debug-issue

Trace and debug code issues using knowledge graph navigation tools.

Updated Sep 8, 2026
One-click install
npx skills add https://github.com/bmiit145/leadBee --skill debug-issue-bmiit145
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: debug-issue
Source: https://github.com/bmiit145/leadBee/tree/main/.gemini/skills/debug-issue
Command: npx skills add https://github.com/bmiit145/leadBee --skill debug-issue-bmiit145

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Debugging unfamiliar or large codebases often means hours of manual searching through files to understand call chains and execution paths. This Skill provides a systematic workflow that uses a code knowledge graph to locate relevant code, trace callers and callees, and identify recent changes that may have introduced a bug. ## Core Features & Use Cases - Graph-Powered Code Navigation: Use semantic search and graph queries to find code related to an issue and trace call chains in both directions. - Execution Flow Analysis: Inspect full execution paths through suspected areas and measure the impact radius of suspected files. - Change Detection: Check whether recent changes are the source of a new issue. - Token-Efficient Operation: Start with minimal context and escalate detail only when needed, targeting completion in five or fewer tool calls. - Use Case: A bug report says lead updates fail intermittently. Use the Skill to semantically locate the update handler, trace its callers and callees, review the execution flow, and check recent changes to pinpoint the regression. ## Quick Start Ask the AI to debug the reported issue by tracing the relevant code paths with the knowledge graph tools, starting from minimal context.

Frequently Asked Questions about debug-issue

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

FAQPage Schema
How do I debug an issue using a code knowledge graph?▼

Start with semantic search to find code related to the issue, then query callers and callees to trace call chains. Inspect execution flows through suspected areas and check recent changes, which are the most common source of new bugs.

How to trace function callers and callees in a large codebase?▼

Use graph query tools with callers_of and callees_of operations on the suspected function. Checking both directions reveals the full context, including the entry point that triggers the bug and everything the function affects downstream.

Can graph-based debugging find regressions from recent changes?▼

Yes. Run the change detection tool to see what was recently modified, then use impact radius analysis on those files to see what else is affected. Recent changes are the most common source of new issues.

Why start with minimal context when debugging with graph tools?▼

Minimal context keeps token usage low and narrows scope quickly. The workflow targets completing a debug task in five or fewer tool calls, escalating to standard detail only when the minimal output is insufficient.

What are the limitations of graph-based code debugging?▼

The graph narrows scope but does not replace reading the source. You should still read the implementation and its tests before changing code, since graph relationships alone cannot confirm runtime behavior or business logic correctness.