skill CX Codex

why · neolabhq — Claude Code skill: what it does, how to install

Q: How to install why in Claude Code?

Run `npx skills add NeoLabHQ/context-engineering-kit --skill why -a claude-code` in your terminal.

Q: Can I change how many why questions are asked?

Yes, you can adjust the `DEPTH` variable, which defaults to 5 iterations.

Conducts iterative Five Whys root cause analysis for technical bugs and incidents. Helps uncover process and system gaps instead of settling for superficial patches.

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

npx skills add NeoLabHQ/context-engineering-kit --skill why -a claude-code

Open on GitHub

What why does

This skill guides the AI assistant through structured Five Whys root cause investigations. Instead of fixing surface symptoms, it recursively asks why an event happened, tracing failures back to missing validations, config discrepancies, or procedural oversights. The default iteration limit is set to 5 via the DEPTH variable, which you can adjust.

Execution begins with a problem definition, followed by step-by-step questioning and backwards validation from cause to symptom. When an issue stems from multiple sources, the analysis branches out to isolate each track. If human error appears in the chain, the skill pushes further to explain why the system allowed that error to occur.

Stopping at the first technical flaw leaves the underlying workflow vulnerable. Because of this, the final output outlines concrete remediations—such as pull request checklist updates or test environment changes—addressing root causes directly.

What it helps with

Trace intermittent end-to-end test failures to configuration drift
Investigate production 500 error spikes during high load
Identify bottlenecks causing slow container build pipelines
Separate multi-factor system failures into isolated investigation branches

Example prompts for the agent

/why Users receive 500 errors during checkout
/why Docker build step takes over an hour in CI
/why Integration tests fail intermittently during database setup

How to install why

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill why -a claude-code

2Manually: put the files in place

~/.claude/skills/why/SKILL.md

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

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill why -a codex

2Manually: put the files in place

.agents/skills/why/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill why -a cursor

2Manually: put the files in place

.cursor/skills/why/SKILL.md

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

1GitHub CLI

gh skill install NeoLabHQ/context-engineering-kit why

2Manually: put the files in place

.github/skills/why/SKILL.md

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill why -a gemini-cli

2Platform CLI

gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/why

Manually: put the files in place

.devin/skills/why/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill why -a opencode

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

Questions about why

How to install why in Claude Code?

Run npx skills add NeoLabHQ/context-engineering-kit --skill why -a claude-code in your terminal.

What does the why skill do?

It conducts an iterative Five Whys investigation to drill down from surface symptoms to the root causes of engineering issues.

Can I change how many why questions are asked?

Yes, you can adjust the DEPTH variable, which defaults to 5 iterations.

Similar skills

Everything for Testing and QA →

why by other authors comes first.

why cursor The skill investigates why code took its current shape by checking Git history and available MCP sources, then returns cited findings about decisions and tradeoffs. CX Codex +1 5,700installs thinking-five-whys-plus tjboudreaux Builds an evidence-backed causal chain from a localized fault to its systemic root. It helps uncover why an issue happened when symptom-level hotfixes keep failing. CX Codex +1 571installs debug cyrusagents Works through a reported bug from reproduction to a minimal fix. Use it when you need to trace an error and verify the result. CX Codex +1 826installs hunt tw93 Pinpoints root causes before touching code when an app crashes or regresses. Enforces reproducible evidence and verification before applying any fix. CX Codex +1 14,900installs troubleshooting ChromeDevTools Diagnoses connection failures and tool errors in Chrome DevTools MCP step by step. Helpful when the server refuses to launch or tab commands fail. CX Codex +1 3,200installs Debug Mode Instructions official github A GitHub Copilot subagent that walks debugging in phases: reproduce the bug, find the root cause, patch it, verify. Useful when a failure is flaky and you don't know where to start. ★ 40,418repo stars debugging mrgoonie Enforces a disciplined debugging methodology that stops guesswork and requires fresh test proof before marking tasks done. CX Codex +1 569installs

From the same set55

do-in-parallel Runs isolated tasks across separate files concurrently via sub-agents and validates work with automated judges. Fits batch refactoring and doc generation. CX Codex +1 1,200installs analyse-problem This skill turns a problem into a one-page A3 document: background, current condition, goal, root cause and an action plan. CX Codex +1 1,200installs setup-serena-mcp Step-by-step assistant workflow to configure the Serena MCP server for semantic code exploration and symbol editing. CX Codex +1 1,200installs write-tests The skill reads your uncommitted and untracked git changes and writes tests for them. Useful when the logic is done but coverage is not. CX Codex +1 1,200installs review-local-changes Reviews uncommitted working-tree changes and returns a list of issues with improvement suggestions. Handy right before you commit. CX Codex +1 1,200installs git-notes Attaches notes to commits without touching their SHA. Useful for marking reviews, test results or adding context after the fact. CX Codex +1 1,100installs setup-context7-mcp This skill walks the agent through setting up the Context7 MCP server and writes the library IDs into CLAUDE.md so code follows current docs. CX Codex +1 1,100installs reset Clears or archives the active FPF reasoning cycle so you can start a fresh analytical session. CX Codex +1 1,100installs