debugging-wizard

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: debugging, developer-tools, logs, performance, research, troubleshooting.

What it does

Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting crashes, or performing log analysis, error investigation, or root cause analysis.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill debugging-wizard

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/debugging-wizard ~/.claude/skills/debugging-wizard

Safety box score

Grade B, low risk: 14 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a local debugging playbook: it runs debuggers, test commands, and git bisect against the user’s codebase. The main risks are ordinary code execution during debugging and a cleanup step that deletes local dependency artifacts; it does not access secrets, elevate privileges, or reach out to remote services by itself.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It explicitly tells the agent to run local debuggers and tests such as `python -m pdb script.py`, `node --inspect-brk script.js`, `dlv debug ./cmd/server`, and `git bisect run npm test`.
Network access	1 (low)	It includes package-install examples like `npm install x` and `npm install`, which can fetch code from the registry, but it does not itself specify remote hosts or data exfiltration.
Filesystem reach	1 (low)	The only destructive file operation shown is project-scoped cleanup, e.g. `rm -rf node_modules package-lock.json`, which stays inside the working tree but deletes local files.
Secrets & credentials	0 (none)	The skill does not ask for API keys, passwords, tokens, `.env` files, browser sessions, or other credential stores.
Privilege & persistence	0 (none)	There is no `sudo`, service registration, shell/profile editing, or OS-wide configuration change.
Instruction hijack surface	0 (none)	It does not tell the agent to ignore instructions, skip confirmations, follow remote content, or hide anything from the user.
Irreversible actions	0 (none)	It is diagnostic guidance only; it does not deploy, publish, pay, message, or delete user data as an end goal.
Transparency	0 (none)	All shipped files are plain markdown with readable commands; there are no binaries, obfuscated blobs, or runtime-downloaded installers.

Before installing

Read `references/quick-fixes.md` and `references/systematic-debugging.md` for the `rm -rf node_modules package-lock.json` step.
Be comfortable with local code execution from `node --inspect`, `python -m pdb`, `dlv debug`, and `git bisect run npm test`.
If you do not want dependency downloads, avoid the `npm install` steps or try them in a throwaway clone first.

Rated 2026-10-21 by an automated review of 6 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/debugging-wizard/SKILL.md
Branch: main
Updated: 2026-09-19

app-platform-troubleshooting — Debug running App Platform applications by accessing containers, analyzing logs, running diagnostics, and applying fixes.
agents-debug — Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes.
aws-observability — Builds, configures, debugs, and optimizes AWS observability with CloudWatch (Log Insights, Metrics, Alarms, Dashboards, EMF), X-Ray, CloudTrail.
principle-fix-root-causes — Apply when debugging.
code-reviewer — Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries.
cpp-pro — Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques.