Image Recognition and Analysis skills for Claude Code and Codex
Skills that describe images, extract text, detect objects and AI-generated media, and run quality checks on generated pictures.
Highest-scoring image analysis skills in the October 22, 2026 snapshot: vision-analysis from MiniMax-AI/skills (69/100). Scores come from the Suede Skill Check.
- 4 listed skills
- 3 repositories
- 1 with full pages
2 from official publishers. 0 bundle scripts. 2 connect to an outside service. Listed in Video, Image, Audio and Creative (4).
All 4 image analysis skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| vision-analysis 69/100 · D | MiniMax-AI/skills | Analyzes, describes, and extracts information from images, including text extraction, using the MiniMax vision MCP tool. |
| image-analyzer 66/100 · D | gooseworks-ai/goose-skills | Analyze images with AI - extract text, describe content, detect objects |
| resemble-detect 74/100 · C | github/awesome-copilot | Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker… |
| verify-product-image 67/100 · D | gooseworks-ai/goose-skills | QC gate for a generated static ad image — verify the file opens, matches the requested dimensions, shows the correct product/subject (right shape… |
How to choose image analysis skills
Vision skills call a hosted model (MiniMax or a GooseWorks endpoint), so check the provider and key.
Deepfake detection through Resemble AI covers audio, image and video in one skill.
For quality checks on generated ad images, use the product image verification skill.
Related topics
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills