Find The Original Image

Find-the-original-image is a reverse image search workflow for working out where a picture first appeared, not just whether it appears somewhere. It walks through Yandex, Google Lens, Bing Visual Search, TinEye and Baidu, and the useful part is the method: pick the engine by what you're holding (Yandex for faces and eastern-European content, TinEye for sorting by oldest, Bing for region-select), crop tightly and retry, flip horizontally, and read the match pages for photographer credits and filenames. The face-search section is the most careful one, flagging GDPR and BIPA exposure and where the tool should not be used. It's a solid starting point for scam and disinformation work, though I'd treat any single engine's miss as meaningless.

skills.sh installs: 56.6K
GitHub stars: 61
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add useosint/skills --skill find-the-original-image --agent claude-code

Installs into .claude/skills of the current project.

Files

Find the original image

The goal is almost never "find a match". It is find the earliest publication and read its page. A match tells you the image exists elsewhere; the earliest page tells you the photographer, the date, the caption, and the names — which is what you actually pivot on.

The beginner mistake: uploading the full frame to one engine, getting nothing, and concluding the image is unindexed. Cropping to one distinctive object and re-searching finds things full-frame search cannot.