gemini-image-describer

85 / 100 · Low risk

Fine to try. Some of what it can do is expected: a media skill usually calls an AI service over the internet.

By duotify/GitHubClawToolkit (GitHub) · media · 254 stars · scanned at commit 583144b

Use this skill when a user provides an image (local file or URL) and wants a detailed Traditional Chinese description of the image content. Prefer this skill for requests like "describe this image", "what's in this picture", "OCR this screenshot", "辨識這張圖", "描述這張照片", or when extracting text from screenshots or photos.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this.

Found in 7 places.

skills/gemini-image-describer/SKILL.md, line 21node .agents/skills/gemini-image-describer/scripts/describe.js <image-path-or-url>
skills/gemini-image-describer/SKILL.md, line 27GEMINI_API_KEY=your_api_key node .agents/skills/gemini-image-describer/scripts/describe.js "https://example.com/photo.jpg"
skills/gemini-image-describer/SKILL.md, line 31GEMINI_API_KEY=your_api_key node .agents/skills/gemini-image-describer/scripts/describe.js "./photos/screenshot.png"

Show 4 more

skills/gemini-image-describer/SKILL.md, line 35GEMINI_API_KEY=your_api_key node .agents/skills/gemini-image-describer/scripts/describe.js "data:image/png;base64,iVBOR..."
skills/gemini-image-describer/SKILL.md, line 43IMAGE_DESCRIBER_DRY_RUN=1 node .agents/skills/gemini-image-describer/scripts/describe.js "https://example.com/photo.jpg"
skills/gemini-image-describer/SKILL.md, line 64mkdir -p artifacts/{issue-comment-id}
skills/gemini-image-describer/SKILL.md, line 100cd .agents/skills/gemini-image-describer

Can call paid AI services billed to you

This is disclosed by the author in the skill's SKILL.md or README. Expected for a media skill.

Found in 1 place.

skills/gemini-image-describer/src/describe.js, line 16import { GoogleGenAI } from "@google/genai";

Sends data to these websites: generativelanguage.googleapis.com

The author does not mention this. Expected for a media skill.

Found in 2 places.

skills/gemini-image-describer/src/describe.js, line 16import { GoogleGenAI } from "@google/genai";
skills/gemini-image-describer/src/describe.js, line 102const res = await fetch(rawInput, {

Other copies in this repository

duotify/GitHubClawToolkit has 1 more folder with a skill named gemini-image-describer. This page shows the lowest-scoring copy.

templates/codex-gemini-api/.agents/skills/gemini-image-describer 85/100 · Low risk

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'gemini-image-describer' ] || [ -L ~/.agents/skills/'gemini-image-describer' ]; then echo 'A skill folder named gemini-image-describer already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/duotify/GitHubClawToolkit' "$d" && git -C "$d" checkout --quiet '583144b0947e3d551f0c4bff0bcc6015c61bf683' -- 'skills/gemini-image-describer' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/gemini-image-describer' ~/.agents/skills/'gemini-image-describer' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'gemini-image-describer' ~/.claude/skills/'gemini-image-describer' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for duotify/GitHubClawToolkit shows the score of its lowest-scoring skill.

SkillTrust badge for duotify/GitHubClawToolkit

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/duotify/GitHubClawToolkit.svg)](https://zalavijaysinh.github.io/skilltrust/repos/duotify/GitHubClawToolkit/)

Score history

Date	Version	Score
2026-11-13	`583144b`	85