Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

ModLens — Vision Bridge

Gives text-only models plug-in vision: hand it an image path and it returns structured JSON with full OCR, layout regions, and semantics.

UtilitiesIntermediate★ 699⑂ 22AI score 9/10Last updated: Aug 13, 2026

What it does

  • Fires automatically whenever an image path or URL (.png, .jpg, .webp, .heic, ...) or a pasted-image placeholder ([Image #1], [Unsupported Image]) shows up and the model cannot see the pixels.
  • Forbids DIY OCR (no PIL, no tesseract) and instead runs the modlens CLI, returning JSON with result.ocr.full_text, result.layout.regions, result.semantics, and an explicit uncertainty list.
  • Runs modlens guard before the first read so models that already have native vision are told to read the image themselves.
  • Also handles provider setup and switching: Gemini API key, OpenAI-compatible endpoints, Claude API, or Claude Code CLI.
  • Includes a runtime resolution order (PATH modlens → npx → bunx) and retry rules for schema mismatch and timeout failures.

Who it's for

  • Anyone working with screenshots, diagrams, or receipts inside a text-only model session.
  • Developers on CLI/terminal workflows where image attachments aren't possible.
  • Teams that want multiple vision providers chained with failover and quota accounting.

Examples

  1. Paste ~/shots/error.png; the skill runs modlens -i ~/shots/error.png and quotes the exact stack trace text back to you.
  2. Feed a UI mockup with --prompt "focus on button labels and placement" to extract layout regions for a front-end spec.
  3. On first use with empty config, ask "set up modlens with my Gemini key" and it follows the onboarding reference to enable only the provider you choose.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/liustack/modlens/HEAD/skills/modlens/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/modlens folder from the GitHub repo liustack/modlens into my ~/.claude/skills/modlens/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/liustack/modlens.git /tmp/modlens && mkdir -p ~/.claude/skills && cp -r /tmp/modlens/skills/modlens ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Install Node.js 22.13+ (https://nodejs.org) or Bun (https://bun.sh); verify with node -v.
  3. Clone the repo: git clone https://github.com/liustack/modlens.git /tmp/modlens
  4. Copy the skill in: mkdir -p ~/.claude/skills && cp -r /tmp/modlens/skills/modlens ~/.claude/skills/
  5. Restart Claude Code and confirm ~/.claude/skills/modlens/SKILL.md exists.
  6. Check your environment: npx --yes --package @liustack/modlens@3.11.0 modlens doctor
  7. Add a provider key (e.g. a Gemini API key). If unsure, ask Claude to "help me configure modlens" and it will follow the bundled configure reference.
  8. Paste an image path to confirm end-to-end operation.
View source on GitHub ↗License: MIT