[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FZT2QVTNB2A7NBSSZPMWR7":3,"skill-same:01M6FZT2QVTNB2A7NBSSZPMWR7":120},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6FZT2QVTNB2A7NBSSZPMWR7","ad-ready",null,"Generate professional advertising images from product URLs using the Ad-Ready pipeline on ComfyDeploy. Use when the user wants to create ads for any product by providing a URL, optionally with a brand profile (70+ brands) and funnel stage targeting. Supports model\u002Ftalent integration, brand-aware creative direction, and multi-format output. Differs from Morpheus (manual fashion photography) — Ad-Ready is URL-driven, brand-intelligent, and funnel-stage aware.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,5,32,33,34,35,36,37,38,39,40,41],"ad ready","ready","ad","professional","targeting","advertising","manual","URL","fashion","direction","create","photography","images","brand","model","ads","pipeline","product","generate","2026-11-10 10:12:30",false,"---\nname: ad-ready\ndescription: Generate professional advertising images from product URLs using the Ad-Ready pipeline on ComfyDeploy. Use when the user wants to create ads for any product by providing a URL, optionally with a brand profile (70+ brands) and funnel stage targeting. Supports model\u002Ftalent integration, brand-aware creative direction, and multi-format output. Differs from Morpheus (manual fashion photography) — Ad-Ready is URL-driven, brand-intelligent, and funnel-stage aware.\n---\n\n# Ad-Ready: AI Advertising Image Generator\n\nGenerate professional advertising images from product URLs using a 4-phase AI pipeline on ComfyDeploy.\n\n**Source:** [github.com\u002FPauldeLavallaz\u002Fads_SV](https:\u002F\u002Fgithub.com\u002FPauldeLavallaz\u002Fads_SV)\n\n---\n\n## Pipeline Architecture\n\nThe pipeline runs as a ComfyUI custom node deployed on ComfyDeploy. A single `ProductToAds_Manual` node executes 4 phases internally:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                  ProductToAds_Manual Node                     │\n│                                                             │\n│  PHASE 1: Product Scraping (Gemini Flash)                   │\n│  ─────────────────────────────────────────                   │\n│  Scrapes product URL → extracts title, description,         │\n│  features, price, materials, image URLs                      │\n│  Also scrapes HTML for high-res product images (≥1000px)    │\n│                                                             │\n│  PHASE 2: Campaign Brief Generation (Gemini Flash)          │\n│  ────────────────────────────────────────────────            │\n│  Brand Identity + Product Data + References →                │\n│  10-point Campaign Brief (creative direction)                │\n│                                                             │\n│  PHASE 3: Blueprint Generation (Gemini Flash)               │\n│  ──────────────────────────────────────────────              │\n│  Master Prompt (funnel stage) + Brief + Keywords →           │\n│  Production-Ready JSON Blueprint                             │\n│                                                             │\n│  PHASE 4: Image Generation (Nano Banana Pro \u002F Imagen 3)     │\n│  ──────────────────────────────────────────────────          │\n│  Blueprint + all reference images → final ad image           │\n│                                                             │\n└─────────────────────────────────────────────────────────────┘\n```\n\n### Phase 2: Campaign Brief (The Creative Brain)\n\nThe Brief Generator is the most critical intermediate step. It acts as a \"Senior Art Director\" that translates raw data into actionable creative direction using a 10-point framework:\n\n1. **Strategic Objective** — Why this campaign exists (awareness\u002Fpositioning\u002Flaunch)\n2. **Central Message** — One idea perceivable without text\n3. **Visual Tone of Voice** — Register: calm\u002Fenergetic\u002Fintimate\u002Fmonumental\n4. **Product Role** — Hero vs co-protagonist vs implicit presence\n5. **Visual Language & Brand Coherence** — Non-negotiable brand codes\n6. **Photographer & Equipment** — Photography as concept, not execution\n7. **Extended Art Direction** — Styling, casting, poses, hair\u002Fmakeup, layout\n8. **Environment & Context** — Where and why (conceptual, never decorative)\n9. **Texture, Material & Product Render** — How surfaces are perceived\n10. **Final Image Signature** — Finish, grain, temporal positioning\n\nWithout the brief, the Master Prompt must guess creative strategy. With it, the Master Prompt only executes.\n\nThe brief prompt template is included at `{baseDir}\u002Fconfigs\u002FBrief_Generator\u002Fbrief_prompt.json`.\n\n### Phase 3: Master Prompts (8 Funnel Stages)\n\nEach funnel stage has a specialized Master Prompt that generates a production-ready JSON Blueprint. All share the same internal simulation:\n\n- **ROUND -1: Brand Identity Forensics** (stages 03+) — Unified Brand Style Manifest\n- **ROUND 0: Fidelity Lock** — Product geometry & talent identity are IMMUTABLE\n- **ROUND 1: Stage Strategy** — Strategic approach specific to funnel position\n- **ROUND 2: Graphic Design** — UI, typography, CTA engineering\n\nThe Blueprint JSON covers: scene production, talent lock, camera perspective, subject action\u002Fpose\u002Fwardrobe, lighting, product constraints, layout architecture, typography, CTA engineering, and brand asset placement.\n\nMaster prompt files are included at `{baseDir}\u002Fconfigs\u002FProduct_to_Ads\u002F`.\n\n### Reference Analyzer\n\nWhen reference images (pose, style, location) are provided, they're analyzed with forensic precision:\n\n- **POSE_REF** → Body position, limbs, weight, gaze, micro-gestures → replicated EXACTLY\n- **PHOTO_STYLE_REF** → Camera, lens, lighting, grading, grain → derived parameters\n- **LOCATION_REF** → Setting, materials, colors, mood → similar but creatively enhanced\n\nThe reference analysis prompt is at `{baseDir}\u002Fconfigs\u002FReference_Analyzer\u002Freference_analysis_prompt.txt`.\n\n---\n\n## ⚠️ CRITICAL: Required Inputs Checklist\n\nBefore running ANY ad generation, ensure ALL of these are provided:\n\n| Input | Required? | How to Get It |\n|-------|-----------|---------------|\n| `--product-url` | ✅ ALWAYS | User provides the product page URL |\n| `--product-image` | ✅ ALWAYS | Download from the product page, or user provides |\n| `--logo` | ✅ ALWAYS | Download from brand website or search online. MUST be an image file |\n| `--reference` | ✅ RECOMMENDED | An existing ad whose style we want to clone. Search online or use previously generated images |\n| `--brand-profile` | ✅ NEVER EMPTY | Pick from catalog or run brand-analyzer first. NEVER leave as \"No Brand\" if a brand is known |\n| `--prompt-profile` | ✅ ALWAYS | Choose based on campaign objective |\n| `--aspect-ratio` | Default: 4:5 | Change if needed for platform |\n| `--model` | ✅ RECOMMENDED | Model\u002Ftalent face. Ads with talent perform much better |\n\n### ? NEVER Skip These Steps:\n\n1. **Product image** — Download the main product photo from the product URL. The scraper is fragile; always provide a product image explicitly.\n2. **Brand logo** — Download the logo from the brand's official website or search for \"{brand name} logo\" online. Must be a clean logo image (PNG preferred).\n3. **Brand profile** — If the brand doesn't exist in the catalog, run `brand-analyzer` skill FIRST to generate one. Never submit with \"No Brand\" when a brand is known.\n4. **Reference image** — Search for an existing ad or visual with a style that matches what we're generating. This dramatically improves output quality.\n\n---\n\n## Auto-Preparation Workflow\n\nWhen the user asks to generate an ad:\n\n```\n1. User provides: product URL + brand name + objective\n\n2. CHECK brand profile exists:\n   → ls ~\u002Fclawd\u002Fad-ready\u002Fconfigs\u002FBrands\u002F | grep -i \"{brand}\"\n   → If not found: run brand-analyzer skill first\n\n3. DOWNLOAD product image:\n   → Visit the product URL or fetch the page\n   → Find and download the main product image\n   → Save to \u002Ftmp\u002Fad-ready-product.jpg\n\n4. DOWNLOAD brand logo:\n   → Search \"{brand name} logo PNG\" or fetch from brand website\n   → Download clean logo image\n   → Save to \u002Ftmp\u002Fad-ready-logo.png\n\n5. FIND reference image:\n   → Search for \"{brand name} advertisement\" or similar\n   → Or use a previously generated ad that has the right style\n   → Save to \u002Ftmp\u002Fad-ready-reference.jpg\n\n6. SELECT prompt profile based on objective:\n   → Awareness: brand discovery, first impressions\n   → Interest: engagement, curiosity\n   → Consideration: comparison, features\n   → Evaluation: deep dive, trust, proof\n   → Conversion: purchase intent, CTAs (most common)\n   → Retention: post-purchase confidence\n   → Loyalty: emotional bond, lifestyle\n   → Advocacy: social amplification, community\n\n7. RUN the generation with ALL inputs filled\n```\n\n---\n\n## Usage\n\n### Full command (recommended):\n```bash\nCOMFY_DEPLOY_API_KEY=\"$KEY\" uv run {baseDir}\u002Fscripts\u002Fgenerate.py \\\n  --product-url \"https:\u002F\u002Fshop.example.com\u002Fproduct\" \\\n  --product-image \"\u002Ftmp\u002Fproduct-photo.jpg\" \\\n  --logo \"\u002Ftmp\u002Fbrand-logo.png\" \\\n  --reference \"\u002Ftmp\u002Freference-ad.jpg\" \\\n  --model \"models-catalog\u002Fcatalog\u002Fimages\u002Fmodel_15.jpg\" \\\n  --brand-profile \"Nike\" \\\n  --prompt-profile \"Master_prompt_05_Conversion\" \\\n  --aspect-ratio \"4:5\" \\\n  --output \"ad-output.png\"\n```\n\n### Auto-fetch mode (downloads product image and logo automatically):\n```bash\nCOMFY_DEPLOY_API_KEY=\"$KEY\" uv run {baseDir}\u002Fscripts\u002Fgenerate.py \\\n  --product-url \"https:\u002F\u002Fshop.example.com\u002Fproduct\" \\\n  --brand-profile \"Nike\" \\\n  --prompt-profile \"Master_prompt_05_Conversion\" \\\n  --auto-fetch \\\n  --output \"ad-output.png\"\n```\n\n### List available brands:\n```bash\nuv run {baseDir}\u002Fscripts\u002Fgenerate.py --list-brands\n```\n\n---\n\n## API Details\n\n**Endpoint:** `https:\u002F\u002Fapi.comfydeploy.com\u002Fapi\u002Frun\u002Fdeployment\u002Fqueue`\n**Deployment ID:** `e37318e6-ef21-4aab-bc90-8fb29624cd15`\n\n### ComfyDeploy Input Variables\n\n| Variable | Type | Description |\n|----------|------|-------------|\n| `product_url` | string | Product page URL to scrape |\n| `producto` | image URL | Product image (uploaded to ComfyDeploy) |\n| `model` | image URL | Model\u002Ftalent face reference |\n| `referencia` | image URL | Style reference ad image (used for both pose + location) |\n| `marca` | image URL | Brand logo image |\n| `brand_profile` | enum | Brand name from catalog (70+ brands) |\n| `prompt_profile` | enum | Funnel stage master prompt |\n| `aspect_ratio` | enum | Output format (1:1, 4:5, 5:4, 9:16, etc.) |\n\n---\n\n## Funnel Stages — Strategic Detail\n\n### 01 — Awareness\n**Goal:** Scroll-stop, curiosity, brand introduction\n**Reject:** Generic \"product on table\" concepts\n**Strategy:** Dynamic camera angles, world-building environments, high-concept creativity\n**CTA:** Soft or optional\n**Visual Hierarchy:** Talent → Product → Optional CTA\n\n### 02 — Interest\n**Goal:** Sustained attention, introduce value proposition\n**Reject:** Abstract visuals that hide the product\n**Strategy:** One clear visual idea, believable micro-world hinting at use-case\n**CTA:** Learn More, Discover, See Details\n**Visual Hierarchy:** Talent → Product → Headline → CTA\n\n### 03 — Consideration\n**Goal:** Informed evaluation, reduce uncertainty\n**Reject:** Pure mood storytelling, vague emotional content\n**Strategy:** Communicate WHAT product does, ONE primary differentiator, ONE proof cue\n**CTA:** Compare, See Details, Explore\n**Visual Hierarchy:** Talent → Product → Key Benefit → Proof Cue → CTA\n**New:** Adds Brand Identity Manifest to Blueprint JSON\n\n### 04 — Evaluation\n**Goal:** Validate purchase decision, proof & trust\n**Reject:** Pure mood, unsupportable claims, visual clutter\n**Strategy:** One trust anchor (quality\u002Flegitimacy\u002Fauthority), one proof cue (reviews\u002Fcertification)\n**CTA:** See Reviews, Verified Quality, Learn More\n**Visual Hierarchy:** Trust Anchor → Proof Cue → Product → Talent → CTA\n\n### 05 — Conversion\n**Goal:** Trigger decisive action, remove friction\n**Reject:** New hesitation-inducing info, complex compositions\n**Strategy:** One hero (product), one action, optional micro-reassurance\n**CTA:** Buy Now, Get Yours, Complete Order (PRIMARY visual element)\n**Visual Hierarchy:** Product → CTA → Optional Reassurance → Brand → Talent\n\n### 06 — Retention\n**Goal:** Post-purchase confidence, reduce churn\n**Reject:** Hard-sell, urgency, price talk\n**Strategy:** \"You made the right choice\" + \"Here is the next step\"\n**CTA:** Start, Set Up, Learn, Track (guidance, not purchase)\n**Visual Hierarchy:** Confirmation → Next Step → Product → Talent\n\n### 07 — Loyalty\n**Goal:** Strengthen emotional bond over time\n**Reject:** Sales layouts, instructional tone, aggressive CTAs\n**Strategy:** \"This brand is part of who you are\" — habitual engagement\n**CTA:** Optional: Explore, Be Part Of, Continue\n**Visual Hierarchy:** Brand World\u002FMood → Talent (identity mirror) → Product → Brand\n\n### 08 — Advocacy\n**Goal:** Turn customers into voluntary brand ambassadors\n**Reject:** Sales language, instructional tone, forced testimonials\n**Strategy:** Signal belonging, create share-worthy imagery, enable organic sharing\n**CTA:** Optional or absent: Join the Movement, Part of Us\n**Visual Hierarchy:** Mood → Talent (identity proxy) → Product (symbol) → Brand\n\n---\n\n## Creating New Ad Types\n\nTo create a new funnel stage or specialized ad type:\n\n1. **Copy** the closest existing Master Prompt from `{baseDir}\u002Fconfigs\u002FProduct_to_Ads\u002F`\n2. **Redefine ROUND 1** with the new strategic objective\n3. **Adjust ROUND 2** UI hierarchy accordingly\n4. **Shift** talent\u002Fproduct narrative roles\n5. **Modify** CTA philosophy and copy voice\n6. **Keep** the JSON output structure identical for pipeline compatibility\n7. **Maintain** the Fidelity Lock (ROUND 0) — product and talent are always immutable\n8. **Save** as `Master_prompt_XX_NewStage.json` — the node auto-discovers new profiles\n\n### Key Evolution Pattern Across Stages:\n\n| Aspect | Early (01-02) | Mid (03-05) | Late (06-08) |\n|--------|--------------|-------------|--------------|\n| Talent role | Attention anchor | Credibility anchor | Identity mirror |\n| Product role | Secondary hero | Evaluation hero | Familiar symbol |\n| CTA | Soft\u002Fexploratory | Proof-led → Decisive | Guidance → Optional |\n| Copy voice | Intriguing | Clarity, proof, action | Supportive → Proud |\n| Visual density | High-concept | Structured, scannable | Editorial, spacious |\n| Environment | World-building | Context-rich | Lifestyle, intimate |\n\n---\n\n## Image Input Types\n\n### Binding Images (strict fidelity — immutable)\n- **talent**: Face\u002Fbody locked, no deviation in facial structure, ethnicity, proportions\n- **product_1-4**: Shape, label text, material, proportions preserved 1:1\n- **brand_logo**: UI\u002Fbutton style derived from logo geometry\n\n### Soft References (creative guidance)\n- **pose_ref**: Body position replicated EXACTLY (spine, limbs, weight, gaze, micro-gestures)\n- **photo_style_ref**: Camera\u002Flighting\u002Fgrading\u002Fgrain derived (can be too literal)\n- **location_ref**: Environment inspired but creatively enhanced\n\nIn the live deployment, the **same reference image** feeds both `pose_ref` and `location_ref`.\n\n---\n\n## Brand Profiles\n\n### Catalog (70+ brands):\n```bash\nls ~\u002Fclawd\u002Fad-ready\u002Fconfigs\u002FBrands\u002F*.json | sed 's\u002F.