Update to Recharm

{
  "description": "Build a Recharm footage brief for a LIKING ad — fronted by warmth, relatability, candor, and similarity, so the viewer buys because the ad feels like a recommendation from someone they'd be friends with. Use whenever a user provides a brief, concept, or ad idea framed around relatable confessions, best-friend recommendations, self-deprecating humor, 'real talk' energy, shared struggles, or unpolished authenticity. Searches the user's Recharm clip library and produces a shareable shot-by-shot brief with clip picks. Trigger on \"liking\", \"relatable ad\", \"real talk\", \"bestie recommendation\", \"girl talk\", \"unpolished\", \"authentic UGC vibe\", \"friend telling a friend\", or any creative where the persuasion engine is warmth and similarity rather than evidence, experts, or urgency.\n",
  "included_files": [
    {
      "relative_path": "templates/brief.html",
      "size_in_bytes": 19746
    }
  ],
  "name": "liking-ad-brief",
  "skill_md_contents": "---\nname: \"liking-ad-brief\"\ndescription: >\n  Build a Recharm footage brief for a LIKING ad — fronted by warmth, relatability, candor, and similarity, so the viewer buys because the ad feels like a recommendation from someone they'd be friends with. Use whenever a user provides a brief, concept, or ad idea framed around relatable confessions, best-friend recommendations, self-deprecating humor, 'real talk' energy, shared struggles, or unpolished authenticity. Searches the user's Recharm clip library and produces a shareable shot-by-shot brief with clip picks. Trigger on \"liking\", \"relatable ad\", \"real talk\", \"bestie recommendation\", \"girl talk\", \"unpolished\", \"authentic UGC vibe\", \"friend telling a friend\", or any creative where the persuasion engine is warmth and similarity rather than evidence, experts, or urgency.\n---\n\n# Liking Ad Brief\n\nYou build a Recharm footage brief for a **liking** ad — one fronted by warmth, relatability, and similarity — the viewer buys because the ad feels like a tip from someone they'd actually be friends with.\n\nThe psychological engine: people say yes to people they like — and we like people who are similar to us, who are candid, who feel familiar. The ad wins by being disarming and relatable before it sells anything: shared struggles, self-deprecating humor, best-friend energy. Distinct from authority (credentials) and social proof (evidence): the driver is *affection and similarity*, so imperfection is an asset, not a flaw.\n\nThe Recharm MCP server (`recharm`) is available in this plugin. Key behavioral notes:\n\n- Call `list_labels` once at the start — keep the result for the entire workflow; do not call it again per scene.\n- Search hits from `search_clips_visually` already include `posterUrl` and `previewUrl` — use them directly. Only call `get_clip_poster_image` as a fallback if a hit is missing `posterUrl`.\n- The template builds \"View clip\" and \"Find similar\" links itself from `clipSymbol`, `brand`, and `searchString` — you don't construct any Recharm app URLs.\n- Do not paginate `search_clips_visually` — use the first page only.\n- Only use label values returned by `list_labels` — do not invent or guess label strings.\n- Do **NOT** call `save_brief`. Instead, render the brief using `templates/brief.html` and upload via `save_html_file`.\n\n**Always refer to a clip in user-facing output as its `clipName` — `<clipSymbol> - <sceneType>`** (e.g. \"AB - Product Reveal\"). If `sceneType` is null, fall back to just the `clipSymbol`.\n\nFollow the steps below in order.\n\n---\n\n## Step 1 — Confirm the brand, hook, and content constraints\n\n**Brand:** If the user already named a brand slug (e.g. `magic_spoon`, `hike_footwear`), use it. Otherwise call `list_brands` and ask the user to pick. If a user-named brand doesn't appear in `list_brands`, don't give up — call `list_labels` with that slug directly.\n\n**Hook selection:** Choose the best-fitting liking hook pattern for the brief. If the user provided a specific hook line, use it and map it to the closest pattern. Make your pick, write a one-sentence rationale, and note why you're rejecting the others — you'll need all of this for the final brief output.