paste this link into your ai. it will know what to do.

/skills/indranilbanerjee-ad-creative

Generate 3-5 ad copy variations per platform — headlines, descriptions, and CTAs formatted to Google, Meta, LinkedIn, TikTok, X, and Pinterest specs — each scored 1-10 with policy-compliance flags, A/B testing groupings, and a message-match check against the landing page. Triggers on \"/digital-marketing-pro:ad-creative\", \"write ad copy for Meta\", \"give me RSA headline variations\", \"we need LinkedIn ad copy\", \"draft TikTok ad creative\". Reads the brand profile, guidelines, and compliance rules; routes video ad scripts to /digital-marketing-pro:video-script and gates AI-generated visua

kindskill

last tended2026-11-01

written byindranilbanerjee

sourcegithub.com/indranilbanerjee/digital-marketing-pro

kept currentwith its source · last read 2026-11-03

savedonce, into someone's innernet

brought here bykt

reuseMIT

yours?it stays under your name. to change it or take it down, write to connect@innernet.live

reading4 min

/digital-marketing-pro:ad-creative

Purpose

Generate high-performing ad copy variations tailored to specific platforms and formats. Each variation is scored for quality and compliance, with recommendations for testing strategy.

Input Required

The user must provide (or will be prompted for):

Product/service: What is being advertised
Platform(s): Google Ads, Meta (Facebook/Instagram), LinkedIn, TikTok, X, Pinterest
Ad format: RSA, single image, carousel, video script, story, etc. For video ad scripts (6s bumper, 15s skippable, 30s spot, UGC-style), route to /digital-marketing-pro:video-script — its step 2.4 carries the per-format structural rules (the 5-second skip deadline, one-message bumpers, native-style disclosure) and its output passes the /check gate. This skill owns the copy layer around the video: headlines, descriptions, and CTAs.
Campaign objective: Awareness, traffic, leads, conversions, app installs
Target audience: Who the ads are for
Key offer/CTA: Promotion, value prop, or desired action
Landing page URL: Where the ad will drive traffic (optional)

Process

Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions and relevant category files. Check for custom templates at ~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.
Identify platform-specific constraints: character limits, format requirements, policy restrictions. For X, read the ad-text rows in scripts/paid_products.json (reported: no hashtag in the ad text, at most one emoji, the URL in the card, not the text)
Generate 3-5 ad copy variations per platform, each with a distinct angle (benefit, urgency, social proof, curiosity, direct)
Score each variation on: brand alignment, clarity, emotional impact, CTA strength, policy compliance
Flag any potential policy violations (restricted claims, prohibited language)
Recommend A/B testing groupings and priority order
If landing page URL is provided, check message match between ad and page

Output

Per platform, a set of ad copy variations including:

Headlines, descriptions, and CTAs formatted to platform specifications
Quality score (1-10) with reasoning per variation
Policy compliance check with flagged issues
A/B testing recommendation with hypothesis for each test
Message match assessment (if landing page provided)
Creative direction notes for visual/video assets (see AI image/video generation guidance below)

AI image & video generation guidance (May 2026)

When the brief includes static visuals or short-form video, recommend the model that fits the use case and call out the compliance overhead:

Asset type	Recommended model (May 2026)	When to use	Compliance note
Product hero stills, lifestyle photography, e-commerce tiles	Google Nano Banana Pro (Gemini 3 Pro Image, multi-image composition, character/object consistency)	Strong text rendering inside images (logos, on-pack copy), brand-character consistency across a campaign, high-fidelity product realism.	Outputs ship with SynthID watermarking by default; ALSO sign with C2PA via `/digital-marketing-pro:c2pa-metadata` before any EU distribution.
Short-form social video (≤8s reels, organic vertical)	A video model with synchronized native audio. The model depends on the backend: resolve `latest-video-google` (Vertex AI) or `latest-video-gemini-api` (Gemini API) with `resolve_model.py`; a Gemini API key alone can't call the Vertex model	Reels, TikTok, Shorts cut-downs, ad-creative experimentation.	Synthetic-voice / synthetic-human content must carry a visible deepfake disclosure under EU Article 50 — see `skills/context-engine/compliance-rules.md` §1.1b.
Long-form video with native audio / multi-modal storytelling	Gemini Omni (multimodal generation, May 2026 I/O launch — text + image + audio + video unified)	Connected-content campaigns where a single brief produces a hero film, social cut-downs, audio version, and stills consistently. Best for brands with disciplined creative governance — Omni's range outpaces most brand-safety review processes.	Default Omni outputs carry SynthID + Gemini provenance markers. Add C2PA before EU publish. Run synthetic-person outputs past Legal — Omni's photoreal humans frequently hit "substantial AI manipulation" thresholds under Article 50.
Static image — fast iteration / mood-boarding	OpenAI gpt-image-2, Midjourney v7, Adobe Firefly	Internal mood boards, concept exploration. Not for shipped EU creative without C2PA.	Adobe Firefly applies Content Credentials to images it fully generates ("where 100% of the pixels are generated using Adobe Firefly", helpx.adobe.com); for the others, check the file with `embed-c2pa.py --verify` instead of assuming. Before EU publish, sign with `/digital-marketing-pro:c2pa-metadata` to add the `c2pa.ai-disclosure` assertion.

