Skip to content
Back to skills

Tarsier Vision Utilities Web Interaction Agents

ASecurity

Tarsier is a Python library by Reworkd that provides vision utilities for AI web interaction agents. It visually tags interactable elements on web pages with bracketed IDs, enabling LLMs to take actions like CLICK [23], and includes an OCR algorithm that converts page screenshots into whitespace-structured text representations that even text-only LLMs can understand.

  • 36 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added June 2, 2026
ai-agentsjavascripttypescriptpythongojavashellgitsecurity

Works with

  • cli

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned June 2, 2026

npx -y skills add agentskillexchange/skills --skill tarsier-vision-utilities-web-interaction-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tarsier Vision Utilities Web Interaction Agents?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Tarsier Vision Utilities Web Interaction Agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/agentskillexchange-tarsier-vision-utilities-web-interaction-agents/badge)](https://www.skillsdirectory.com/skills/agentskillexchange-tarsier-vision-utilities-web-interaction-agents)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "Tarsier Vision Utilities for Web Interaction Agents"
slug: "tarsier-vision-utilities-web-interaction-agents"
description: "Tarsier is a Python library by Reworkd that provides vision utilities for AI web interaction agents. It visually tags interactable elements on web pages with bracketed IDs, enabling LLMs to take actions like CLICK [23], and includes an OCR algorithm that converts page screenshots into whitespace-structured text representations that even text-only LLMs can understand."
github_stars: 1758
verification: "security_reviewed"
source: "https://github.com/reworkd/tarsier"
author: "Reworkd"
category: "Browser Automation"
framework: "Custom Agents"
tool_ecosystem:
  github_repo: "reworkd/tarsier"
  github_stars: 1758
---

# Tarsier Vision Utilities for Web Interaction Agents

Tarsier is a Python library by Reworkd that provides vision utilities for AI web interaction agents. It visually tags interactable elements on web pages with bracketed IDs, enabling LLMs to take actions like CLICK [23], and includes an OCR algorithm that converts page screenshots into whitespace-structured text representations that even text-only LLMs can understand.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install tarsier
- npm run build

Requirements and caveats from upstream:
- <img alt="Python" src="https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54" />
- python
- This compiles the TypeScript into JavaScript, which can then be utilized in the Python package.

Basic usage or getting-started notes:
- If you've tried using an LLM to automate web interactions, you've probably run into questions like:
- shell
- Visit our [cookbook](https://github.com/reworkd/Tarsier/tree/main/cookbook) for agent examples using Tarsier:

- Source: https://github.com/reworkd/tarsier
- Extracted from upstream docs: https://raw.githubusercontent.com/reworkd/tarsier/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/tarsier-vision-utilities-web-interaction-agents/)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.