\n\n**Liking hook patterns:**\n- *Real Talk* — \"Okay, real talk — I almost didn't post this.\"\n- *Same-Boat* — \"If your mornings look like this, we're already friends.\"\n- *Candid Confession* — \"I'm the laziest person I know. This is the only thing that stuck.\"\n- *Best-Friend Rec* — \"My best friend wouldn't shut up about this. She was right.\"\n- *Self-Roast* — \"I ignored this for a year because I'm stubborn. Don't be me.\"\n- *Compliment Open* — \"You clearly have good taste — that's exactly why this will annoy you.\"\n- *Inside Joke* — \"POV: you swear you'll meal prep this week.\"\n- *Unpolished Review* — \"No script, no ring light — here's what I actually think.\"\n- *Shared Enemy* — \"We both hate [annoying thing]. So does this brand.\"\n- *Kitchen-Table Chat* — \"Come here, sit down — we need to talk about breakfast.\"\n\n**ActorType preference:** Liking ads live on warm, natural, imperfect footage — authenticity beats polish everywhere in this arc. Confirm with the user:\n- **No Actor** — purely product/environment footage\n- **Actor B-roll** — hands, partial body, people in motion (recommended)\n- **Both** (No Actor + Actor B-roll) — good default\n- **No filter** — include all footage\n\n**Brand-fit rationale:** While confirming, form a view on *why liking will work for this specific brand* — does its buyer respond to friend-to-friend energy, and does the brand's voice allow candid, unpolished, similarity-driven creative? You'll write this into the brief's `why.brandFit` field in Step 6 so anyone opening the brief understands the strategy, not just the shot list.\n\n---\n\n## Step 2 — Fetch available labels\n\nCall `list_labels(brandName)` and keep the result for the rest of the workflow. Note:\n- **Scene Type**: `Hook`, `Visual Hook`, `CTA`, `Product Benefits`, `Product Shot`, `Lifestyle`, `Bowl Shot`, `Box Shot`, etc.\n- **Actor Type**: whether a person appears and whether they are speaking.\n- **Product**: maps to specific flavors or SKUs.\n\n---\n\n## Step 3 — Section the brief using the liking narrative arc\n\nBreak the brief into **10–14 scenes** using this arc:\n\n| Arc segment | Typical scenes | Purpose |\n|---|---|---|\n| **Hook** | 1–2 | A disarming, candid, relatable open — the viewer instantly recognizes the vibe and likes the voice. |\n| **Relatable Moments** | 2–3 | Everyday scenes the target buyer actually lives — imperfect, warm, familiar. Similarity does the persuading. |\n| **Shared Struggle** | 1–2 | The mutual pain or running joke that bonds viewer and voice — the \"you too?\" beat before the answer. |\n| **Product Reveal** | 1–2 | The product enters like a friend's recommendation across the kitchen table — casual, not staged. |\n| **Benefit Payoff** | 2–3 | Benefits shown in warm, lived-in contexts — genuine enjoyment, not studio perfection. |\n| **Friendship Beat** | 1 | The relationship pays off — comfort, delight, the feeling of a good tip from a good friend. |\n| **CTA** | 1 | \"Trust me on this one\" / \"You'll thank me later.\" |\n\nFor each scene capture:\n- `name`: short heading (e.g. \"Hook — pajama-clad morning kitchen chaos\")\n- `description`: 1–2 sentences describing what appears on screen\n- `arcSegment`: one of the 7 arc segment names above (must match exactly — the HTML uses these for color-coding)\n\n**If the user supplied an explicit scene breakdown, use it. Otherwise show the proposed breakdown and wait for confirmation.**\n\n---\n\n## Step 4 — Build search queries\n\nFor each scene, generate **3–5 search queries** — short visual phrases (under ~8 words) describing what is literally on screen, not abstract concepts. Vary phrases to cover different subjects, framings, and environments. You need enough query diversity to surface **4 strong, visually distinct clips per scene** — a single query rarely gets you there.\n\n### Filter rules\n- Apply ActorType labels to every query (baseline, not counted toward the category limit).\n- Add at most **1 additional label category** per query (Scene Type or Product).