Update to JuicyLucy Ads

{
  "description": "The static ad format library — 36 named creative mechanisms for single-image ads (breaking news, reviews, us-vs-them, iPhone notes, transformation, tier list, testimonial, meme, stat headline, Venn diagram, and more) with a generation workflow, a copy-ready image prompt template, an iteration recipe by campaign objective, and a production QA checklist. Use when choosing a format for a new static concept, when a brief asks \"what format should this ad take\", when generating format baselines and controlled variants, or when auditing a static creative against its format's mechanism. Formats only — copy rules live in static-copywriting, the pipeline in static-ad-production.",
  "included_files": [],
  "name": "static-formats",
  "skill_md_contents": "---\nname: static-formats\ndescription: The static ad format library — 36 named creative mechanisms for single-image ads (breaking news, reviews, us-vs-them, iPhone notes, transformation, tier list, testimonial, meme, stat headline, Venn diagram, and more) with a generation workflow, a copy-ready image prompt template, an iteration recipe by campaign objective, and a production QA checklist. Use when choosing a format for a new static concept, when a brief asks \"what format should this ad take\", when generating format baselines and controlled variants, or when auditing a static creative against its format's mechanism. Formats only — copy rules live in static-copywriting, the pipeline in static-ad-production.\n---\n\n# Static ad format library\n\nThirty-six creative mechanisms that work as a single static image, derived\nfrom observed high-performing paid-social formats. Six clearly video-first\nformats are deliberately absent — script, whiteboard, AI podcast, claymation,\nnative/UGC, and greenscreen — because a still cannot carry them; video ad\ntypes come from the `/video-ad-production` blueprints, not from this list.\n\nExamples use the fictional product **VELORA Daily Focus Gummies** so the\nmechanism — not a brand — is what you compare. They are concept examples, not\nclaim-approved production ads.\n\n**A brand may narrow this catalogue.** Resolve the brand first (`brand-<slug>`\nin the catalogue; exactly one installed → use it; several → ask; none → create\none first, per the `juicylucy-setup` skill's `extending.md`).\nIf the brand carries a `format-renditions.md`, it re-angles these mechanisms\nfor that brand and may exclude some outright — its exclusions win.\n\n## The formats and what each one does\n\n1. **Breaking news** — Borrows the urgency and hierarchy of a news bulletin to frame the product update as timely.\n2. **Reviews / ratings** — Leads with rating, stars, and short review cards; use only substantiated reviews and avoid third-party logos without permission.\n3. **Offer** — Makes price, bundle, gift, or discount the dominant visual hook.\n4. **Us vs. them** — Side-by-side feature comparison that makes the choice easy to scan.\n5. **Doodle** — Handwritten arrows, circles, and notes create a casual creator-made feel.\n6. **Low-stock alert** — Scarcity headline plus inventory cue; only use when scarcity is truthful.\n7. **Myth vs. fact** — Contrasts a familiar misconception with the brand's corrective idea.\n8. **iPhone notes** — Looks like a personal note or checklist; low-polish and native-feeling.\n9. **Transformation** — Before/after contrast showing a visible change in state or routine.\n10. **Zero stars** — Pattern interrupt that opens negative, then flips into a positive reveal.\n11. **Search results** — Search-engine mockup that mirrors the customer's question-and-answer path; avoid real logos.\n12. **Bundle** — Product-stack image that communicates quantity, savings, and completeness.\n13. **Don't be an idiot** — Provocative blunt headline that challenges an unhelpful habit; keep tone playful.\n14. **Forum post** — Anonymous forum-thread aesthetic that reads like a candid discovery; avoid impersonating real users.\n15. **Side effect** — Reframes the desired outcome as a humorous \"side effect.\"\n16. **We're sorry** — Mock apology that turns a benefit into a witty confession.\n17. **Tier list** — Ranks habits or options from best to worst for fast, shareable comparison.\n18. **Story-style** — Casual vertical-social visual language with handwriting, polls, or stickers; no platform logo needed.\n19. **X signs** — Numbered symptom/sign list that helps viewers self-identify with the problem.\n20. **Problem vs. solution** — Split layout that makes pain and resolution visually immediate.\n21. **Warning** — Caution-label visual used as a humorous or dramatic benefit hook.\n22. **You can avoid** — Prevention angle focused on escaping an unwanted outcome.\n23. **Reasons why** — Short numbered reasons supporting purchase or adoption.\n24. **Email screenshot** — Familiar inbox/message format that feels personal and specific.\n25. **Text message** — Short conversational proof or objection handling in chat bubbles.\n26. **Problems** — Clusters several pain points around the product and crosses them out.\n27. **Hack 101** — Educational formula or lesson that packages the product as a simple tactic.