Product To AdsSAFE
๐ง Curated collection of 1209+ best OpenClaw skills โ weekly updated by MyClaw.ai
Overview
๐ง Curated collection of 1209+ best OpenClaw skills โ weekly updated by MyClaw.ai
4f3b4a2a472eOBSERVED ยท 2026-10-08Install
Commands as the repository documents them. They are shown, not run.
uv run {baseDir}/scripts/generate.py --list-brandsHost compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit โ this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: ad-ready
description: 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/talent integration, brand-aware creative direction, and multi-format output. Differs from Morpheus (manual fashion photography) โ Ad-Ready is URL-driven, brand-intelligent, and funnel-stage aware.
---
# Ad-Ready: AI Advertising Image Generator
Generate professional advertising images from product URLs using a 4-phase AI pipeline on ComfyDeploy.
**Source:** [github.com/PauldeLavallaz/ads_SV](https://github.com/PauldeLavallaz/ads_SV)
---
## Pipeline Architecture
The pipeline runs as a ComfyUI custom node deployed on ComfyDeploy. A single `ProductToAds_Manual` node executes 4 phases internally:
```
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ProductToAds_Manual Node โ
โ โ
โ PHASE 1: Product Scraping (Gemini Flash) โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ Scrapes product URL โ extracts title, description, โ
โ features, price, materials, image URLs โ
โ Also scrapes HTML for high-res product images (โฅ1000px) โ
โ โ
โ PHASE 2: Campaign Brief Generation (Gemini Flash) โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ Brand Identity + Product Data + References โ โ
โ 10-point Campaign Brief (creative direction) โ
โ โ
โ PHASE 3: Blueprint Generation (Gemini Flash) โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ Master Prompt (funnel stage) + Brief + Keywords โ โ
โ Production-Ready JSON Blueprint โ
โ โ
โ PHASE 4: Image Generation (Nano Banana Pro / Imagen 3) โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ Blueprint + all reference images โ final ad image โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
```
### Phase 2: Campaign Brief (The Creative Brain)
The 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:
1. **Strategic Objective** โ Why this campaign exists (awareness/positioning/launch)
2. **Central Message** โ One idea perceivable without text
3. **Visual Tone of Voice** โ Register: calm/energetic/intimate/monumental
4. **Product Role** โ Hero vs co-protagonist vs implicit presence
5. **Visual Language & Brand Coherence** โ Non-negotiable brand codes
6. **Photographer & Equipment** โ Photography as concept, not execution
7. **Extended Art Direction** โ Styling, casting, poses, hair/makeup, layout
8. **Environment & Context** โ Where and why (conceptual, never decorative)
9. **Texture, Material & Product Render** โ How surfaces are perceived
10. **Final Image Signature** โ Finish, grain, temporal positioning
Without the brief, the Master Prompt must guess creative strategy. With it, the Master Prompt only executes.
The brief prompt template is included at `{baseDir}/configs/Brief_Generator/brief_prompt.json`.
### Phase 3: Master Prompts (8 Funnel Stages)
Each funnel stage has a specialized Master Prompt that generates a production-ready JSON Blueprint. All share the same internal simulation:
- **ROUND -1: Brand Identity Forensics** (stages 03+) โ Unified Brand Style Manifest
- **ROUND 0: Fidelity Lock** โ Product geometry & talent identity are IMMUTABLE
- **ROUND 1: Stage Strategy** โ Strategic approach specific to funnel position
- **ROUND 2: Graphic Design** โ UI, typography, CTA engineering
The Blueprint JSON covers: scene production, talent lock, camera perspective, subject action/pose/wardrobe, lighting, product constraints, layout architecture, typography, CTA engineering, and brand asset placement.
Master prompt files are included at `{baseDir}/configs/Product_to_Ads/`.
### Reference Analyzer
Reference images (`referencia`) are **optional** and **off by default**. The pipeline generates creative direction internally from Brand Identity + Campaign Brief. Only use a reference when the user explicitly asks to clone a specific ad's style.
When used, the reference is analyzed for pose, photographic style, and location cues.
---
## โ ๏ธ CRITICAL: Required Inputs Checklist
Before running ANY ad generation, ensure these are provided:
| Input | Required? | How to Get It |
|-------|-----------|---------------|
| `--product-url` | โ
ALWAYS | User provides the product page URL |
| `--product-image` | โ
ALWAYS | Download from the product page, or user provides |
| `--brand-profile` | โ
NEVER EMPTY | Pick from catalog or run brand-analyzer first. NEVER leave as "No Brand" if a brand is known |
| `--prompt-profile` | โ
ALWAYS | Choose based on campaign objective |
| `--aspect-ratio` | Default: 4:5 | Change if needed for platform |
| `--model` | ๐ถ OPTIONAL | Model/talent face. Ads with talent perform much better. Empty = product-only ad (no person). When used, pick from `~/clawd/models-catalog/catalog/images/` (114 models available) |
| `--logo` | ๐ถ OPTIONAL | Try to find it. Use if good quality & easy to get. Skip if low-res or hard to find. Empty = bypassed |
| `--reference` | ๐ถ OPTIONAL (off) | Only when user explicitly asks to clone a reference ad. Empty = bypassed |
| `--creative-brief` | ๐ถ ON-DEMAND | Only when user gives explicit creative direction. Omit to let pipeline auto-generate from brand profile |
| `--language` | ๐ถ ON-DEMAND | Trust audit
SAFEgrade B ยท trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
<key>k5Ey9KFlkqpj+SDkUw+5ED9lTA3En/qUi0zdrydUCH3kMWTE3Eh65NXnFCaxlY2omY2JHnlEoK7Li7oOEvM7eG5VPdcO/sFlMfoCRdnLYdepJ+uLzYwOWR8W4yQVve/clxVFTVRL4DFleKInGdpAxIbHZT2yi4ADAMENls1N1XSLojRuqXePXDeAT/4Mv4TTx0s
You are a Senior Fashion Photography Art Director specializing in visual reference analysis.
Gates applied: no_behavioural_pass.
4f3b4a2a472efull audit observations/trust-audit/skill/leoyeai__product-to-ads.json ยท Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 4f3b4a2a472e | SAFE | B | 89 | first audit |
Questions
What does the Product To Ads skill do?
๐ง Curated collection of 1209+ best OpenClaw skills โ weekly updated by MyClaw.ai
Is Product To Ads safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Product To Ads access on my machine?
The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does Product To Ads work with?
Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (4f3b4a2a472e), read on 2026-10-08. The repository is watched, and a new audit runs when it changes โ this is the first audit.