debug-execution

Execute browser debug plans with Chrome DevTools MCP and capture evidence.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/metasaver/claude-marketplace --skill debug-execution
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debug-execution
Source: https://github.com/metasaver/claude-marketplace/tree/main/plugins/metasaver-core/skills/workflow-steps/debug-execution
Command: npx skills add https://github.com/metasaver/claude-marketplace --skill debug-execution

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates browser debugging by executing a debug plan and collecting evidence (screenshots, console, network).

Core Features & Use Cases

  • Evidence capture: DOM snapshots, screenshots, console and network logs.
  • Step validation: Verifies outcomes against expectations per step.
  • Plan-driven: Works from a prepared debug-plan with URL and interactions.

Quick Start

Run the debug-execution step after you have a debug-plan from debug-plan to collect evidence.

Frequently Asked Questions about debug-execution

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

FAQPage Schema
How do I capture evidence from browser interactions during debugging?

Browser debug execution captures DOM snapshots, screenshots, console logs, and network diagnostics automatically as you navigate and interact with a web application. Run debug-execution after preparing a debug-plan to collect a structured evidence bundle organized for validation and reporting.

What steps can I automate with Chrome DevTools debugging?

Chrome DevTools debugging automates navigation to a URL, baseline DOM and visual capture, interaction loops (click, fill, hover, key press), and outcome validation. Each step collects evidence and compares results against expected outcomes to verify functionality.

Can I validate web application behavior against expected outcomes?

Yes. Debug execution validates each interaction step against specified expectations, collecting console and network diagnostics alongside evidence. Results are packaged in a comprehensive validation report ready for analysis and documentation.

Do I need to prepare a debug plan before running browser debugging?

Yes. Debug execution works from a prepared debug-plan that defines the target URL and interaction sequence. Generate the debug-plan separately, then pass it to debug-execution to collect evidence and validate outcomes.

What happens if an interaction doesn't match the expected outcome?

Debug execution captures the mismatch in its validation report, including DOM state, screenshot, and diagnostic logs. The structured evidence bundle documents what occurred versus what was expected, supporting root-cause analysis.

How are console and network logs collected during debugging?

Console and network diagnostics are captured automatically as part of the evidence bundle during each interaction step. They're included in the comprehensive report alongside DOM snapshots and screenshots for full debugging context.