\n28. **Emergency** — High-urgency \"rescue\" framing for an acute moment of need.\n29. **Testimonial** — Portrait, quote, name, and proof markers; use real approved testimony in production.\n30. **Don't buy this** — Reverse-psychology opener followed by a qualifier that identifies the ideal customer.\n31. **Stat headline** — One oversized number drives attention; clearly label personal experiments and substantiate broader claims.\n32. **Meme** — Familiar two-panel joke built around a relatable before/after moment.\n33. **New vs. old** — Contrasts the previous routine or product with the improved one.\n34. **Text on skin** — Editorial human close-up with a short message written on skin for an unexpected visual hook.\n35. **Us vs. us** — Shows product or brand evolution without attacking a competitor.\n36. **Venn diagram** — Two audience desires overlap at the product or core benefit.\n\n## Step-by-step generation workflow\n\n1. **Choose one mechanism.** Start from the list above. Do not combine more\n   than two mechanisms in the first draft.\n2. **Lock the input facts.** Product name and appearance, one audience, one\n   pain point, one benefit, one proof point, one offer, the exact CTA — from\n   the resolved brand and the brief, with every claim needing substantiation\n   marked. Copy passes `static-copywriting`'s two compliance layers.\n3. **Write one hook.** Short enough to read on a phone — ideally 3–9 words.\n4. **Choose the proof object.** Product photo, rating, quote, comparison\n   rows, checklist, chart, message thread, or before/after scene.\n5. **Set the hierarchy.** Hook first, proof second, product third, CTA last.\n   The ad should still make sense at thumbnail size.\n6. **Generate the image** with Codex's own image tool (the configured provider\n   only when it is unavailable), using the prompt template below — one\n   distinct style per call.\n7. **Check exact text.** Image models misspell and alter copy. Regenerate\n   with less text, or replace text via `static-image-craft` when exact\n   wording matters.\n8. **Check claim safety.** Remove invented ratings, testimonials, scarcity,\n   percentages, endorsements, or outcome claims; replace with approved\n   evidence.\n9. **Create controlled variants.** Mechanism fixed; vary one variable at a\n   time — hook, hero image, color, proof, or offer.\n10. **Export platform sizes.** 1080×1080 square and 1080×1350 feed portrait\n    as baselines; 1080×1920 only when the layout still reads as a static\n    story. The batch's contracted ratio wins when the pipeline sets one.\n11. **Name per the workspace grammar.** Filenames come from the `ad-naming`\n    skill's tool applying the `juicylucy` skill's `naming.json` — never an\n    ad-hoc scheme, never typed by hand; reserve collision-free names before\n    moving outputs in.\n12. **Record results.** Log spend, impressions, thumb-stop/CTR, CVR, CPA, and\n    the exact variable changed. Promote mechanisms, not just artworks.\n\n## Copy-ready image prompt template\n\n```text\nUse case: ads-marketing\nAsset type: [RATIO] paid-social static ad\nPrimary request: Create a [STYLE NAME] static ad for [PRODUCT].\nAudience: [ONE SPECIFIC AUDIENCE]\nScene/backdrop: [SETTING OR UI-LIKE FORMAT]\nSubject: [PRODUCT + PERSON/OBJECT IF NEEDED]\nComposition: [HOOK POSITION], [PROOF OBJECT], [PRODUCT POSITION], [CTA POSITION]\nStyle: polished performance creative, mobile-first hierarchy, [BRAND AESTHETIC]\nColor palette: [COLORS]\nText (verbatim):\n- Headline: \"[HEADLINE]\"\n- Proof: \"[PROOF OR SUPPORTING LINE]\"\n- CTA: \"[CTA]\"\nConstraints: fictional placeholders only unless supplied; no third-party logos; no watermark; no unsupported badges; product label legible.\nAvoid: tiny copy, clutter, duplicated products, extra fingers, fake platform chrome, invented certifications.\n```\n\n## Iteration recipe\n\nFor a new concept round, pick 3–5 mechanisms matching the campaign objective:\n\n- **Awareness / pattern interrupt:** Breaking news, warning, zero stars,\n  don't buy this, meme.\n- **Problem education:** X signs, problems, myth vs. fact, problem vs.\n  solution, you can avoid.\n- **Trust / proof:** Reviews, testimonial, forum post, stat headline,\n  transformation.\n- **Purchase intent:** Offer, bundle, low stock, us vs. them, new vs. old.\n- **Native / organic feel:** Doodle, notes, story-style, email, text message.\n\nGenerate one baseline per mechanism, select the best two, then create three\ncontrolled variants of each. Keep a clean control so performance differences\nattribute to the changed variable.\n\n## Production QA checklist\n\n- Headline is readable at 25% zoom.\n- Product and brand are identifiable in under one second.\n- Only one primary message and one CTA.\n- Copy is spelled exactly as approved.\n- Ratings, testimonials, statistics, scarcity, and comparisons are documented.\n- No unlicensed platform, publication, or review-site logos.\n- Before/after imagery is representative and policy-compliant.\n- Required disclaimers remain readable.\n- Export has correct dimensions, color, and safe margins.\n- Filename follows the workspace grammar and the experiment log identifies\n  style, hook, audience, and version.\n"
}