Debug Issue

When you're staring at a bug and don't know where to start, this skill uses a knowledge graph to trace the problem systematically. It searches for relevant code nodes, maps out call chains in both directions, visualizes execution flows, and checks recent changes that might have introduced the issue. The get_impact_radius feature is especially handy because it shows you what else breaks when you touch a suspected file. It's built for the kind of debugging where you need to understand how everything connects rather than just grep and guess. The approach assumes you're working in a codebase large enough that tracing callers and callees manually would take forever.

skills.sh installs: 302
GitHub stars: 32.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tirth8205/code-review-graph --skill 'Debug Issue' --agent claude-code

Installs into .claude/skills of the current project.

Files

Debug Issue

Trace a bug through the knowledge graph before reading source.

Steps

Call semantic_search_nodes_tool to find code related to the issue.
Call query_graph_tool with callers_of and callees_of to trace the call chain in both directions.
Call get_flow_tool for the execution path that reaches the suspect code. Its entry point is where the bug is triggered.
Call detect_changes_tool to check whether a recent change caused the issue.
Call get_impact_radius_tool on the suspect files to see what a fix would affect.

Token Efficiency Rules

Call get_minimal_context_tool(task="<your task>") before any other graph tool.
Pass detail_level="minimal" unless it is not enough. Minimal drops source, so leave semantic_search_nodes_tool(include_source=True) and get_review_context_tool at standard.
Prefer a targeted query_graph_tool call over a broad listing call.
Budget: about five tool calls per task. Source snippets stand in for file reads.
Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.