onboard
Explains this repository's shared Claude Code setup to a new teammate, covering what is committed and shared, what stays…
Finds the root cause of a bug, failure or recurring problem by asking "why" until the answer is a cause you can fix. Use when the user asks why something keeps happening, or wants the root cause rather than a quick fix.
Claude Code
$ npx -y skills add wesammustafa/claude-code-quest --skill five-whys --agent claude-code
Codex
$ npx skills add wesammustafa/claude-code-quest --skill five-whys -a codex -y
Cursor
$ npx skills add wesammustafa/claude-code-quest --skill five-whys -a cursor -y
Gemini CLI
$ npx skills add wesammustafa/claude-code-quest --skill five-whys -a gemini-cli -y
GitHub Copilot
$ npx skills add wesammustafa/claude-code-quest --skill five-whys -a github-copilot -y
OpenCode
$ npx skills add wesammustafa/claude-code-quest --skill five-whys -a opencode -y
Windsurf
$ npx skills add wesammustafa/claude-code-quest --skill five-whys -a windsurf -y
# What: a project skill that finds a problem's root cause by asking "why" until the answer is something you can fix. # Runs: when you type /five-whys <problem>, or when Claude matches your request to the description. # Side effects: none intended. It tells Claude to investigate and change no files; each tool call still follows your permission settings. # Requires: Claude Code. Platforms: any. # Remove: delete .claude/skills/five-whys/. # Tested in Claude Code v2.1.285 (stable) on macOS, 2026-10-06 name: five-whys description: Finds the root cause of a bug, failure or recurring problem by asking "why" until the answer is a cause you can fix. Use when the user asks why something keeps happening, or wants the root cause rather than a quick fix. argument-hint: "[problem]"
Find the root cause of this problem: $ARGUMENTS
If no problem is given, ask for one in a single sentence, then stop.
1. Restate the problem as a symptom someone can observe: what happens, where and when. 2. Ask "Why does this happen?" Answer from evidence: the code, tests, logs and git history. Mark any answer you can't back with evidence as a guess. 3. Ask "Why?" of that answer, and keep going until the answer is a cause the team can change. That often takes about five rounds; stop sooner if you get there, and say so if you need more. 4. Check the chain backwards: each cause must explain the step before it. 5. Report the chain as a numbered list, the root cause in one sentence, then one fix for the root cause and one for the symptom.
Don't change any files. Propose the fixes and let the user decide.
Learn Claude Code by doing it, one small step at a time, with Pip cheering you on. How it works · The three levels · Every page
Explains this repository's shared Claude Code setup to a new teammate, covering what is committed and shared, what stays…
The team's checklist for reviewing a change to linkcheck. Use before you commit or open a pull request.
The team's review of a change to linkcheck, run the same way on a laptop and in CI. Use on a staged diff or a pull request.
Builds a requested feature test-first, one behavior at a time, and stops at a diff for review. Use when the user asks for a new…
Adds a one-line entry for the staged changes to CHANGELOG.md. Use when the user asks for a changelog entry.
Runs the link checker on a folder and explains each broken link it finds, with the file, the line and a likely fix. Use when…
Draws static SVG figures for lessons, READMEs and manuals in the AI Engineering from Scratch look: paper panel, blueprint accent,…
End-to-end workflow for creating complete JavaScript concept documentation, orchestrating all skills from research to final review
Test a learner on a single Claude Code tutorial lesson (01-10) with 10 questions, scoring answers and flagging weak spots. Use…