\n- Use Scene Type matching the arc segment: Hook/Visual Hook for the hook; Lifestyle/Product Benefits for the middle segments; Product Shot for the reveal; CTA for the close.\n- Apply Product label only for scenes where the specific SKU is the hero.\n\n---\n\n## Step 5 — Search and collect clip media\n\n**Run all first-round queries in parallel** (all 3–5 queries per scene in one batch). Then fill gaps with follow-up queries only where needed.\n\nFor each scene:\n1. Call `search_clips_visually` with `brandName`, `query`, and any `filters`.\n2. Pool the results from all of the scene's queries and pick the **4 best clips** — rank primarily by lowest `cosineDistance`, but prefer visual variety (different framings, subjects, environments) over four near-identical picks.\n3. Deduplicate by `clipSymbol`. Use **at most one clip per `rawVideoPublicId`** — clips sharing a source video look near-identical; keep the best (lowest cosineDistance).\n4. If a scene has fewer than 4 strong matches after the first round, run 1–2 follow-up queries with different phrasings before settling for fewer. A scene may ship with 2–3 clips if the library is genuinely thin — never pad with weak matches (cosineDistance well into the \"weak\" range) just to hit 4.\n5. Take `posterUrl` and `previewUrl` directly from the search hit. If a hit is missing `previewUrl` and has a `rawVideoPublicId`, derive it: `https://res.cloudinary.com/recharm/video/upload/so_0,eo_4,q_auto,f_auto/{rawVideoPublicId}.mp4`.\n6. Track per clip: `clipSymbol`, `clipName`, `posterUrl`, `previewUrl`, `cosineDistance`, `searchString`, `filters`. `searchString` must be the **exact query string** used in the `search_clips_visually` call that surfaced the clip — the template uses it to build the \"Find similar\" link, which reopens the full visual-search result set (including the clips you considered but rejected). The template also builds each \"View clip\" link from `clipSymbol`, so `clipSymbol` must be exactly as returned.\n7. Scenes with no strong matches → `clips: []` (renders as \"custom shoot needed\" gap in the HTML).\n\n**Arc-specific search guidance:**\n- **Hook:** Warm, candid, imperfect moments — messy kitchens, pajamas, real-morning energy, natural light.\n- **Relatable Moments:** Daily-life footage the buyer recognizes as their own — commute rush, snooze button, fridge stare.\n- **Shared Struggle:** Comic-relatable friction — burnt toast, empty cereal box, sad desk breakfast — played warm, not miserable.\n- **Product Reveal / Benefit / CTA:** Product Shot, Benefits, CTA Scene Types; favor cozy, natural, unstaged-feeling clips over polished studio shots.\n\n---\n\n## Step 6 — Assemble the JSON data payload\n\nBuild this object — the HTML template renders everything from it:\n\n```json\n{\n  \"title\": \"<e.g. 'You'll Thank Me Later · Magic Spoon · Frosted'>\",\n  \"brand\": \"<brandName slug>\",\n  \"generatedAt\": \"<YYYY-MM-DD>\",\n  \"filterChips\": [\n    { \"category\": \"Actor Type\", \"value\": \"Actor B-Roll\" },\n    { \"category\": \"Actor Type\", \"value\": \"No Actor\" },\n    { \"category\": \"Product\", \"value\": \"Frosted\" },\n    { \"category\": \"Scenes\", \"value\": \"12\" }\n  ],\n  \"why\": {\n    \"explainer\": \"<2–3 sentences: what a liking ad is and the mechanism that makes it convert — we say yes to people we like — similarity, candor, and warmth make the recommendation feel like it comes from a friend. Written for someone who has never heard the term.>\",\n    \"brandFit\": \"<2–3 sentences: why this mechanism fits THIS brand specifically — its category, how its buyers decide, and the context that makes the liking angle credible.>\"\n  },\n  \"hook\": {\n    \"pattern\": \"<Pattern name, e.g. 'Best-Friend Rec'>\",\n    \"line\": \"<The actual hook line, e.g. 'My best friend wouldn't shut up about this cereal. She was right.'>\",\n    \"rationale\": \"<1–2 sentences: why this hook fits this brand and audience>\"\n  },\n  \"rejectedHooks\": [\n    {\n      \"pattern\": \"<Pattern name>\",\n      \"line\": \"<What the hook line would have been>\",\n      \"reason\": \"<1 sentence — specific reason this pattern is a weaker fit here>\"\n    }\n  ],\n  \"actorType\": \"<e.g. 