*\\\u002F\u002F\u002F' | sed 's\u002F\\.json\u002F\u002F'\n```\n\n### Creating new brand profiles:\nUse the `brand-analyzer` skill:\n```bash\nGEMINI_API_KEY=\"$KEY\" uv run ~\u002F.clawdbot\u002Fskills\u002Fbrand-analyzer\u002Fscripts\u002Fanalyze.py \\\n  --brand \"Brand Name\" --auto-save\n```\n\nThe Brand Analyzer uses a 3-phase methodology:\n1. **Phase 1:** Official research via Google Search (canonical data: name, founding, positioning, vision, mission, tagline)\n2. **Phase 1.1:** Independent campaign research (10+ distinct campaigns via Google Images\u002FPinterest)\n3. **Phase 2-3:** Visual analysis → JSON profile following the standard template\n\nOutput covers: brand_info, brand_values, target_audience, tone_of_voice, visual_identity, photography, campaign_guidelines, brand_behavior, channel_expression, compliance.\n\n---\n\n## Aspect Ratios\n\n| Ratio | Use Case |\n|-------|----------|\n| `4:5` | **Default.** Instagram feed, Facebook |\n| `9:16` | Stories, Reels, TikTok |\n| `1:1` | Square posts |\n| `16:9` | YouTube, landscape banners |\n| `5:4` | Alternative landscape |\n| `2:3` | Pinterest |\n| `3:4` | Portrait |\n\n---\n\n## Config Files Reference\n\nThe skill includes reference copies of all pipeline configuration files:\n\n```\n{baseDir}\u002Fconfigs\u002F\n├── Brief_Generator\u002F\n│   └── brief_prompt.json              # 10-point campaign brief framework\n├── Product_to_Ads\u002F\n│   ├── Master_prompt_01_Awareness.json\n│   ├── Master_prompt_02_Interest.json\n│   ├── Master_prompt_03_Consideration.json\n│   ├── Master_prompt_04_Evaluation.json\n│   ├── Master_prompt_05_Conversion.json\n│   ├── Master_prompt_06_Retention.json\n│   ├── Master_prompt_07_Loyalty.json\n│   └── Master_prompt_08_Advocacy.json\n└── Reference_Analyzer\u002F\n    └── reference_analysis_prompt.txt   # Pose\u002Fstyle\u002Flocation analysis prompt\n```\n\nThese configs are the canonical reference for the pipeline's behavior. The actual live configs are stored in the ComfyUI deployment at `ads_SV\u002Fconfigs\u002F`.\n\n---\n\n## Known Limitations\n\n1. **Product image scraping is fragile** — always provide product images manually\n2. **photo_style_ref can be too literal** — style reference may be replicated too closely\n3. **Some websites block scraping** — provide product data manually when scraping fails\n4. **Single reference = pose + location** — live deployment uses one image for both\n5. **Gemini hallucinations** — occasional issues in complex reasoning steps\n6. **No brief editing** — brief is generated automatically; manual override not yet supported\n\n---\n\n## Ad-Ready vs Morpheus\n\n| Feature | Ad-Ready | Morpheus |\n|---------|----------|----------|\n| Input | Product URL (auto-scrapes) | Manual product image |\n| Brand intelligence | 70+ brand profiles | None |\n| Funnel targeting | 8 funnel stages | None |\n| Brief generation | Auto (10-point creative direction) | None |\n| Creative direction | Objective-driven (brief → blueprint) | Pack-based (camera, lens, lighting) |\n| Best for | Product advertising campaigns | Fashion\u002Flifestyle editorial photography |\n| Control level | High-level (strategy-first) | Granular (every visual parameter) |\n\n---\n\n## API Key\n\nUses ComfyDeploy API key. Set via `COMFY_DEPLOY_API_KEY` environment variable.\n\n## Source Repository\n\n- GitHub: [PauldeLavallaz\u002Fads_SV](https:\u002F\u002Fgithub.com\u002FPauldeLavallaz\u002Fads_SV)\n- Architecture: ComfyUI custom node package with 3 nodes:\n  - `ProductToAds_Manual` — Full manual control, single format\n  - `ProductToAds_Auto` — Auto-downloads images, generates 4 formats\n  - `BrandIdentityAnalyzer` — Analyzes brands via Gemini + Google Search\n","# Ad-Ready: AI Advertising Image Generator\n\nGenerate professional advertising images from product URLs using a 4-phase AI pipeline on ComfyDeploy.\n\n**Source:** [github.com\u002FPauldeLavallaz\u002Fads_SV](https:\u002F\u002Fgithub.com\u002FPauldeLavallaz\u002Fads_SV)\n\n---\n\n## Pipeline Architecture\n\nThe pipeline runs as a ComfyUI custom node deployed on ComfyDeploy. A single `ProductToAds_Manual` node executes 4 phases internally:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                  ProductToAds_Manual Node                     │\n│                                                             │\n│  PHASE 1: Product Scraping (Gemini Flash)                   │\n│  ─────────────────────────────────────────                   │\n│  Scrapes product URL → extracts title, description,         │\n│  features, price, materials, image URLs                      │\n│  Also scrapes HTML for high-res product images (≥1000px)    │\n│                                                             │\n│  PHASE 2: Campaign Brief Generation (Gemini Flash)          │\n│  ────────────────────────────────────────────────            │\n│  Brand Identity + Product Data + References →                │\n│  10-point Campaign Brief (creative direction)                │\n│                                                             │\n│  PHASE 3: Blueprint Generation (Gemini Flash)               │\n│  ──────────────────────────────────────────────              │\n│  Master Prompt (funnel stage) + Brief + Keywords →           │\n│  Production-Ready JSON