Skill

graph-debug

From bdk

Systematically debug issues using graph-powered code navigation — trace call chains, find execution paths, correlate with recent changes.

npx claudepluginhub broneq/bdk --plugin bdk

Tool Access

This skill is limited to using the following tools:

mcp__code-review-graph__semantic_search_nodes_tool mcp__code-review-graph__query_graph_tool mcp__code-review-graph__get_flow_tool mcp__code-review-graph__detect_changes_tool mcp__code-review-graph__get_impact_radius_tool mcp__code-review-graph__get_minimal_context_tool

Preview

> Relies on BDK foundation (STARTUP_INSTRUCTIONS.md). Assumes environment discovery has already run (language, test runner, build tool are known).

SKILL.md

Similar Skills

using-superpowers

178.4k

Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.

3 files

superpowers

Stats

Stars0

Forks0

Last CommitApr 30, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Relies on BDK foundation (STARTUP_INSTRUCTIONS.md). Assumes environment discovery has already run (language, test runner, build tool are known).

Graph Debug

Systematically trace and debug issues using the knowledge graph.

Steps

Run get_minimal_context(task="debug <issue>") first.
Use semantic_search_nodes to find code related to the issue.
Use query_graph with callers_of and callees_of to trace call chains.
Use get_flow to see full execution paths through suspected areas.
Run detect_changes to check if recent changes caused the issue.
Use get_impact_radius on suspected files to see what else is affected.

Tips

Check both callers and callees to understand full context.
Look at affected flows to find entry point that triggers the bug.
Recent changes are the most common source of new issues.

Token Efficiency

Start every session with get_minimal_context(task="<your task>").
Use detail_level="minimal" on all calls. Escalate to "standard" only when minimal is insufficient.
Target: ≤5 tool calls, ≤800 total output tokens.