'Both (Actor B-Roll + No Actor)'>\",\n  \"scenes\": [\n    {\n      \"name\": \"<Scene heading>\",\n      \"arcSegment\": \"<Exactly one of: Hook | Relatable Moments | Shared Struggle | Product Reveal | Benefit Payoff | Friendship Beat | CTA>\",\n      \"description\": \"<1–2 sentences of on-screen description>\",\n      \"clips\": [\n        {\n          \"clipSymbol\": \"<symbol>\",\n          \"clipName\": \"<clipName from search result>\",\n          \"posterUrl\": \"<posterUrl from the search hit>\",\n          \"previewUrl\": \"<previewUrl from the search hit, or derived from rawVideoPublicId, or null>\",\n          \"cosineDistance\": 0.142,\n          \"searchString\": \"<exact query phrase used to find this clip>\",\n          \"filters\": { \"<category>\": [\"<label>\"] }\n        }\n      ]\n    }\n  ]\n}\n```\n\nNotes:\n- `filterChips` is what renders under the title — one chip per applied footage filter. Include every ActorType label applied, any Product/Scene Type filters used broadly, and a `Scenes` count chip. Keep values short (chip-sized) — this replaces the old prose subtitle.\n- `why.explainer` and `why.brandFit` render as a prominent \"Why this approach\" panel — write them for a reader who has never heard of the liking lever and needs to be convinced it fits their brand. Target **4 clip picks per scene** in `clips`.\n- Include **at least 5 rejected hooks** in `rejectedHooks` with specific, brand-aware reasons so the user understands the creative logic behind the chosen pattern.\n\n---\n\n## Step 7 — Render and save the brief\n\n1. **Read** `templates/brief.html` (in this skill's directory).\n2. **Replace** the exact string `__BRIEF_DATA_JSON__` with the JSON payload (serialized as a single string — no pretty-printing needed, just ensure it is valid JSON). After serializing, replace every `</` with `<\\/` in the JSON string — the payload lives inside an inline `<script>` tag, and an unescaped `</` in any text field would terminate the script and break the whole page.\n3. **Call the Recharm MCP `save_html_file` tool** with:\n   - `brandName`: the brand slug used throughout this workflow\n   - `html`: the fully rendered HTML string (max 20 MB)\n\n   This uploads the HTML to Recharm's public-share storage and returns a shareable `url`.\n4. **Surface the `url`** to the user.\n5. Give a short **summary**: custom-shoot gaps, scenes that shipped with fewer than 4 clips, arc segments with thin library coverage, any weak-match clips flagged.\n\n---\n\n## What not to do\n\n- Don't confuse liking with social proof or authority — no review counts, no credentials. The persuasion is affection and similarity; evidence talk breaks the spell.\n- Don't over-polish — studio-perfect footage kills relatability. In this arc, warmth and imperfection are features.\n- Don't reveal the product before the Shared Struggle — protect the tension arc.\n- Don't settle for 1 clip per scene — the brief is a menu, not a lock; editors need 4 options per scene to cut alternates.\n- Don't pad to 4 clips with weak matches — 2–3 strong picks beat 4 with a dud.\n- Don't drop `posterUrl`/`previewUrl` from search hits — the template needs them for thumbnails and hover previews.\n- Don't add download links — raw downloadable video URLs aren't available; \"View clip\" and \"Find similar\" open in the Recharm app.\n- Don't call `save_brief` — use the Recharm MCP `save_html_file` tool with `brandName` + `html`.\n- Don't use label values not returned by `list_labels`.\n- Don't over-filter — default to 1 label category per query beyond ActorType.\n- Don't invent `clipSymbol`s — only use ones returned by `search_clips_visually`.\n- Don't refer to a clip by `clipSymbol` alone — always use `clipName` in user-facing output.\n- Don't paraphrase `searchString` — it must be the exact query used, or the visual-search results link in the brief won't reproduce the search.\n- Don't call `save_html_file` more than once per brief — each call mints a new URL.\n- Don't give up if a brand doesn't appear in `list_brands` — try `list_labels` directly.\n"
}