debugging-toolkit-smart-debug

Automate AI-assisted debugging analysis for software issues in production and staging environments.

Updated Feb 24, 2026
One-click install
npx skills add https://github.com/chicanoandres702/SentientAIBrowser --skill debugging-toolkit-smart-debug-chicanoandres702
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debugging-toolkit-smart-debug
Source: https://github.com/chicanoandres702/SentientAIBrowser/tree/main/.agents/workflows/debugging-toolkit-smart-debug
Command: npx skills add https://github.com/chicanoandres702/SentientAIBrowser --skill debugging-toolkit-smart-debug-chicanoandres702

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-assisted debugging workflows that orchestrate triage, instrumentation suggestions, and root-cause analysis for complex software issues.

Core Features & Use Cases

  • Initial triage: analyze errors, stack traces, environment, and logs.
  • Observability-driven data collection: gather metrics, traces, and events for faster diagnosis.
  • Hypothesis generation and strategy selection: propose multiple hypotheses with evidence and test plans.
  • Safe instrumentation and production-ready fixes: suggest deployment-safe instrumentation and validation steps.

Quick Start

Provide a detailed issue description and environment context to receive a prioritized diagnostic plan.

Frequently Asked Questions about debugging-toolkit-smart-debug

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

FAQPage Schema
How do I perform root-cause analysis on a complex production error using stack traces?

Root-cause analysis on stack traces is automated by generating prioritized hypotheses, evaluating evidence, and proposing targeted fix plans to accurately identify the underlying software issue.

What's the best way to structure triage for staging environment performance issues?

Triage for staging performance issues is structured by analyzing error messages, evaluating reproduction steps, and mapping affected components to generate a systematic diagnostic plan.

How does AI-assisted debugging handle observability data collection?

AI-assisted debugging handles observability by guiding the collection of metrics, traces, and events, then applying that data to select diagnostic strategies and validate root-cause hypotheses.

Can I use this debugging approach to suggest safe instrumentation for production environments?

Yes, this approach suggests deployment-safe instrumentation for production environments, recommending targeted observability data collection steps that avoid disrupting live system performance.

Do I need to provide reproduction steps to get a fix proposal for my software issue?

Providing reproduction steps, environment context, and affected components significantly improves the accuracy of generated fix proposals, validation plans, and prevention steps for your software issue.

Limitations of automated triage when diagnosing software issues without environment context?

Automated triage is limited without environment context, as missing logs, metrics, or stack traces restrict hypothesis generation and prevent accurate root-cause analysis and fix validation.