"
version: "2.7.0"
type: report
authors:
  - name: "coreyhaines31"
date-released: "2026-07-13"
url: "https://skillstore.io/skills/coreyhaines31-ad-creative/audits/9"
identifiers:
  - type: other
    value: "skillstore:coreyhaines31-ad-creative:audit:9"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Launch a Paid Campaign

Create platform-compliant ad variations from a product brief, audience definition, offer, and brand voice.

Iterate from Performance Data

Find patterns in supplied campaign results and generate focused variants that preserve winning angles.

Review a Creative Batch

Turn grounded concepts into a visual review page that clients can compare before production or launch.

Try These Prompts

Create a Starter Ad Set

Create five Meta ad concepts for [product] aimed at [audience]. Use [offer] and this brand voice: [voice]. Ask for missing essentials first.

Build Platform Variations

Use this product context: [context]. Generate Google, Meta, and LinkedIn variations. Show each angle, character count, CTA, and required disclaimer.

Iterate from Results

Analyze this ad performance table: [data]. Identify strong and weak patterns. Create twelve controlled variations and state the hypothesis behind each group.

Plan a Grounded Creative Cycle

Use these winning ads, reviews, comments, and account results: [sources]. Build an evidence-ranked roadmap, production mix, review page plan, and monthly retro framework.

Best Practices

Provide platform, audience, offer, product proof, brand voice, and compliance constraints before generation.
Ground claims in current reviews, comments, winning ads, and verified product facts.
Change one major variable per test and preserve a clear hypothesis for every variation group.

Avoid

Do not invent statistics, testimonials, endorsements, urgency, or product capabilities.
Do not generate many near-duplicate lines that test wording instead of distinct strategic angles.
Do not upload or publish creative without human review for claims, rights, consent, and platform policy.