skill CX Codex

debugging · mrgoonie — Claude Code skill: what it does, how to install

Q: How to install debugging in Claude Code?

Run `npx skills add mrgoonie/claudekit-skills --skill debugging -a claude-code` in your terminal. The configuration file is saved to `~/.claude/skills/debugging/SKILL.md`.

Enforces a disciplined debugging methodology that stops guesswork and requires fresh test proof before marking tasks done.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add mrgoonie/claudekit-skills --skill debugging -a claude-code

Open on GitHub

What debugging does

The skill replaces trial-and-error patching with a structured investigation workflow. It organizes debugging into four sub-skills: systematic investigation, root-cause tracing, defense-in-depth validation, and mandatory post-fix verification.

Under these rules, an assistant cannot jump straight into editing code. It must investigate the root failure and track invalid inputs to their origin. The framework explicitly forbids declaring success without running verification commands and inspecting output.

This strict sequence prevents masking symptoms with temporary workarounds. According to the author, structured debugging achieves a 95% first-time fix rate compared to 40% when thrashing with random changes.

What it helps with

trace root causes backward through complex call stacks
stop the agent from applying random trial-and-error fixes
prevent recurring regressions across multiple application layers
verify bug fixes with fresh command execution before completion

Example prompts for the agent

Use root-cause-tracing to find where this invalid payload originated in the stack
Apply systematic-debugging to investigate the auth test failure
Run verification-before-completion checks before marking this bug resolved

How to install debugging

1Skills CLI (Vercel)

npx skills add mrgoonie/claudekit-skills --skill debugging -a claude-code

2Manually: put the files in place

~/.claude/skills/debugging/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/debugging/

1Skills CLI (Vercel)

npx skills add mrgoonie/claudekit-skills --skill debugging -a codex

2Manually: put the files in place

.agents/skills/debugging/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add mrgoonie/claudekit-skills --skill debugging -a cursor

2Manually: put the files in place

.cursor/skills/debugging/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install mrgoonie/claudekit-skills debugging

2Manually: put the files in place

.github/skills/debugging/SKILL.md

1Skills CLI (Vercel)

npx skills add mrgoonie/claudekit-skills --skill debugging -a gemini-cli

2Platform CLI

gemini skills install https://github.com/mrgoonie/claudekit-skills --path .claude/skills/debugging

Manually: put the files in place

.devin/skills/debugging/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add mrgoonie/claudekit-skills --skill debugging -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about debugging

How to install debugging in Claude Code?

Run npx skills add mrgoonie/claudekit-skills --skill debugging -a claude-code in your terminal. The configuration file is saved to ~/.claude/skills/debugging/SKILL.md.

What does the debugging skill do?

It enforces a disciplined four-phase troubleshooting process. The agent must locate the origin of invalid data, build layered guards, and verify results with fresh test output before completing the task.

What sub-skills are included in debugging?

The suite contains four modules: systematic-debugging, root-cause-tracing, defense-in-depth validation across four application layers, and verification-before-completion.

Similar skills

All skills for Testing and QA →

debugging by other authors comes first.

debugging tursodatabase A skill for tracking down tursodb bugs: compare bytecode against SQLite, turn on trace logs, run ThreadSanitizer, replay a seed and measure stack use. CX Codex +1 1,300installs debugging akillness A skill that walks the agent through a reproduce → isolate → verify loop for concrete bugs, regressions and flaky failures. Useful once you already have a failing test or request. CX Codex +1 361installs systematic-debugging spencerpauly Enforces a structured debugging workflow on your AI assistant instead of random edits. It helps isolate elusive bugs and verify root causes with evidence. CX Codex +1 545installs debugging-and-error-recovery addyosmani This skill guides an agent from reproducing a failure to checking the fix. Use it when tests fail, a build breaks, or runtime behavior differs from expectations. CX Codex +1 62,800installs debugger VoltAgent Community Diagnoses software failures, reads stack traces, and isolates root causes to fix elusive bugs. Helpful when logs alone do not explain a crash. 13,459installs debugging-network-issues daymade A methodology for network, streaming and protocol failures where the obvious cause is probably wrong. CX Codex +1 675installs debugging-strategies Seth Hobson This skill gives an agent a step-by-step way to investigate bugs, crashes, and performance problems. Use it when a project behaves unexpectedly. CX Codex 13,414installs principle-prove-it-works backnotprop Forces the agent to verify task outputs against real artifacts before declaring completion. It prevents models from reporting success just because code compiles. CX Codex +1 5,200installs

From the same set21

devops A skill for deploying and managing infrastructure across Cloudflare, Docker, GCP and Kubernetes. Useful when the agent has to ship a service or debug a cluster. CX Codex +1 987installs chrome-devtools A skill that drives Puppeteer scripts from the shell: screenshots, clicks, form filling, Core Web Vitals and network inspection. CX Codex +1 736installs aesthetic A skill that walks your coding agent through interface design: reading other people's layouts, generating design images, and iterating until they hold up. CX Codex +1 714installs problem-solving A collection of structured creative thinking techniques to unblock agent reasoning. Helps find clean abstractions when conventional coding solutions hit a dead end. CX Codex +1 570installs media-processing Runs FFmpeg and ImageMagick pipelines for video transcoding, audio extraction, image batch processing, and HLS streaming manifests. CX Codex +1 558installs ai-multimodal A skill that runs audio, video, image and PDF tasks through the Gemini API. Useful when you need a transcript, a screenshot read, or tables pulled out of a document. CX Codex +1 530installs context-engineering Guides LLM agent context design, token compaction, and memory isolation to prevent attention degradation during long runs. CX Codex +1 495installs shopify A skill for building on Shopify: apps, checkout and admin extensions, Liquid themes, plus GraphQL and REST API work. CX Codex +1 450installs