{"id":"ad-creative","name":"ad-creative","summary":"プラットフォームごとに3〜5種類の広告コピーバリエーションを生成する。見出し、説明、CTAはGoogle、Meta、LinkedIn、TikTok、X、Pinterestの仕様に合わせてフォーマットされ、それぞれポリシー準拠フラグ、A/Bテストグループ、ランディングページとのメッセージマッチチェックで1〜10点を獲得…","body":"# /digital-marketing-pro:ad-creative\n\n## Purpose\n\nGenerate high-performing ad copy variations tailored to specific platforms and formats. Each variation is scored for quality and compliance, with recommendations for testing strategy.\n\n## Input Required\n\nThe user must provide (or will be prompted for):\n\n- **Product/service**: What is being advertised\n- **Platform(s)**: Google Ads, Meta (Facebook/Instagram), LinkedIn, TikTok, X, Pinterest\n- **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.\n- **Campaign objective**: Awareness, traffic, leads, conversions, app installs\n- **Target audience**: Who the ads are for\n- **Key offer/CTA**: Promotion, value prop, or desired action\n- **Landing page URL**: Where the ad will drive traffic (optional)\n\n## Process\n\n1. **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.\n2. Identify platform-specific constraints: character limits, format requirements, policy restrictions\n3. Generate 3-5 ad copy variations per platform, each with a distinct angle (benefit, urgency, social proof, curiosity, direct)\n4. Score each variation on: brand alignment, clarity, emotional impact, CTA strength, policy compliance\n5. Flag any potential policy violations (restricted claims, prohibited language)\n6. Recommend A/B testing groupings and priority order\n7. If landing page URL is provided, check message match between ad and page\n\n## Output\n\nPer platform, a set of ad copy variations including:\n\n- Headlines, descriptions, and CTAs formatted to platform specifications\n- Quality score (1-10) with reasoning per variation\n- Policy compliance check with flagged issues\n- A/B testing recommendation with hypothesis for each test\n- Message match assessment (if landing page provided)\n- Creative direction notes for visual/video assets (see AI image/video generation guidance below)\n\n### AI image & video generation guidance (May 2026)\n\nWhen the brief includes static visuals or short-form video, recommend the model that fits the use case and call out the compliance overhead:\n\n| Asset type | Recommended model (May 2026) | When to use | Compliance note |\n|---|---|---|---|\n| 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. |\n| Short-form social video (≤8s reels, organic vertical) | **Gemini Veo 3.1** (synchronized native audio, longer/more coherent clips than Veo 3.0) | 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. |\n| 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. |\n| 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. | None of these auto-embed C2PA — manually sign with `/digital-marketing-pro:c2pa-metadata` before EU publish. |\n\n**Workflow recommendation:**\n\n1. Brief the visual concept in this skill's output (subject, composition, brand-character constraints, on-pack text if any).\n2. 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.\n3. 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.\n\n## Agents Used\n\n- **content-creator** — Ad copy generation, angle development, CTA crafting\n- **media-buyer** — Platform specs, policy compliance, testing strategy\n- **brand-guardian** — Voice alignment, compliance review, claim verification","author":"@indranilbanerjee","ownerProfile":null,"authorContacts":null,"sourceUrl":"https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/ad-creative","license":"MIT","category":"writing","lang":"en","tokens":1318,"stars":0,"calls30d":1,"claimed":false,"visibility":"public","origin":"crawler","version":"0.1.0","createdAt":"2026-08-22","updatedAt":"2026-08-22","files":[],"requires":{"mcp":[],"tools":[]},"safety":{"flags":[],"scannedAt":"2026-08-22","hasScripts":false,"networkEndpoints":[]}}