Blueprint                             │\n│                                                             │\n│  PHASE 4: Image Generation (Nano Banana Pro \u002F Imagen 3)     │\n│  ──────────────────────────────────────────────────          │\n│  Blueprint + all reference images → final ad image           │\n│                                                             │\n└─────────────────────────────────────────────────────────────┘\n```\n\n### Phase 2: Campaign Brief (The Creative Brain)\n\nThe Brief Generator is the most critical intermediate step. It acts as a \"Senior Art Director\" that translates raw data into actionable creative direction using a 10-point framework:\n\n1. **Strategic Objective** — Why this campaign exists (awareness\u002Fpositioning\u002Flaunch)\n2. **Central Message** — One idea perceivable without text\n3. **Visual Tone of Voice** — Register: calm\u002Fenergetic\u002Fintimate\u002Fmonumental\n4. **Product Role** — Hero vs co-protagonist vs implicit presence\n5. **Visual Language & Brand Coherence** — Non-negotiable brand codes\n6. **Photographer & Equipment** — Photography as concept, not execution\n7. **Extended Art Direction** — Styling, casting, poses, hair\u002Fmakeup, layout\n8. **Environment & Context** — Where and why (conceptual, never decorative)\n9. **Texture, Material & Product Render** — How surfaces are perceived\n10. **Final Image Signature** — Finish, grain, temporal positioning\n\nWithout the brief, the Master Prompt must guess creative strategy. With it, the Master Prompt only executes.\n\nThe brief prompt template is included at `{baseDir}\u002Fconfigs\u002FBrief_Generator\u002Fbrief_prompt.json`.\n\n### Phase 3: Master Prompts (8 Funnel Stages)\n\nEach funnel stage has a specialized Master Prompt that generates a production-ready JSON Blueprint. All share the same internal simulation:\n\n- **ROUND -1: Brand Identity Forensics** (stages 03+) — Unified Brand Style Manifest\n- **ROUND 0: Fidelity Lock** — Product geometry & talent identity are IMMUTABLE\n- **ROUND 1: Stage Strategy** — Strategic approach specific to funnel position\n- **ROUND 2: Graphic Design** — UI, typography, CTA engineering\n\nThe Blueprint JSON covers: scene production, talent lock, camera perspective, subject action\u002Fpose\u002Fwardrobe, lighting, product constraints, layout architecture, typography, CTA engineering, and brand asset placement.\n\nMaster prompt files are included at `{baseDir}\u002Fconfigs\u002FProduct_to_Ads\u002F`.\n\n### Reference Analyzer\n\nWhen reference images (pose, style, location) are provided, they're analyzed with forensic precision:\n\n- **POSE_REF** → Body position, limbs, weight, gaze, micro-gestures → replicated EXACTLY\n- **PHOTO_STYLE_REF** → Camera, lens, lighting, grading, grain → derived parameters\n- **LOCATION_REF** → Setting, materials, colors, mood → similar but creatively enhanced\n\nThe reference analysis prompt is at `{baseDir}\u002Fconfigs\u002FReference_Analyzer\u002Freference_analysis_prompt.txt`.\n\n---\n\n## ⚠️ CRITICAL: Required Inputs Checklist\n\nBefore running ANY ad generation, ensure ALL of these are provided:\n\n| Input | Required? | How to Get It |\n|-------|-----------|---------------|\n| `--product-url` | ✅ ALWAYS | User provides the product page URL |\n| `--product-image` | ✅ ALWAYS | Download from the product page, or user provides |\n| `--logo` | ✅ ALWAYS | Download from brand website or search online. MUST be an image file |\n| `--reference` | ✅ RECOMMENDED | An existing ad whose style we want to clone. Search online or use previously generated images |\n| `--brand-profile` | ✅ NEVER EMPTY | Pick from catalog or run brand-analyzer first. NEVER leave as \"No Brand\" if a brand is known |\n| `--prompt-profile` | ✅ ALWAYS | Choose based on campaign objective |\n| `--aspect-ratio` | Default: 4:5 | Change if needed for platform |\n| `--model` | ✅ RECOMMENDED | Model\u002Ftalent face. Ads with talent perform much better |\n\n### ? NEVER Skip These Steps:\n\n1. **Product image** — Download the main product photo from the product URL. The scraper is fragile; always provide a product image explicitly.\n2. **Brand logo** — Download the logo from the brand's official website or search for \"{brand name} logo\" online. Must be a clean logo image (PNG preferred).\n3. **Brand profile** — If the brand doesn't exist in the catalog, run `brand-analyzer` skill FIRST to generate one. Never submit with \"No Brand\" when a brand is known.\n4. **Reference image** — Search for an existing ad or visual with a style that matches what we're generating. This dramatically improves output quality.