mcpField
C
claude-vision-skill

claude-vision-skill

github.com/asuojunAgent workflows2.3k63 installsUpdated 6d ago
Repository

About claude-vision-skill

claude-vision-skill guides an agent to inspect images when its current model lacks native image input. It invokes a bundled Node.js script for local paths, URLs, or clipboard images, with fallback behavior and configuration guidance.

Key features

  1. 01Inspect images from file paths
  2. 02Process remote image URLs
  3. 03Read images from clipboard
  4. 04Fallback handling for missing paths

Use cases

  1. 01Describe a local image for a user
  2. 02Analyze an image shared by URL
  3. 03Handle a pasted image without a visible path

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/asuojun/claude-vision-skill --skill claude-vision-skill

After installing, type/claude-vision-skillin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

AGENTS.md
.gitignore
README.md
cyberboss-setup.md
clipboard.ps1
CLAUDE.md
vision.js
clipboard.swift

Details

From the project README

Vision Helper

The current model may not support native image input. When the user provides an image path or URL, do not rely on viewing the image directly. Instead run:

node /Users/wwu/.codex/skills/claude-vision-skill/vision.js "<absolute image path>" "<prompt>"

For an image URL:

node /Users/wwu/.codex/skills/claude-vision-skill/vision.js --url "<image url>" "<prompt>"

When the user pastes an image into the chat but no file path or URL is visible:

node /Users/wwu/.codex/skills/claude-vision-skill/vision.js --clipboard "<prompt>"

--clipboard reads the current image from the system clipboard (macOS uses a bundled Swift helper, Windows uses a bundled PowerShell script; the pasted image is usually still there). If it fails, ask the user to save the image to a file and provide the absolute path.

Fallback rules (automatic):

  • If a local path is given but the file does not exist, vision.js automatically falls back to the clipboard.
  • If no image path or URL is given at all, vision.js automatically tries the clipboard.
  • Pass --no-fallback to disable this behavior and fail with an explicit error instead.

Rules:

  • Always use the absolute path to vision.js.
  • Use an absolute image path for local files, or --url for remote images.
  • Prefer --clipboard when the user pasted an image with no accessible path.
  • Use Chinese for descriptions unless the user asks otherwise.
  • Configuration lives in .env next to vision.js (DASHSCOPE_API_KEY, VISION_MODEL, DASHSCOPE_BASE_URL). Never print or commit the API key.
  • If the API call fails, report the error to the user and ask them to check the key, model, or base URL.

Comments

Markdown supported