Debug Issue
- 771 installs
- 28.5k repo stars
- Updated August 2, 2026
- tirth8205/code-review-graph
debug issue is a Claude Code skill that systematically traces bugs in large codebases using a pre-built knowledge graph and graph query tools for developers who need call-chain and impact analysis instead of guessing fil
About
debug issue is a graph-powered debugging skill from tirth8205/code-review-graph that replaces ad-hoc file grepping with structured navigation through a codebase knowledge graph. The workflow starts with semantic_search_nodes_tool to locate related code, then uses query_graph_tool with callers_of and callees_of, get_flow for execution paths, detect_changes_tool for recent regressions, and get_impact_radius_tool on suspected files. Developers reach for debug issue when a bug spans multiple modules in a large repository and they need caller-callee context, full flow traces, and blast-radius analysis before applying a fix.
- 5-step graph-powered debugging workflow
- Always begins with get_minimal_context to minimize tokens
- Combines semantic search, caller/callee tracing, execution flow, change detection and impact radius
- Enforces detail_level="minimal" and ≤5 tool calls per task
- Targets completion in ≤800 output tokens
Debug Issue by the numbers
- 771 all-time installs (skills.sh)
- Ranked #58 of 596 Debugging skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/tirth8205/code-review-graph --skill debug-issueAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 771 |
|---|---|
| repo stars | ★ 28.5k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | tirth8205/code-review-graph ↗ |
How do you debug bugs using a code knowledge graph?
Systematically trace bugs in a large codebase using a pre-built knowledge graph instead of guessing where to look.
Who is it for?
Developers debugging regressions in large repos that already have a code-review-graph knowledge graph indexed.
Skip if: Greenfield projects without a built knowledge graph or simple single-file bugs solvable with a stack trace alone.
When should I use this skill?
A developer reports a bug in a large codebase and the agent should trace callers, callees, flows, and recent changes via graph tools.
What you get
Call chain trace, execution flow map, recent change suspects, and impact radius report for affected files.
- call chain trace
- execution flow map
- impact radius report
By the numbers
- Uses 5 graph debugging tools: semantic search, query graph, get flow, detect changes, impact radius
Files
Debug Issue
Use the knowledge graph to systematically trace and debug issues.
Steps
1. Use semantic_search_nodes_tool to find code related to the issue. 2. Use query_graph_tool with callers_of and callees_of to trace call chains. 3. Use get_flow to see full execution paths through suspected areas. 4. Run detect_changes_tool to check if recent changes caused the issue. 5. Use get_impact_radius_tool on suspected files to see what else is affected.
Tips
- Check both callers and callees to understand the full context.
- Look at affected flows to find the entry point that triggers the bug.
- Recent changes are the most common source of new issues.
Token Efficiency Rules
- ALWAYS start with
get_minimal_context(task="<your task>")before any other graph tool. - Use
detail_level="minimal"on all calls. Only escalate to "standard" when minimal is insufficient. - Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.
Related skills
Azure DiagnosticsSystematically diagnose and resolve production issues on Microsoft Azure using official Microsoft guidance.495k1.3kAzure MessagingQuickly diagnose and fix connection, authentication, and message-processing failures when using Azure Event Hubs or Service Bus SDKs.483k1.3k
Diagnosing BugsGet a systematic, step-by-step process that surfaces the real root cause instead of guessing at bugs.291k200k
Use My BrowserWhen their agent task requires access to the live browser session, rendered DOM state, authenticated dashboards, localhost apps, or DevTools-selected elements instea269k71
Systematic DebuggingFollow a repeatable four-phase process that forces root-cause discovery before any code changes.210k265k
Safe DebugGet conservative, non-destructive diagnosis of deep learning and agent errors before any code changes are made.185k512How it compares
Use debug issue when a knowledge graph is available; fall back to conventional stack-trace debugging for small repos without graph indexing.
FAQ
Which graph tools does debug issue use?
debug issue from code-review-graph uses semantic_search_nodes_tool, query_graph_tool with callers_of and callees_of, get_flow, detect_changes_tool, and get_impact_radius_tool to trace bugs systematically.
When is debug issue better than grep?
debug issue suits large codebases where bugs cross module boundaries. Graph caller-callee and flow tracing reveal entry points and impact radius that keyword search alone often misses.
Is Debug Issue safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.