cliany-site

Convert web workflows into repeatable CLI commands using Chrome CDP and LLM planning.

10|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/pearjelly/cliany.site --skill cliany-site
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cliany-site
Source: https://github.com/pearjelly/cliany.site/tree/main
Command: npx skills add https://github.com/pearjelly/cliany.site --skill cliany-site

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

cliany-site automates complex web workflows by turning browser interactions into reusable CLI commands via Chrome CDP and LLMs.

Core Features & Use Cases

  • Explore web pages with an LLM-guided plan to auto-generate domain-specific adapters.
  • Replay actions through generated CLI commands with standard JSON envelopes for automation pipelines.
  • Manage sessions and dynamic adapters across multiple domains for scalable web automation.

Quick Start

Describe your target web workflow and run cliany-site doctor to verify prerequisites, then run explore to generate a domain adapter.

Frequently Asked Questions about cliany-site

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn complex web workflows into repeatable CLI commands?

You can turn web workflows into CLI commands by using Chrome CDP AXTree captures combined with LLM-driven planning to explore pages and auto-generate domain-specific adapters for replaying actions.

How does LLM-driven planning work with Chrome CDP for web automation?

LLM-driven planning with Chrome CDP works by capturing the accessibility tree to understand page structure, allowing the LLM to formulate an interaction plan and generate a standardized JSON envelope for automation pipelines.

Do I need Python and a Chrome instance to generate web automation adapters?

Yes, you need Python 3.11+, a running Chrome instance, and valid LLM API keys to securely operate the adapter generation and web automation pipeline.

What is the best way to automate browser interactions across multiple domains?

The best way to automate multi-domain browser interactions is by managing sessions and dynamic domain-specific adapters that translate captured web actions into standardized, replayable JSON envelopes.

How do I start generating a domain-specific adapter for a web page?

To start generating a domain adapter, describe your target web workflow, run the doctor command to verify prerequisites, and then run the explore command to let the LLM guide the adapter generation.