\n\n---\n\n## Auto-Preparation Workflow\n\nWhen the user asks to generate an ad:\n\n```\n1. User provides: product URL + brand name + objective\n\n2. CHECK brand profile exists:\n   → ls ~\u002Fclawd\u002Fad-ready\u002Fconfigs\u002FBrands\u002F | grep -i \"{brand}\"\n   → If not found: run brand-analyzer skill first\n\n3. DOWNLOAD product image:\n   → Visit the product URL or fetch the page\n   → Find and download the main product image\n   → Save to \u002Ftmp\u002Fad-ready-product.jpg\n\n4. DOWNLOAD brand logo:\n   → Search \"{brand name} logo PNG\" or fetch from brand website\n   → Download clean logo image\n   → Save to \u002Ftmp\u002Fad-ready-logo.png\n\n5. FIND reference image:\n   → Search for \"{brand name} advertisement\" or similar\n   → Or use a previously generated ad that has the right style\n   → Save to \u002Ftmp\u002Fad-ready-reference.jpg\n\n6. SELECT prompt profile based on objective:\n   → Awareness: brand discovery, first impressions\n   → Interest: engagement, curiosity\n   → Consideration: comparison, features\n   → Evaluation: deep dive, trust, proof\n   → Conversion: purchase intent, CTAs (most common)\n   → Retention: post-purchase confidence\n   → Loyalty: emotional bond, lifestyle\n   → Advocacy: social amplification, community\n\n7. RUN the generation with ALL inputs filled\n```\n\n---\n\n## Usage\n\n### Full command (recommended):\n```bash\nCOMFY_DEPLOY_API_KEY=\"$KEY\" uv run {baseDir}\u002Fscripts\u002Fgenerate.py \\\n  --product-url \"https:\u002F\u002Fshop.example.com\u002Fproduct\" \\\n  --product-image \"\u002Ftmp\u002Fproduct-photo.jpg\" \\\n  --logo \"\u002Ftmp\u002Fbrand-logo.png\" \\\n  --reference \"\u002Ftmp\u002Freference-ad.jpg\" \\\n  --model \"models-catalog\u002Fcatalog\u002Fimages\u002Fmodel_15.jpg\" \\\n  --brand-profile \"Nike\" \\\n  --prompt-profile \"Master_prompt_05_Conversion\" \\\n  --aspect-ratio \"4:5\" \\\n  --output \"ad-output.png\"\n```\n\n### Auto-fetch mode (downloads product image and logo automatically):\n```bash\nCOMFY_DEPLOY_API_KEY=\"$KEY\" uv run {baseDir}\u002Fscripts\u002Fgenerate.py \\\n  --product-url \"https:\u002F\u002Fshop.example.com\u002Fproduct\" \\\n  --brand-profile \"Nike\" \\\n  --prompt-profile \"Master_prompt_05_Conversion\" \\\n  --auto-fetch \\\n  --output \"ad-output.png\"\n```\n\n### List available brands:\n```bash\nuv run {baseDir}\u002Fscripts\u002Fgenerate.py --list-brands\n```\n\n---\n\n## API Details\n\n**Endpoint:** `https:\u002F\u002Fapi.comfydeploy.com\u002Fapi\u002Frun\u002Fdeployment\u002Fqueue`\n**Deployment ID:** `e37318e6-ef21-4aab-bc90-8fb29624cd15`\n\n### ComfyDeploy Input Variables\n\n| Variable | Type | Description |\n|----------|------|-------------|\n| `product_url` | string | Product page URL to scrape |\n| `producto` | image URL | Product image (uploaded to ComfyDeploy) |\n| `model` | image URL | Model\u002Ftalent face reference |\n| `referencia` | image URL | Style reference ad image (used for both pose + location) |\n| `marca` | image URL | Brand logo image |\n| `brand_profile` | enum | Brand name from catalog (70+ brands) |\n| `prompt_profile` | enum | Funnel stage master prompt |\n| `aspect_ratio` | enum | Output format (1:1, 4:5, 5:4, 9:16, etc.) |\n\n---\n\n## Funnel Stages — Strategic Detail\n\n### 01 — Awareness\n**Goal:** Scroll-stop, curiosity, brand introduction\n**Reject:** Generic \"product on table\" concepts\n**Strategy:** Dynamic camera angles, world-building environments, high-concept creativity\n**CTA:** Soft or optional\n**Visual Hierarchy:** Talent → Product → Optional CTA\n\n### 02 — Interest\n**Goal:** Sustained attention, introduce value proposition\n**Reject:** Abstract visuals that hide the product\n**Strategy:** One clear visual idea, believable micro-world hinting at use-case\n**CTA:** Learn More, Discover, See Details\n**Visual Hierarchy:** Talent → Product → Headline → CTA\n\n### 03 — Consideration\n**Goal:** Informed evaluation, reduce uncertainty\n**Reject:** Pure mood storytelling, vague emotional content\n**Strategy:** Communicate WHAT product does, ONE primary differentiator, ONE proof cue\n**CTA:** Compare, See Details, Explore\n**Visual Hierarchy:** Talent → Product → Key Benefit → Proof Cue → CTA\n**New:** Adds Brand Identity Manifest to Blueprint JSON\n\n### 04 — Evaluation\n**Goal:** Validate purchase decision, proof & trust\n**Reject:** Pure mood, unsupportable claims, visual clutter\n**Strategy:** One trust anchor (quality\u002Flegitimacy\u002Fauthority), one proof cue (reviews\u002Fcertification)\n**CTA:** See Reviews, Verified Quality, Learn More\n**Visual Hierarchy:** Trust Anchor → Proof Cue → Product → Talent → CTA\n\n### 05 — Conversion\n**Goal:** Trigger decisive action, remove friction\n**Reject:** New hesitation-inducing info, complex compositions\n**Strategy:** One hero (product), one action, optional micro-reassurance\n**CTA:** Buy Now, Get Yours, Complete Order (PRIMARY visual element)\n**Visual Hierarchy:** Product → CTA → Optional Reassurance → Brand → Talent\n\n### 06 — Retention\n**Goal:** Post-purchase confidence, reduce churn\n**Reject:** Hard-sell, urgency, price talk\n**Strategy:** \"You made the right choice\" + \"Here is the next step\"\n**CTA:** Start, Set Up, Learn, Track (guidance, not purchase)\n**Visual Hierarchy:** Confirmation → Next Step → Product → Talent\n\n### 07 — Loyalty\n**Goal:** Strengthen emotional bond over time\n**Reject:** Sales layouts, instructional tone, aggressive CTAs\n**Strategy:** \"This brand is part of who you are\" — habitual engagement\n**CTA:** Optional: Explore, Be Part Of, Continue\n**Visual Hierarchy:** Brand World\u002FMood → Talent (identity mirror) → Product → Brand\n\n### 08 — Advocacy\n**Goal:** Turn customers into voluntary brand ambassadors\n**Reject:** Sales language, instructional tone, forced testimonials\n**Strategy:** Signal belonging, create share-worthy imagery, enable organic sharing\n**CTA:** Optional or absent: Join the Movement, Part of Us\n**Visual Hierarchy:** Mood → Talent (identity proxy) → Product (symbol) → Brand\n\n---\n\n## Creating New Ad Types\n\nTo create a new funnel stage or specialized ad type:\n\n1. **Copy** the closest existing Master Prompt from `{baseDir}\u002Fconfigs\u002FProduct_to_Ads\u002F`\n2. **Redefine ROUND 1** with the new strategic objective\n3. **Adjust ROUND 2** UI hierarchy accordingly\n4. **Shift** talent\u002Fproduct narrative roles\n5. **Modify** CTA philosophy and copy voice\n6. **Keep** the JSON output structure identical for pipeline compatibility\n7. **Maintain** the Fidelity Lock (ROUND 0) — product and talent are always immutable\n8. **Save** as `Master_prompt_XX_NewStage.json` — the node auto-discovers new profiles\n\n### Key Evolution Pattern Across Stages:\n\n| Aspect | Early (01-02) | Mid (03-05) | Late (06-08) |\n|--------|--------------|-------------|--------------|\n| Talent role | Attention anchor | Credibility anchor | Identity mirror |\n| Product role | Secondary hero | Evaluation hero | Familiar symbol |\n| CTA | Soft\u002Fexploratory | Proof-led → Decisive | Guidance → Optional |\n| Copy voice | Intriguing | Clarity, proof, action | Supportive → Proud |\n| Visual density | High-concept | Structured, scannable | Editorial, spacious |\n| Environment | World-building | Context-rich | Lifestyle, intimate |\n\n---\n\n## Image Input Types\n\n### Binding Images (strict fidelity — immutable)\n- **talent**: Face\u002Fbody locked, no deviation in facial structure, ethnicity, proportions\n- **product_1-4**: Shape, label text, material, proportions preserved 1:1\n- **brand_logo**: UI\u002Fbutton style derived from logo geometry\n\n### Soft References (creative guidance)\n- **pose_ref**: Body position replicated EXACTLY (spine, limbs, weight, gaze, micro-gestures)\n- **photo_style_ref**: Camera\u002Flighting\u002Fgrading\u002Fgrain derived (can be too literal)\n- **location_ref**: Environment inspired but creatively enhanced\n\nIn the live deployment, the **same reference image** feeds both `pose_ref` and `location_ref`.\n\n---\n\n## Brand Profiles\n\n### Catalog (70+ brands):\n```bash\nls ~\u002Fclawd\u002Fad-ready\u002Fconfigs\u002FBrands\u002F*.json | sed 's\u002F.*\\\u002F\u002F\u002F' | sed 's\u002F\\.json\u002F\u002F'\n```\n\n### Creating new brand profiles:\nUse the `brand-analyzer` skill:\n```bash\nGEMINI_API_KEY=\"$KEY\" uv run ~\u002F.clawdbot\u002Fskills\u002Fbrand-analyzer\u002Fscripts\u002Fanalyze.py \\\n  --brand \"Brand Name\" --auto-save\n```\n\nThe Brand Analyzer uses a 3-phase methodology:\n1. **Phase 1:** Official research via Google Search (canonical data: name, founding, positioning, vision, mission, tagline)\n2. **Phase 1.1:** Independent campaign research (10+ distinct campaigns via Google Images\u002FPinterest)\n3. **Phase 2-3:** Visual analysis → JSON profile following the standard template\n\nOutput covers: brand_info, brand_values, target_audience, tone_of_voice, visual_identity, photography, campaign_guidelines, brand_behavior, channel_expression, compliance.\n\n---\n\n## Aspect Ratios\n\n| Ratio | Use Case |\n|-------|----------|\n| `4:5` | **Default.** Instagram feed, Facebook |\n| `9:16` | Stories, Reels, TikTok |\n| `1:1` | Square posts |\n| `16:9` | YouTube, landscape banners |\n| `5:4` | Alternative landscape |\n| `2:3` | Pinterest |\n| `3:4` | Portrait |\n\n---\n\n## Config Files Reference\n\nThe skill includes reference copies of all pipeline configuration files:\n\n```\n{baseDir}\u002Fconfigs\u002F\n├── Brief_Generator\u002F\n│   └── brief_prompt.json              # 10-point campaign brief framework\n├── Product_to_Ads\u002F\n│   ├── Master_prompt_01_Awareness.json\n│   ├── Master_prompt_02_Interest.json\n│   ├── Master_prompt_03_Consideration.json\n│   ├── Master_prompt_04_Evaluation.json\n│   ├── Master_prompt_05_Conversion.json\n│   ├── Master_prompt_06_Retention.json\n│   ├── Master_prompt_07_Loyalty.json\n│   └── Master_prompt_08_Advocacy.json\n└── Reference_Analyzer\u002F\n    └── reference_analysis_prompt.txt   # Pose\u002Fstyle\u002Flocation analysis prompt\n```\n\nThese configs are the canonical reference for the pipeline's behavior. The actual live configs are stored in the ComfyUI deployment at `ads_SV\u002Fconfigs\u002F`.\n\n---\n\n## Known Limitations\n\n1. **Product image scraping is fragile** — always provide product images manually\n2. **photo_style_ref can be too literal** — style reference may be replicated too closely\n3. **Some websites block scraping** — provide product data manually when scraping fails\n4. **Single reference = pose + location** — live deployment uses one image for both\n5. **Gemini hallucinations** — occasional issues in complex reasoning steps\n6. **No brief editing** — brief is generated automatically; manual override not yet supported\n\n---\n\n## Ad-Ready vs Morpheus\n\n| Feature | Ad-Ready | Morpheus |\n|---------|----------|----------|\n| Input | Product URL (auto-scrapes) | Manual product image |\n| Brand intelligence | 70+ brand profiles | None |\n| Funnel targeting | 8 funnel stages | None |\n| Brief generation | Auto (10-point creative direction) | None |\n| Creative direction | Objective-driven (brief → blueprint) | Pack-based (camera, lens, lighting) |\n| Best for | Product advertising campaigns | Fashion\u002Flifestyle editorial photography |\n| Control level | High-level (strategy-first) | Granular (every visual parameter) |\n\n---\n\n## API Key\n\nUses ComfyDeploy API key. Set via `COMFY_DEPLOY_API_KEY` environment variable.