Agent skill

chromium-debug-use

Attach to a user's already-open Chromium-family browser for live inspection and light interaction after explicit local approval

Stars 172
Forks 39

Install this agent skill to your Project

npx add-skill https://github.com/marcusquinn/aidevops/tree/main/.agents/tools/browser/chromium-debug-use

SKILL.md

Chromium Debug Use

Read tools/browser/chromium-debug-use.md first.

Use This Skill When

The user wants to inspect or lightly interact with something already open in a Chromium-family browser (Chrome, Brave, Edge, Vivaldi, Chromium) before committing to a heavier automation tool.

Workflow

  1. Confirm explicit, user-approved live-session investigation.
  2. If the debug port is not yet open, have the user launch with the flag from tools/browser/chromium-debug-use.md.
  3. Use .agents/scripts/chromium-debug-use-helper.sh version and list to confirm access.
  4. Prefer snapshot, html, and eval to understand the page before using click, type, navigate, or screenshot.
  5. Once the flow is understood, hand off to the best-fit longer-term tool:
    • tools/browser/playwright.md — repeatable isolated automation
    • tools/browser/dev-browser.md — aidevops-managed persistent profile
    • tools/browser/playwriter.md — per-tab extension consent in the user's normal browser
    • tools/browser/chrome-devtools.md — performance, network, and console inspection

Safety

  • Local-only and temporary; the user must have enabled the debug path for this investigation.
  • Prefer loopback endpoints and temporary profiles.
  • Do not use this path for unrelated tabs or long-lived background control.

Commands

bash
.agents/scripts/chromium-debug-use-helper.sh version
.agents/scripts/chromium-debug-use-helper.sh list
.agents/scripts/chromium-debug-use-helper.sh snapshot <target>
.agents/scripts/chromium-debug-use-helper.sh html <target> [selector]
.agents/scripts/chromium-debug-use-helper.sh eval <target> "document.title"
.agents/scripts/chromium-debug-use-helper.sh click <target> "button.submit"
.agents/scripts/chromium-debug-use-helper.sh type <target> "hello world"
.agents/scripts/chromium-debug-use-helper.sh screenshot <target> /tmp/page.png

Use --browser-url http://127.0.0.1:9222 when the session is not on the default endpoint.

Expand your agent's capabilities with these related and highly-rated skills.

marcusquinn/aidevops

pageindex

PageIndex - Vectorless reasoning-based RAG for document retrieval

172 39
Explore
davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results