Skip to content

hoavdc/CodexKit / skills/codexkit-root-cause-analyzer

codexkit-root-cause-analyzer

Verified

Conduct structured root cause analysis using Ishikawa (Fishbone), 5 Whys, and Pareto methods. Suitable for production incidents, quality defects, customer complaints, and recurring operational problems. Use when problems recur or when initial fixes do not resolve the issue. Do not use for one-time, obvious fixes or strategic decision-making.

FileKindSize
SKILL.mdskill md4.9 KB
agents/openai.yamlconfig168 B
examples/common-mistakes.mdmarkdown811 B
examples/good-output.mdmarkdown887 B
verification/checklist.mdmarkdown1.3 KB

verification/checklist.md

View on GitHub
# 4C Verification Checklist — Root Cause Analyzer

> Use this checklist after generating output. Answer each question honestly.

## Correctness — Is it right?

- [ ] Each 'Why' in the chain is causally connected — not just correlated
- [ ] Contributing factors distinguish between necessary and sufficient causes
- [ ] Root cause is a system/process flaw, not an individual's action

## Completeness — Is it done?

- [ ] Problem statement includes who, what, when, where, and magnitude
- [ ] Multiple causal chains explored — not just the first plausible explanation
- [ ] Corrective AND preventive actions are both proposed

## Context-fit — Does it match?

- [ ] Analysis depth matches the severity and recurrence risk
- [ ] Method chosen (5 Whys, Fishbone, Fault Tree) suits the problem type
- [ ] Recommendations are within the team's control to implement

## Consequence — Is it safe to use?

- [ ] If only the corrective action is taken (not preventive), will this recur?
- [ ] Is the root cause systemic enough that other teams should be notified?
- [ ] If we fixed nothing, what's the expected frequency and impact of recurrence?

---

**Final question:** _If this output were used immediately in production, what is the single biggest risk?_

Write the answer here before considering the skill output complete.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall