gsd-debug

Parse subcommands and flags to run isolated debug agents and generate a Root Cause Report.

1|Updated May 24, 2026
One-click install
npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill gsd-debug-tinner-deinno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd-debug
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/gsd/gsd-debug
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill gsd-debug-tinner-deinno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

gsd-debug helps you systematically debug issues by isolating subcomponents and preserving progress even when the conversation context resets.

Core Features & Use Cases

  • Scientific-method debugging workflow: Gather symptoms, form hypotheses, run targeted investigation, and converge toward a root cause.
  • Persistent debug checkpoints: Use a session manager to retain state across context resets and support continuation.
  • Subagent isolation: Orchestrates a session manager and a debugger agent to reduce confusion and improve repeatability.
  • Diagnose-only mode: Run the workflow to produce a Root Cause Report without applying a fix.

Quick Start

Run the skill with: gsd-debug --diagnose Provide a clear description of the issue you are seeing.

Frequently Asked Questions about gsd-debug

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

FAQPage Schema
How do I debug an issue systematically when my conversation context keeps resetting?

To debug systematically despite context resets, use persistent checkpoints to retain investigation state across sessions. This allows you to preserve gathered symptoms and formed hypotheses, then continue root-cause analysis without losing progress when the context resets.

What is the scientific method approach for root-cause analysis during incident triage?

Root-cause analysis using the scientific method involves gathering symptoms, forming hypotheses, and running targeted investigations via isolated debug agents. This structured workflow converges toward a reliable root cause while reducing confusion and improving repeatability.

How do I run a diagnose-only investigation to find a root cause without applying a fix?

To run a diagnose-only investigation, execute the debug workflow with the --diagnose flag and provide a clear issue description. The system parses subcommands, runs isolated debug agents, and generates a Root Cause Report without applying any fixes.

Can I list investigation statuses and continue a previous debug session using slugs?

Yes, you can list statuses and continue a previous debug session. The workflow supports status tracking by slug and continuation of an investigation, utilizing a session manager to orchestrate state retention across context resets.

Does subagent isolation help with debug session management?

Subagent isolation helps debug session management by orchestrating a session manager and a debugger agent separately. This isolation reduces context confusion and improves the repeatability of targeted investigations during root-cause analysis.