Root cause analysis with 5 Whys methodology for software problems. Triggers: 根本原因, root cause, 5 Whys, なぜなぜ分析, 対症療法, patch, symptom, 症状, 表面的, workaround, ワークアラウンド, 本質的, 応急処置, bandaid, quick fix.
/plugin marketplace add thkt/claude-config/plugin install complete-workflow-system@thkt-development-workflowsThis skill is limited to using the following tools:
references/five-whys.mdreferences/symptom-patterns.mdTarget: Solve problems once and properly by addressing root causes, not symptoms.
| Type | Example | Result |
|---|---|---|
| Symptom Fix | Add setTimeout to wait for DOM | Works now, breaks later |
| Root Cause Fix | Use React ref properly | Permanent solution |
| Symptom Fix | Add flag to prevent double-submit | Complexity grows |
| Root Cause Fix | Disable button during submission | Simple, reliable |
| Section | File | Focus | Triggers |
|---|---|---|---|
| 5 Whys | references/five-whys.md | Analysis process, templates | 5 Whys, なぜなぜ |
| Patterns | references/symptom-patterns.md | Common symptom→cause patterns | 対症療法, workaround |
Before implementing a fix, ask:
Problem: Button click triggers action twice
Solution: Use ref instead of state for imperative flag, or disable button properly
| Principle | Application |
|---|---|
| Prevention > Patching | Best fix prevents the problem entirely |
| Simple > Complex | Root cause solutions are usually simpler |
| Ask Why | Don't accept the first answer |
| Progressive Enhancement | Can CSS/HTML solve this? |
// Bad: Symptom: setTimeout to wait for DOM
useEffect(() => {
setTimeout(() => {
document.getElementById("target")?.scrollIntoView();
}, 100);
}, []);
// Good: Root cause: Use React ref
const targetRef = useRef<HTMLDivElement>(null);
useEffect(() => {
targetRef.current?.scrollIntoView();
}, []);
// Bad: Symptom: Multiple effects to sync state
useEffect(() => {
setFilteredItems(items.filter((i) => i.active));
}, [items]);
useEffect(() => {
setCount(filteredItems.length);
}, [filteredItems]);
// Good: Root cause: Derive state, don't sync
const filteredItems = useMemo(() => items.filter((i) => i.active), [items]);
const count = filteredItems.length;
// Bad: Symptom: Parent polling child for state
const childRef = useRef()
useEffect(() => {
const interval = setInterval(() => { childRef.current?.getValue() }, 1000)
}, [])
// Good: Root cause: Proper data flow (lifting state or callbacks)
const [value, setValue] = useState()
return <Child onValueChange={setValue} />
enhancing-progressively - CSS-first approach often addresses root causesapplying-code-principles - Design principles prevent root cause issuesroot-cause-reviewer - Primary consumer of this skillThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.