\n\n## Source Repository\n\n- GitHub: [PauldeLavallaz\u002Fads_SV](https:\u002F\u002Fgithub.com\u002FPauldeLavallaz\u002Fads_SV)\n- Architecture: ComfyUI custom node package with 3 nodes:\n  - `ProductToAds_Manual` — Full manual control, single format\n  - `ProductToAds_Auto` — Auto-downloads images, generates 4 formats\n  - `BrandIdentityAnalyzer` — Analyzes brands via Gemini + Google Search\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fpauldelavallaz\u002Fad-ready",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add kbarbel640-del\u002Fskills --skill ad-ready",{"tool":60,"command":61},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill ad-ready",{"tool":63,"command":64},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill ad-ready","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002FSKILL.md",true,[68,74,78,82,86,90,94,98,102,106,110,114],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"_meta.json","REFERENCE","参考文档",806,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002F_meta.json",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"configs\u002FBrief_Generator\u002Fbrief_prompt.json",7763,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FBrief_Generator\u002Fbrief_prompt.json",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"configs\u002FProduct_to_Ads\u002FMaster_prompt_01_Awareness.json",14095,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_01_Awareness.json",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"configs\u002FProduct_to_Ads\u002FMaster_prompt_02_Interest.json",16076,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_02_Interest.json",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"configs\u002FProduct_to_Ads\u002FMaster_prompt_03_Consideration.json",12531,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_03_Consideration.json",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"configs\u002FProduct_to_Ads\u002FMaster_prompt_04_Evaluation.json",11178,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_04_Evaluation.json",{"path":95,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":96,"sourceHtmlUrl":97},"configs\u002FProduct_to_Ads\u002FMaster_prompt_05_Conversion.json",11314,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_05_Conversion.json",{"path":99,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":100,"sourceHtmlUrl":101},"configs\u002FProduct_to_Ads\u002FMaster_prompt_06_Retention.json",11694,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_06_Retention.json",{"path":103,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":104,"sourceHtmlUrl":105},"configs\u002FProduct_to_Ads\u002FMaster_prompt_07_Loyalty.json",12010,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_07_Loyalty.json",{"path":107,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":108,"sourceHtmlUrl":109},"configs\u002FProduct_to_Ads\u002FMaster_prompt_08_Advocacy.json",12381,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FProduct_to_Ads\u002FMaster_prompt_08_Advocacy.json",{"path":111,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":112,"sourceHtmlUrl":113},"configs\u002FReference_Analyzer\u002Freference_analysis_prompt.txt",2080,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fconfigs\u002FReference_Analyzer\u002Freference_analysis_prompt.txt",{"path":115,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Fgenerate.py","SCRIPT","脚本",19819,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpauldelavallaz\u002Fad-ready\u002Fscripts\u002Fgenerate.py",[121,152,178,199,205,225],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":132,"publishedAt":42},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":42},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[162,135,163,164,165,166,33,167,168,169,170,171,172,173,174,175,176,140,177],"dilemm ai","arena","analyze","browser","openclaw agent","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":187,"publishedAt":42},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[184],{"categoryNo":185,"categoryName":186,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[188,189,190,191,192,193,194,136,195,175,177,196,135,197,198],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":200,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":42},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[203],{"categoryNo":185,"categoryName":186,"taxonomyType":20,"taxonomyTypeDesc":21},[191,190,189,188,198,193,194,136,192,175,177,195,196,135,197],{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":42},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[212,213,214,215,216,217,218,219,220,221,222,223,224],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":235,"publishedAt":42},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[231,232],{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":233,"categoryName":234,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000037","律师与法务",[236,237,238,239,136,240,241,47,242,196,243,244,245,246,247,149,248,249,250],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]