skills/use-context-root-cause-analysis/SKILL.md
Root cause analysis with 5 Whys.
npx skillsauth add thkt/claude-config use-context-root-cause-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fix the root cause, not the symptom. Symptom fixes add complexity; root-cause fixes prevent recurrence.
Ask "why" five times, descending through abstraction levels.
| Step | Level | | ---- | ------------------------ | | 1 | Observable fact | | 2 | Implementation detail | | 3 | Design decision | | 4 | Architectural constraint | | 5 | Root cause |
| Tip | Description | | ---------------- | -------------------------------- | | Stay factual | Evidence, not assumptions | | Don't stop early | First "why" is rarely root cause | | Don't go deep | Stop when actionable | | Validate | "Because [5], therefore [4]..." | | Verify fix | "Will this prevent the problem?" | | Watch complexity signals | When intermittent / multiple independent changes overlap / behavior unexplained, enumerate ≥3 cause-layer candidates before converging |
| Field | Description | | ---------- | ---------------------------------------- | | Symptom | User-facing failure | | Root cause | Why the failure occurred (5 Whys result) | | Pattern | Isolated / Recurring / Systematic |
| Value | Meaning | | ---------- | ------------------------------------------------- | | Isolated | Single location, no recurrence path | | Recurring | Similar code exists nearby, recurrence possible | | Systematic | Design-rooted, architecture-level recurrence risk |
Consumers (e.g., /fix Non-obvious flow) branch on the Pattern field to decide
whether to apply defense-in-depth or escalate.
| Topic | File | | -------------------- | -------------------------------------------------- | | Worked examples | ${CLAUDE_SKILL_DIR}/references/five-whys.md | | Symptom → Root Cause | ${CLAUDE_SKILL_DIR}/references/symptom-patterns.md |
documentation
Generates and updates .claude/OUTCOME.md interactively. When the file is absent or empty (no Behavior / all sections TBD), collects content via AskUserQuestion and writes the stub; when present, shows the current state and applies updates.
development
Judge a SKILL.md against craft axes (single responsibility, description distinctiveness, imperative voice, verifiable completion, calibration, progressive disclosure) and apply the fixes the audit surfaces. Do not use for format-presence-only checks (use reviewer-prompt) or reproducibility loops (use /tuning).
tools
Internal helper for /think Step 11. Renders SOW.md + Spec.md as an integrated Astro view and returns a dev server URL.
development
Extract repository spec while detecting bugs, spec gaps, and consistency drift via dual-purpose documentation. OUTCOME.md-axis question-driven exploration with ephemeral output. Do NOT use for code review (use /audit or /polish), feature implementation (use /code), planning only (use /think), or single-bug fix (use /fix).