Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

debug-issue — Claude Code skill: what it does, how to install

This skill traces bugs through a code graph before source inspection, then checks call paths and change impact. Use it when an issue needs a narrower debugging scope.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add tirth8205/code-review-graph --skill debug-issue -a claude-code
Open on GitHub

What debug-issue does

debug-issue starts with get_minimal_context_tool, then uses semantic_search_nodes_tool to locate code connected to an issue. It follows callers and callees with query_graph_tool, retrieves an execution path with get_flow_tool, and checks recent changes through detect_changes_tool.

For suspect files, the skill calls get_impact_radius_tool to inspect what a fix could affect. It favours minimal detail and targeted graph queries over broad listings. Its budget is about five tool calls and 800 tokens of graph output per task.

Read the implementation and tests before editing code. The graph narrows the search, so treating its output as a replacement for source review would be a mistake.

What it helps with

  • locate code related to a reported bug
  • trace callers and callees around suspect code
  • find a recent change behind an issue
  • map the execution path to a bug trigger
  • check the impact of a planned fix

Example prompts for the agent

  • Debug this issue through the code graph and identify the execution entry point.
  • Investigate whether a recent change caused this bug, then check the fix impact radius.
  • Trace the call chain for this error before reading the implementation and tests.

How to install debug-issue

1Skills CLI (Vercel)

npx skills add tirth8205/code-review-graph --skill debug-issue -a claude-code

2Manually: put the files in place

~/.claude/skills/debug-issue/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/debug-issue/

From the same set7

The whole set →
build-graph tirth8205 Builds or updates a repository knowledge graph for code review. Use it during first setup, after a branch switch, or following a large refactor. Claude Code CX Codex Cursor +1 1,300installs review-delta tirth8205 This skill reviews changes since the last commit and maps their blast radius. Use it for focused code review without loading the whole project. Claude Code CX Codex Cursor +1 1,200installs review-changes tirth8205 Reviews a change set through a knowledge graph, scoring risk and tracing impact. Use it to inspect changed functions, affected flows, and missing tests. Claude Code CX Codex Cursor +1 1,100installs refactor-safely tirth8205 Plans a refactor from a dependency graph, lists edits before a rename and checks the impact radius before large changes. Claude Code CX Codex Cursor +1 1,100installs explore-codebase tirth8205 Guides coding agents through repository structure using the code-review-graph MCP knowledge graph under tight token budgets. Claude Code CX Codex Cursor +1 1,100installs review-pr tirth8205 This skill reviews a PR or branch through a code knowledge graph, showing risk, affected flows, and test gaps. Use it when a diff needs structural context. Claude Code CX Codex Cursor +1 1,100installs

Similar

metrics-dashboard phuryn A skill that helps you design a product metrics dashboard with North Star Metric, Input Metrics, Health Metrics, and Business Metrics. Use it when defining KPIs, setting up product analytics, or building a data monitoring plan. Claude Code CX Codex Cursor +1 3,000installs brainstorm-ideas-existing phuryn Skill to brainstorm product ideas for an existing product from PM, Designer, and Engineer perspectives. Use it to generate features, solve identified opportunities, or ideate with your product trio. Claude Code CX Codex Cursor +1 3,000installs mem0-vercel-ai-sdk mem0ai Connects Mem0 memory to the Vercel AI SDK. It shows your agent how to retrieve and store context inside generateText and streamText calls. Claude Code CX Codex Cursor +1 508installs node-inspect-debugger Hermes Agent Skill brings real breakpoints, step through, and variable inspection to Node.js debugging instead of console.log. Works with any Node process: tests, dev servers, Ink components. Claude Code CX Codex Cursor +1 396installs cf-cli cloudflare Cloudflare's official CLI for the public API and Workers projects, now available in your editor. Search for commands by task description, manage DNS, storage, and deployments. Claude Code CX Codex Cursor +1 10,700installs qa-only garrytan Reports bugs across browser apps, APIs, CLI tools, and background workers without touching your codebase. Useful for verification runs before a release. Claude Code CX Codex Cursor +1 395installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about debug-issue

How do I install debug-issue in Claude Code?

Run npx skills add tirth8205/code-review-graph --skill debug-issue -a claude-code, then run npx skills add tirth8205/code-review-graph --skill debug-issue -a claude-code again. The skill file is at ~/.claude/skills/debug-issue/SKILL.md.

What does debug-issue do?

It investigates bugs through a code graph by finding related nodes, tracing calls, retrieving execution flow, checking recent changes, and inspecting a fix's impact radius.

How does debug-issue limit graph context?

It calls get_minimal_context_tool first and uses detail_level="minimal" where supported. Standard detail is used only when minimal context is insufficient.

Source text

SKILL.md · MIT 
---
name: debug-issue
description: Systematically debug issues using graph-powered code navigation
---

## Debug Issue

Trace a bug through the knowledge graph before reading source.

### Steps

1. Call `semantic_search_nodes_tool` to find code related to the issue.
2. Call `query_graph_tool` with `callers_of` and `callees_of` to trace the call chain in both directions.
3. Call `get_flow_tool` for the execution path that reaches the suspect code. Its entry point is where the bug is triggered.
4. Call `detect_changes_tool` to check whether a recent change caused the issue.
5. 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"` wherever a tool accepts it. Use "standard" only when minimal is not enough.
- Prefer a targeted `query_graph_tool` call over a broad listing call.
- Budget: about five tool calls and 800 tokens of graph output per task.
- Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.

© tirth8205 · MIT · tirth8205/code-review-graph

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor