Image Scanner

Scans image folders to identify formats, analyze dominant colors and styles, and automatically classify and organize photography files.

Security Scan

The skill's code and instructions are internally consistent for a filename-and-metadata-based image scanner; it does not request credentials, install code from external URLs, or perform network exfiltration — however some advertised capabilities (pixel-level color analysis and automatic moving) are not implemented and should be treated as unimplemented/optional features.

Purpose & Capability

Name and description match what the code does: scanning a directory, identifying image file extensions, inferring style from filenames, and producing a report. The code's operations (reading directory contents and file metadata) are proportional to the stated purpose.

Instruction Scope

SKILL.md promises dominant-color analysis and style classification; the index.js implementation only infers style from filename keywords and sets color to 'unknown' with a comment stating an image analysis library is required. The README/usage and CLI args align with the code, but the declared pixel-level analysis is not implemented.

Install Mechanism

No install spec and only a small local index.js file — nothing is downloaded or written during install. This is low-risk and expected for an instruction-only/light-code skill.

Credentials

The skill requires no environment variables, no credentials, and no special config paths. It only requires filesystem read access to the directory the user provides, which is proportionate to its function.

Persistence & Privilege

Skill is not always-enabled and does not request elevated or persistent privileges. However the 'classify' action references moving files (not implemented in the code) — users should verify whether automatic moves will occur and confirm actions before running on important folders.

Assessment

This skill appears coherent and locally self-contained: it reads the directory you point it at, inspects filenames and file metadata, and prints a report. It does not send data over the network or require credentials. Two practical cautions: (1) SKILL.md advertises color-based analysis but the shipped code does not perform pixel analysis (color remains 'unknown'); if you need true dominant-color detection the code must be extended with an image-processing library. (2) The classify/move behavior is only described and not implemented — treat the 'classify' action as a dry-run until you confirm whether file-moving logic will run. Before using on important photos, test on a small sample directory and keep backups. If you expect automatic pixel analysis or automatic moves, ask the author for an updated implementation or review/modify the code locally first.

# image-scanner

## Description

扫描指定文件夹，识别图片格式、分析主色调和风格，自动分类整理摄影作品。

## Triggers

- 扫描图片文件夹

- 分析照片类型

- 整理摄影作品

- 识别图片颜色风格

- 批量处理图片文件

## Capabilities

- 扫描目录中的所有图片文件

- 识别图片格式（JPG/PNG/RAW/HEIC/TIFF 等）

- 分析图片主色调（冷色/暖色/黑白/鲜艳）

- 按风格分类（人像/风景/静物/建筑等）

- 生成分类报告

- 可选：自动创建子文件夹并移动文件

## Usage

openclaw skill image-scanner --path <目录路径> --action scan

openclaw skill image-scanner --path <目录路径> --action classify --output <输出目录>