Workflow recommendation:

Brief the visual concept in this skill's output (subject, composition, brand-character constraints, on-pack text if any).
Hand the visual spec to whichever production track owns image/video — your design team, any AI image/video tool (the model table above maps use-case → generator), or a connected design platform (e.g. the Canva / Figma MCP connectors listed in /digital-marketing-pro:integrations). The spec is deliberately tool-agnostic: any production track can consume it unchanged.
Treat all AI-generated visuals as Article 50 in-scope until proven otherwise. The pre-publish gate (/digital-marketing-pro:check) blocks unsigned AI assets for EU-targeted campaigns.

Agents Used

content-creator — Ad copy generation, angle development, CTA crafting
media-buyer — Platform specs, policy compliance, testing strategy
brand-guardian — Voice alignment, compliance review, claim verification

keep it where your ai can reach it.

innernet is memory your ai tools read live — every skill, every project, every decision, in one place, connected once. save this skill to yours, or publish one of your own as a link like this.

save it to your innernet see every skill

Input Required

The user must provide (or will be prompted for):

Product/service: What is being advertised

Platform(s): Google Ads, Meta (Facebook/Instagram), LinkedIn, TikTok, X, Pinterest

Ad format: RSA, single image, carousel, video script, story, etc. For video ad scripts (6s bumper, 15s skippable, 30s spot, UGC-style), route to /digital-marketing-pro:video-script — its step 2.4 carries the per-format structural rules (the 5-second skip deadline, one-message bumpers, native-style disclosure) and its output passes the /check gate. This skill owns the copy layer around the video: headlines, descriptions, and CTAs.

Campaign objective: Awareness, traffic, leads, conversions, app installs

Target audience: Who the ads are for

Key offer/CTA: Promotion, value prop, or desired action

Landing page URL: Where the ad will drive traffic (optional)

Process

Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions and relevant category files. Check for custom templates at ~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.

Identify platform-specific constraints: character limits, format requirements, policy restrictions. For X, read the ad-text rows in scripts/paid_products.json (reported: no hashtag in the ad text, at most one emoji, the URL in the card, not the text)

Generate 3-5 ad copy variations per platform, each with a distinct angle (benefit, urgency, social proof, curiosity, direct)

Score each variation on: brand alignment, clarity, emotional impact, CTA strength, policy compliance

Flag any potential policy violations (restricted claims, prohibited language)

Recommend A/B testing groupings and priority order

If landing page URL is provided, check message match between ad and page

Output

Per platform, a set of ad copy variations including:

Headlines, descriptions, and CTAs formatted to platform specifications

Quality score (1-10) with reasoning per variation

Policy compliance check with flagged issues

A/B testing recommendation with hypothesis for each test

Message match assessment (if landing page provided)

Creative direction notes for visual/video assets (see AI image/video generation guidance below)

AI image & video generation guidance (May 2026)

When the brief includes static visuals or short-form video, recommend the model that fits the use case and call out the compliance overhead:

Asset type	Recommended model (May 2026)	When to use	Compliance note
Product hero stills, lifestyle photography, e-commerce tiles	Google Nano Banana Pro (Gemini 3 Pro Image, multi-image composition, character/object consistency)	Strong text rendering inside images (logos, on-pack copy), brand-character consistency across a campaign, high-fidelity product realism.	Outputs ship with SynthID watermarking by default; ALSO sign with C2PA via `/digital-marketing-pro:c2pa-metadata` before any EU distribution.
Short-form social video (≤8s reels, organic vertical)	A video model with synchronized native audio. The model depends on the backend: resolve `latest-video-google` (Vertex AI) or `latest-video-gemini-api` (Gemini API) with `resolve_model.py`; a Gemini API key alone can't call the Vertex model	Reels, TikTok, Shorts cut-downs, ad-creative experimentation.	Synthetic-voice / synthetic-human content must carry a visible deepfake disclosure under EU Article 50 — see `skills/context-engine/compliance-rules.md` §1.1b.
Long-form video with native audio / multi-modal storytelling	Gemini Omni (multimodal generation, May 2026 I/O launch — text + image + audio + video unified)	Connected-content campaigns where a single brief produces a hero film, social cut-downs, audio version, and stills consistently. Best for brands with disciplined creative governance — Omni's range outpaces most brand-safety review processes.	Default Omni outputs carry SynthID + Gemini provenance markers. Add C2PA before EU publish. Run synthetic-person outputs past Legal — Omni's photoreal humans frequently hit "substantial AI manipulation" thresholds under Article 50.
Static image — fast iteration / mood-boarding	OpenAI gpt-image-2, Midjourney v7, Adobe Firefly	Internal mood boards, concept exploration. Not for shipped EU creative without C2PA.	Adobe Firefly applies Content Credentials to images it fully generates ("where 100% of the pixels are generated using Adobe Firefly", helpx.adobe.com); for the others, check the file with `embed-c2pa.py --verify` instead of assuming. Before EU publish, sign with `/digital-marketing-pro:c2pa-metadata` to add the `c2pa.ai-disclosure` assertion.

Workflow recommendation:

Brief the visual concept in this skill's output (subject, composition, brand-character constraints, on-pack text if any).

Hand the visual spec to whichever production track owns image/video — your design team, any AI image/video tool (the model table above maps use-case → generator), or a connected design platform (e.g. the Canva / Figma MCP connectors listed in /digital-marketing-pro:integrations). The spec is deliberately tool-agnostic: any production track can consume it unchanged.

Treat all AI-generated visuals as Article 50 in-scope until proven otherwise. The pre-publish gate (/digital-marketing-pro:check) blocks unsigned AI assets for EU-targeted campaigns.