opencli-browser

The opencli-browser skill provides an interface for agents to control a Chrome browser session. It supports inspecting page content, interacting with UI elements via selectors or numeric references, managing browser sessions, and capturing network data.

14.6K
Installs
6
Use cases
5/10
Quality

Is opencli-browser safe to install?

Review the source first

Review the source first: our audit of opencli-browser's source files found 25 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands to control a live browser, which can perform any action a user can take in a browser, including navigating to arbitrary URLs, submitting forms, and uploading files.

How we audit skills: our security review methodology.

Who is this skill for?

AI agents that require browser automation to perform tasks like data extraction, form submission, or navigating logged-in web flows.

What can you do with it?

  • Inspecting web page structure and content
  • Filling and submitting web forms
  • Clicking UI elements and navigating links
  • Extracting data from web pages
  • Managing browser sessions for multi-step workflows
  • Capturing network traffic for data retrieval

How good is this skill?

Quality score: 5/10. The documentation is comprehensive, providing clear instructions on session management, the target contract, and error handling. It includes specific command references and best practices for agent-based browser interaction.

What does the skill file contain?

SKILL.md
# opencli-browser

The first reader of this CLI is an agent, not a human. Every subcommand returns a structured envelope that tells you exactly what matched, how confident the match is, and what to do if it didn't. Lean on those envelopes — do not guess.

This skill is for **driving a live browser** to accomplish an agent task. If you are building a reusable adapter under `~/.opencli/clis/<site>/` use `opencli-adapter-author` instead.

---

## Prerequisites

```bash
opencli doctor
```

Until `doctor` is green, nothing else will work. Typical failures: Chrome not running, extension not installe...

Frequently asked questions

How do I handle page navigation or form submissions?

Run the state command to get a fresh snapshot of the page after any navigation, form submit, or SPA route change, as these actions invalidate previous element references.

Should I use CSS selectors or numeric references?

Prefer numeric references from state or find commands, as they are resilient to DOM drift. Use CSS selectors only when necessary and pair them with --nth if multiple matches exist.

How do I verify that a write action succeeded?

Run get value or state after type, select, or fill commands to confirm the input was correctly applied, especially for autocomplete widgets or masked fields.

What is the purpose of the doctor command?

The doctor command verifies the environment, checking if Chrome is running, extensions are installed, and debug ports are available.

Data sourced from jackwener/opencli on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

find-skills

2.3M

Users seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages

The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.

highclipackage-managervercel-labs

agent-browser

506.7K

AI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications

The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.

highbrowser-automationclivercel-labs

image-to-video

355.0K

Developers and users who need to automate video generation from images using the RunComfy platform

The image-to-video skill routes user requests to specific RunComfy animation models based on intent. It selects HappyHorse 1.0 I2V for general animation, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition. The skill executes the RunComfy CLI to process inputs and download generated video files.

highaivideo-generationagentspace-so

video-edit

338.7K

Users of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer

The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.

highvideo-editingai-agentagentspace-so