trace

Generate competing hypotheses and rank evidence to trace complex issues.

Updated May 31, 2026
One-click install
npx skills add https://github.com/Ewallyw/claude-config-public --skill trace-ewallyw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/Ewallyw/claude-config-public/tree/main/claude-config-master/claude-config-master/skills/trace
Command: npx skills add https://github.com/Ewallyw/claude-config-public --skill trace-ewallyw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps users trace complex issues by orchestrating evidence-driven hypotheses and gathering evidence to explain observed results.

Core Features & Use Cases

  • Evidence-Driven Tracing: Orchestrates competing tracer hypotheses and gathers evidence to explain observed results.
  • Team Mode Orchestration: Utilizes Claude built-in team mode for collaborative tracing with multiple lanes.
  • Hypothesis Generation: Automatically generates multiple hypotheses for tracing.
  • Evidence Gathering: Collects evidence for and against each hypothesis.
  • Evidence Ranking: Ranks evidence based on strength.
  • Critical Unknown Identification: Identifies critical unknowns to reduce uncertainty.
  • Discriminating Probe Recommendations: Recommends the best next steps to collapse uncertainty.
  • Use Case: Ideal for tracing ambiguous, causal, evidence-heavy questions like runtime bugs, performance issues, or architecture analysis.

Quick Start

Use the trace skill to explain why a runtime error occurred by providing the error observation.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I trace complex runtime errors using evidence-driven hypothesis generation?

Tracing complex runtime errors involves generating competing hypotheses and gathering evidence for and against each one. This evidence-driven approach ranks evidence strength and identifies critical unknowns to reduce uncertainty.

What is the best way to resolve ambiguous performance issues through causal analysis?

The best way to resolve ambiguous performance issues is orchestrating team mode tracing to generate multiple hypotheses, gather supporting evidence, and recommend discriminating probes to collapse uncertainty.

How does evidence ranking help with complex issue resolution?

Evidence ranking helps complex issue resolution by evaluating the strength of gathered evidence for and against each hypothesis. This allows you to identify critical unknowns and prioritize next steps to reduce uncertainty.

Can I use team mode orchestration for architecture analysis and tracing?

Yes, you can use team mode orchestration for architecture analysis by running multiple collaborative tracing lanes. It generates competing hypotheses and gathers evidence to explain observed architectural results.

When do I need to identify critical unknowns during runtime error analysis?

You need to identify critical unknowns during runtime error analysis when evidence is ambiguous. Recognizing these unknowns allows you to recommend the best next steps and discriminating probes to reduce uncertainty.