OpenSkillIndex← back to search
claude-codeopenclawautomation

Skills image-collect

This skill extracts knowledge from an image and saves it locally.

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/bondli/image-collect" ~/.claude/skills/openclaw-skills-image-collect && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/bondli/image-collect" ~/.openclaw/skills/openclaw-skills-image-collect && rm -rf "$T"
manifest: skills/bondli/image-collect/SKILL.md
tags
#image-processing#ocr#data-extraction#local-storage#content-understanding
source content

Image Collect Skill

This skill extracts knowledge from an image and saves it locally.

When to use

Use this skill when:

  • User sends an image
  • User asks to save image as knowledge
  • Image needs OCR or content understanding

What it does

  1. Download image
  2. Extract text and meaning
  3. Generate summary
  4. Save image locally
  5. Append knowledge to JSON database

Command

Run:

node dist/index.js "<image_url>"

Example:

node dist/index.js "https://example.com/image.png" node dist/index.js "data:image/png;base64,xxxx" node dist/index.js "/tmp/image.png"

Output

Returns extracted knowledge including:

  • summary
  • keywords
  • text
  • saved image path