Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
buluslan avatar

Ecom Image2

buluslan/gpt-image2-ecommerce

  • 16 installs
  • 274 repo stars
  • Updated April 27, 2026
  • buluslan/gpt-image2-ecommerce

Generate e-commerce product images and advertising visuals with GPT-Image-2 via Codex CLI by matching user intent to structured JSON prompt templates.

About

Maps an e-commerce image request to structured JSON prompt templates and invokes GPT-Image-2 through Codex CLI to produce product, banner, UGC, and packaging visuals. A seller uses it to create commercial product photography and ad creative.

  • Covers hero, lifestyle, flat lay, packaging, UGC, and many scene types
  • Extracts scene type, product info, and style to assemble prompts

Ecom Image2 by the numbers

  • 16 all-time installs (skills.sh)
  • Ranked #1,021 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/buluslan/gpt-image2-ecommerce --skill ecom-image2

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs16
repo stars★ 274
Last updatedApril 27, 2026
Repositorybuluslan/gpt-image2-ecommerce ↗

What it does

Generate e-commerce product images and advertising visuals with GPT-Image-2 via Codex CLI by matching user intent to structured JSON prompt templates.

Files

SKILL.mdMarkdownGitHub ↗

Overview

Generate e-commerce images using GPT-Image-2 via Codex CLI. Match user intent to structured JSON prompt templates, assemble concise prompts, and invoke image generation.

Workflow

Step 1: Intent Recognition

From the user's request, extract:

  • Scene type: hero image, lifestyle, flat lay, macro detail, poster/banner, social media, UGC, model showcase, before/after, packaging, infographic, creative concept, size spec, multi-product, livestream, virtual try-on, exploded view, ghost mannequin, multi-angle grid, magazine editorial, seasonal campaign, luxury atmospherics, device mockup, storefront, sports campaign
  • Product info: category (beauty/electronics/food/fashion/home/jewelry/sports), description, material, key selling points
  • Style preference: luxury, fresh, tech, minimal, or other variant
  • Reference image: whether user provided a product photo path

If the user provides a product photo path, note it for --image parameter.

Step 2: Template Matching

Read the matching template from references/templates/. Match by scanning keywords and trigger_phrases in each template:

Trigger WordsTemplate File
白底图, 主图, hero image, packshot01-hero-image.json
场景图, 生活图, lifestyle02-lifestyle-scene.json
平铺图, flat lay, 俯拍03-flat-lay.json
细节图, 微距, macro, 特写04-detail-macro.json
海报, poster, banner, 促销05-poster-banner.json
社交媒体, 小红书, Instagram, TikTok06-social-media.json
UGC, 买家秀, GRWM07-ugc-style.json
模特, model, 人物展示08-model-showcase.json
对比, before after, 前后09-before-after.json
包装, packaging, 礼盒10-packaging.json
信息图, A+, 详情页11-infographic.json
创意, 概念, creative12-creative-concept.json
尺寸, 规格, 使用步骤13-size-spec.json
套装, 组合, bundle14-multi-product.json
直播, livestream15-livestream.json
试穿, 融入, try on16-try-on-virtual.json
拆解图, 爆炸图, exploded view, 内部结构17-exploded-view.json
隐形模特, ghost mannequin, 3D服装18-ghost-mannequin.json
多角度, 网格, grid, 多色展示19-multi-angle-grid.json
杂志, 封面, editorial, magazine20-magazine-editorial.json
季节, 四季, campaign, 春夏秋冬21-seasonal-campaign.json
奢华, 氛围, 烟雾, luxury, atmospheric22-luxury-atmospherics.json
设备模型, 界面, mockup, SaaS, APP23-device-mockup.json
店铺, 门面, 空间, storefront, 实体店24-storefront.json
运动, 健身, sports, fitness25-sports-campaign.json

No match → default to 01-hero-image.json.

Only read the matched template file (progressive disclosure). Do not load all templates.

Step 3: Prompt Assembly

From the matched JSON template:

1. Take prompt_template as the base structure 2. Replace {variables} with user-provided info 3. If user specified a style variant → apply variants.<name>.overrides 4. If product category known → apply category_tips.<category> 5. Simplify: keep only core fields with values, remove empty/null fields 6. Output a concise JSON object (not the full template metadata)

Key principle: keep prompts simple. Only include essential information. Image2 performs best with concise, focused prompts rather than overly complex ones.

Example assembled prompt for a beauty hero image:

{
  "type": "product photography",
  "subject": "frosted glass serum bottle with matte white cap",
  "background": "clean white background",
  "lighting": "soft diffused studio lighting",
  "composition": "centered, front view",
  "quality": "8K, commercial e-commerce photography",
  "category_note": "emphasize texture and glow"
}

Step 4: Image Generation

Run the generation script:

bash scripts/imagegen.sh --prompt-file <(echo '<assembled_json>') --mode auto

Or call codex exec directly:

Without reference image:

codex exec --ephemeral --skip-git-repo-check --sandbox read-only --color never - <<< "Use imagegen to create an image with this request:
<assembled_json>

Requirements:
- Generate the image directly
- Do not provide explanation
- Return only the image result"

With reference image:

codex exec --ephemeral --skip-git-repo-check --sandbox read-only --color never \
  --image /path/to/ref.png \
  - <<< "Use imagegen to create an image with this request:
<assembled_json>

Reference image(s) are attached. Use them as visual identity/style references.
Requirements:
- Generate the image directly
- Do not provide explanation
- Return only the image result"

HTTP service mode: If curl -sf http://127.0.0.1:4312/health succeeds, submit via HTTP instead:

curl -sf -X POST http://127.0.0.1:4312/v1/images/generations \
  -H 'content-type: application/json' \
  -d '{"prompt":"<assembled_json>","images":["/path/to/ref.png"],"timeout_sec":180}'

Step 5: Result Cleanup

After generation, images are saved to ~/.codex/generated_images/<session_id>/. Must clean up:

1. Copy generated image to the user's working directory (or specified output path) and rename with descriptive name 2. Delete the original codex session folder to avoid duplicate storage:

rm -rf ~/.codex/generated_images/<session_id>

3. Report the final image path to the user

Step 6: Suggestions

If applicable, suggest:

  • Try a different style variant (list available variants from template)
  • Adjust product category for more tailored results
  • Add a reference image for better product consistency
  • Try a different scene type

Anti-AI Tips (for UGC / Livestream / Social Media scenes)

When generating UGC, livestream, or social media content, these rules are critical:

  • Specify exact phone model: iPhone 14 Pro, iPhone 15 Pro
  • Add visible imperfections: pores, slight noise, warm color cast, imperfect framing
  • Use candid language: NOT professional photography, NOT AI-generated look
  • Show real environment: slightly messy, real objects, water stains, used towels
  • Reference film tone: Kodak Portra 400 color feel
  • Explicitly state: NOT retouched, NOT smoothed
  • Avoid AI-signature words: no perfect, flawless, stunning, hyper-realistic

Prompt Writing Guidelines

  • Keep it simple: only core information, no excessive constraints
  • Natural language preferred: Image2 understands descriptive sentences better than keyword lists
  • Specify material: describe textures explicitly (frosted glass, brushed metal, matte finish)
  • Lighting matters: always include lighting direction and quality
  • Use references: passing a product photo via --image significantly improves consistency

Related skills

remotion-devRemotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k101-skillsAi Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665101-skillsAi Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665101-skillsAi Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665101-skillsRemotion RenderRender videos programmatically using React components and Remotion framework441k665halt-catch-fireRemotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665
Generative Mediaecommerce
Browse by category
AI & AgentsFrontend & DesignBackend & DataDev ToolsAutomationTesting & ReviewSecurityMonitoring & CloudDocs & Planning
Design & frontend
Design systemsAnimation & motionAccessibility (a11y)CSS & TailwindUI designUXDesign to codeshadcn/uiLanding pagesBest design skills
Most searched skills
find-skillscavemanfrontend-designbrainstormingsystematic-debuggingstop-slopemil-design-engui-ux-pro-maxkarpathy-guidelinesweb-design-guidelinesreact-best-practicesgrill-meimprovemicrosoft-foundryagent-browser
Browse all listings
All agent skillsAll MCP serversAll marketplacesAll plugins

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.