gitnexus-debugging_skill

Overview

This skill helps you debug bugs, trace errors, and find the root cause of failing code paths using GitNexus tools. It connects error symptoms to execution flows, shows callers and callees for suspect symbols, and lets you trace processes and custom call chains. Use it to turn an error message or intermittent failure into a concrete investigation plan.

How this skill works

Run targeted queries for error text or symptoms to discover related processes and symbols. Inspect a suspect with context to see incoming and outgoing calls, then read process traces or run custom cypher traces to follow execution paths. If the index is stale, refresh analysis (e.g., npx gitnexus analyze) before querying.

When to use it

• You get an error message and need to know where it originates
• A function returns wrong data or behaves unexpectedly
• An endpoint returns 500 or another HTTP error intermittently
• You must find who calls a method or what a method calls
• You want to trace a regression to recent changes

Best practices

• Start by clearly capturing the symptom (exact error text, stack, or failing input)
• Run gitnexus_query for the error text, then pick the most relevant symbol or process
• Use gitnexus_context on suspects to reveal callers, callees, and external dependencies
• Trace process flows via READ gitnexus://repo/.../process/... before inspecting source files
• Use gitnexus_cypher for tailored call-chain queries when default traces miss relationships

Example use cases

• Investigate a 500 from the payment endpoint: query error text → inspect validatePayment → find external fetchRates without timeout
• Track down a wrong return value by starting with the function name, view callers to see upstream data sources
• Diagnose intermittent failures by looking for external calls or async dependencies in context
• Find who calls a deprecated helper to plan safe removal or refactor
• Map hot paths for a performance issue by finding symbols with many callers