systematic-debugging

Reproduce software failures, isolate scope, and verify minimal fixes.

Updated Apr 15, 2026
One-click install
npx skills add https://github.com/AoManoh/project_templates --skill systematic-debugging-aomanoh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: systematic-debugging
Source: https://github.com/AoManoh/project_templates/tree/main/skills/systematic-debugging
Command: npx skills add https://github.com/AoManoh/project_templates --skill systematic-debugging-aomanoh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It prevents AI debugging from guessing by enforcing a reproducible, evidence-driven workflow that locates the true root cause, applies a minimal fix, and verifies the result.

Core Features & Use Cases

  • Reproduce and Isolate: Collect failure evidence and narrow scope to the smallest reproducing path.
  • Root-Cause Hypothesis: Produce a testable hypothesis tied to specific source logic (not vague possibilities).
  • Verify and Record: Validate the fix using the original reproduction steps, check for regression, and write a debug record to docs for traceability.
  • Guardrails for Stuck Debugging: Detect “repeat attempts / unverified attribution” risk and trigger escalation via pua.

Quick Start

Trigger systematic-debugging when you observe a failing test or runtime error and ask the AI to reproduce the issue, identify the root cause with source-level evidence, implement the minimal fix, verify with the original steps, and write the session to docs/debug.

Frequently Asked Questions about systematic-debugging

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

FAQPage Schema
How do I find the root cause of intermittent software failures instead of guessing?▼

Root cause analysis for intermittent software failures requires reproducing the issue, isolating scope to the smallest path, and forming a testable hypothesis tied to specific source logic. This evidence-driven workflow prevents unverified guesses by validating fixes using original reproduction steps and regression testing.

What is the best way to debug cross-module breakages and multi-file interactions?▼

Debugging cross-module breakages and multi-file interactions demands an evidence-first workflow that collects failure evidence, narrows scope, and produces a source-level root-cause hypothesis. A minimal verified fix is then applied and validated against original reproduction steps to ensure accuracy.

How to systematically debug environment or concurrency anomalies in large applications?▼

Systematically debug environment or concurrency anomalies by reproducing the failure, isolating scope, and forming a testable root-cause hypothesis constrained by SPEC.md phases. Apply a minimal verified fix, check for regressions, and document the session for traceability.

Does evidence-driven debugging work for complex runtime errors without external dependencies?▼

Evidence-driven debugging for complex runtime errors works without external dependencies by enforcing a reproducible workflow. It collects failure evidence, narrows scope to the smallest reproducing path, and applies a minimal fix verified by original reproduction steps and regression-safe testing.

What should I do when my debugging attempts keep repeating without finding the root cause?▼

When debugging attempts repeat without finding the root cause, an evidence-driven workflow detects unverified attribution risk and triggers escalation. It enforces source-level reasoning, original reproduction verification, and persistent documentation to break the cycle of guesswork.

How do I document my debugging trail for regression testing and future traceability?▼

Document your debugging trail for regression testing by writing debug records to docs/debug. Persistent documentation captures the root cause, the minimal fix applied, and the verification steps, ensuring full traceability and preventing future regressions.