Ecom Adds
Generate 4 scroll-stopping e-commerce ad creatives for a product using deep customer research, competitor ad analysis via Facebook Ads Library, reference image sourcing via Tavily, and image generation via Nano Banana 2 (Gemini). Use when the user asks to create ads, ad creatives, DTC ads, Facebook/Instagram ads, or generate advertising images for a product.
Install
npx skills add Samin12/ecom-adds --skill ecom-addsgit clone --depth 1 https://github.com/Samin12/ecom-adds.git /tmp/ecom-adds
mkdir -p ~/.claude/skills
cp -r /tmp/ecom-adds/. ~/.claude/skills/ecom-addsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# E-Commerce Ad Generator You are an elite creative strategist — not just a designer, but someone who thinks like the best DTC advertisers in the world. Your job is to generate 4 ad creatives that make the viewer feel "this was made for ME." You will research deeply, understand the customer psychologically, and produce ads grounded in the 4 pillars of advertising psychology: **Attention, Curiosity, Emotion, and Connection.** Remember: Nobody cares about your product's ingredients list or GSM weight. They care about how it makes them feel, what problem it solves, and whether it connects with their identity. The best ads don't sell — they spark enough curiosity to click, or connect so deeply that the viewer shares it with their friends. You have roughly **0.5 seconds** to stop someone's scroll. Every creative decision must serve that reality. The product to generate ads for: $ARGUMENTS --- ## PHASE 1: Deep Product & Customer Research Good ads come from deep research, not staring at a blank doc. You need to understand the customer better than they understand themselves. The ideas, the hooks, the headlines — they come from research, not from generic AI copywriting. ### Step 1a: Web Research Use WebSearch to conduct thorough research. Run **at least 5-6 searches** covering:
Details
- Skill name
ecom-adds- Repository
- Samin12/ecom-adds
- Repo updated
- 29 April 2026
FAQ
What does the Ecom Adds skill do?
Generate 4 scroll-stopping e-commerce ad creatives for a product using deep customer research, competitor ad analysis via Facebook Ads Library, reference image sourcing via Tavily, and image generation via Nano Banana 2 (Gemini). Use when the user asks to create ads, ad creatives, DTC ads, Facebook/Instagram ads, or generate advertising images for a product.
How do I install the Ecom Adds skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Samin12/ecom-adds --skill ecom-adds. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Ecom Adds popular?
It lives in Samin12/ecom-adds, which has 8 GitHub stars and 9 forks.
Related skills
Podcast From Research
9Easternguy/podcast-from-research
Research-to-podcast pipeline for learning new topics: 20-angle full-coverage research (with blind-spot discovery) → steered NotebookLM audio overview → MP3 delivered to you, with everything ingested into a local GBrain knowledge base for permanent recall. When the user says "create a podcast on X", this handles it end-to-end. Installs its own dependencies (notebooklm-py, GBrain) if missing.
Video to 3d
12enwong93-sketch/video-to-3d
Turn a single-character A-pose orbit video or an approved whole multi-view character sheet into an editable Blender model using local MiniMax H3 MAIN/H3 IR generation when needed, measured 8-72 angle evidence, calibrated Blender overlays, detailed per-angle visual modeling, and final topology/beauty review. Use for fixed-subject character turntables and Blender reconstruction; do not use for action footage, moving subjects, direct neural-mesh generation, or photogrammetry capture.
Layered Holo Card
10JamesonZGJ/layered-holo-card-skill
Turn an existing photo or artwork into a layered 2.5D holographic collectible card while preserving its composition and subject pixels. Use for floating subjects, layered photo cards, or 把照片做成主体浮起的全息闪卡; not for redesigning the image or flat whole-card tilt alone.
Image Audit
12xiaowu89/skill-function
对图片进行鉴黄、政治、暴恐内容审核。先将图片压缩到 500px/JPEG 后直传 NX API 审核，以表格汇总结果。适用于用户提到图片审核、内容检查、鉴黄、政治识别、暴恐识别、违规扫描、图片安全、JPG/PNG/WebP 审核的场景。
Openclaw Genpark Video Creator
10alphaparkinc/openclaw-genpark-video-creator
OpenClaw GenPark Video Creator - SMPTE timecode drop-frame/non-drop-frame converter, Ken Burns cubic Bezier camera pan/zoom trajectory solver, and multi-track EDL timeline reconciler with zero dependencies.
Gpt Images
12lukasersil/gpt-images
Turns a plain-language brief into a production-ready prompt for OpenAI GPT Image models (ChatGPT Images 2.5, gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2). Returns a seven-block prompt, a settings block for the chosen surface, and three concrete levers for the next iteration. Covers text inside the image, reference binding, edits that do not drift, transparent backgrounds, and the hard API limits on size, quality and input images. Triggers: 'write an image prompt', 'gpt image prompt', 'chatgpt images 2.5', 'make me a poster', 'product shot prompt', 'article cover image', 'edit this
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.