Debug Issue

Traces bugs through codebases using knowledge graph call-chain and impact analysis.

Updated May 3, 2017
One-click install
npx skills add https://github.com/arnonmoscona/dot_files --skill debug-issue-arnonmoscona
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Debug Issue
Source: https://github.com/arnonmoscona/dot_files/tree/main/claude/projects/toolguard/.claude/skills/debug-issue
Command: npx skills add https://github.com/arnonmoscona/dot_files --skill debug-issue-arnonmoscona

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Debugging unfamiliar or large codebases requires manually tracing call chains and guessing which recent change introduced a bug, which is slow and error-prone. ## Core Features & Use Cases - Graph-Based Code Navigation: Uses semantic search and graph queries to find code related to an issue and trace callers and callees. - Change Detection: Runs change detection to identify whether recent modifications caused the issue. - Impact Analysis: Computes the impact radius of suspected files to reveal what else is affected. - Use Case: When a production bug appears after a deploy, trace the failing execution flow, inspect recent changes, and identify the entry point triggering the bug in a handful of tool calls. ## Quick Start Debug the failing checkout flow by tracing its call chain and checking recent changes with the knowledge graph.

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 trace callers and callees to follow the call chain. Use flow queries to see full execution paths and run change detection to check whether recent edits caused the bug.

How to find which recent change caused a bug?

Run the detect_changes tool to list recent modifications in the suspected area, then use get_impact_radius on changed files to see what downstream code is affected. Recent changes are the most common source of new issues.

What is impact radius analysis in code debugging?

Impact radius analysis shows every part of the codebase affected by a suspected file, computed by traversing the dependency graph. It helps confirm whether a change in one file explains failures elsewhere.

How can I reduce token usage when exploring a code graph?

Always start with get_minimal_context for your task before other graph tools, and use detail_level minimal on all calls. Escalate to standard detail only when minimal output is insufficient, targeting five or fewer tool calls.

When is graph-based debugging not the right approach?

Graph-based debugging requires an indexed knowledge graph of the codebase, so it does not help for unindexed code, runtime-only issues like race conditions, or problems in external services. Use logs and profilers for those cases.