debug-issue

Trace call chains from symptom to entry point before proposing bug fixes.

2|Updated Jul 18, 2026
One-click install
npx skills add https://github.com/Arasz/ai-badger --skill debug-issue-arasz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debug-issue
Source: https://github.com/Arasz/ai-badger/tree/main/features/common/skills/debug-issue
Command: npx skills add https://github.com/Arasz/ai-badger --skill debug-issue-arasz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When a bug report or failing test names a symptom but the code path producing it is unknown, developers often guess at fixes without understanding how execution actually reaches the failure. This Skill enforces tracing the full call chain from symptom to entry point before any hypothesis or fix is proposed. ## Core Features & Use Cases - Symptom-to-code location: Find the relevant code via semantic search or baseline grep on error messages, log lines, and exception types. - Bidirectional caller/callee tracing: Walk both callers and callees outward until reaching a test or public entry point such as an HTTP handler, CLI command, or message consumer. - Recent-change detection: Use git log, git blame, or change-detection tooling to check whether a recent commit introduced the bug before assuming it is old. - Use Case: A failing test reports a wrong status code. Use this Skill to locate the code emitting it, trace callers back to the HTTP handler, follow the execution path, and identify the commit that introduced the regression before writing a fix. ## Quick Start Ask the agent to trace why this test fails by walking the call chain from the error message back to its entry point before suggesting any fix.

Frequently Asked Questions about debug-issue

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

FAQPage Schema
How do I trace where a bug comes from in a codebase?

Start by grepping for the error message, log line, or exception type to locate the code, then walk callers and callees outward until you reach a test or public entry point. Only form a hypothesis after the full path is traced.

How to find what calls a function without a code graph tool?

Use your IDE's find-references and go-to-definition features, or run grep -rn on the symbol name to find callers and read the function body for callees. These baseline methods replace graph queries when no graph server is available.

Does this debugging workflow require a code graph server?

No. Every step carries a tool-agnostic baseline: grep for locating code, IDE navigation for tracing, and git log or git blame for change detection. Graph-based calls are optional accelerations, not requirements.

Why check git history when debugging a new bug?

Recent changes are the most common source of new bugs, so running git log -S on the symbol or git blame on suspected lines is cheap relative to guessing. Skipping this check often means missing that yesterday's diff caused today's failure.

When should I use call-chain tracing instead of general debugging?

Use it specifically for the tracing step: when a symptom is located but the call chain to its entry point still needs walking before a hypothesis forms. A general reproduce-isolate-fix discipline governs the overall debugging loop.