Drill into root cause with a 5-Why why chain, why analysis, or structured root cause investigation.

MITAuto-check passedDevelopment

Install 5why Root Cause

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill 5why-root-cause -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins 5why-root-cause --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/RBraga01/Quality-Engineering-Skills/skills/problem-solving/5why-root-cause .claude/skills/5why-root-cause && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
5why-root-cause
GitHub stars
1.2k
Token cost
~2k tokens
SKILL.md length
1,019 words
Files
2 (incl. references)
Skills in repo
686
Repo updated
First seen
Licence
MIT

At a glance

Drill into root cause with a 5-Why why chain, why analysis, or structured root cause investigation.

  • Works in 4 steps: State the symptom precisely → Build the Why chain → Validate the chain → …
  • FMEA cause analysis
  • SKILL.md covers Goal, Required Execution Checklist, When to use and Prerequisites, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

5why Root Cause is an agent skill from hashgraph-online/awesome-codex-plugins. Drill into root cause with a 5-Why why chain, why analysis, or structured root cause investigation. Builds a Why chain from symptom to systemic root cause, validates each step with evidence, and detects circular reasoning. Use for 8D D4, CAPA, FMEA cause analysis, or any quality investigation requiring confirmed root cause identification.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/chain-validation.md`).

It sits in Development, covering Root cause analysis. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is MIT.

When your agent uses it

  • FMEA cause analysis
  • Any quality investigation requiring confirmed root cause identification

Example prompts

  • “/5why-root-cause”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. State the symptom precisely
  2. Build the Why chain
  3. Validate the chain
  4. Validate the root cause

What it can do on your machine

Read from SKILL.md and the folder at commit 78497e5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

5why Root Cause loads about 2k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 1,019 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its MIT licence (© hashgraph-online). 1,019 words, ~2,020 tokens.

Download SKILL.mdSave it as .claude/skills/5why-root-cause/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
5why-root-cause
description
Drill into root cause with a 5-Why why chain, why analysis, or structured root cause investigation. Builds a Why chain from symptom to systemic root cause, validates each step with evidence, and detects circular reasoning. Use for 8D D4, CAPA, FMEA cause analysis, or any quality investigation requiring confirmed root cause identification.
license
MIT
metadata.author
RBraga01
metadata.version
1.1
metadata.iso-9001
10.2
metadata.iatf-16949
10.2.3
metadata.domain
quality-engineering
metadata.subdomain
problem-solving
metadata.industries
automotive,electronics,aerospace,medical,general
metadata.status
approved
metadata.created
2026-06-01

5-Why Root Cause Analysis

Goal

Identify and validate a systemic root cause through a structured, evidence-based Why chain that can be directly linked to a corrective action.

Required Execution Checklist

  • Problem defined with measurable data (value vs. specification)
  • Linear Why chain built — one cause path at a time, no branching
  • Each Why supported by objective evidence (not opinion or "probably")
  • Logical consistency verified — reversal check passed
  • Systemic root cause identified (not "human error" or symptom)
  • Root cause validated: reproducibility test + elimination test
  • Output enables definition of corrective action (PCA or CAPA)

When to use

Use 5-Why for any quality problem with a single, linear cause chain. Works best for process failures, equipment failures, and procedural non-compliances. For complex problems with multiple contributing causes, use Fishbone first to identify candidate root causes, then use 5-Why to drill into each.

If multiple potential cause paths exist — do not combine them into one chain. Run separate 5-Why chains for each path and determine which is confirmed by evidence.

Prerequisites

  • Problem is clearly defined (use Is/Is-Not to scope if needed)
  • The investigation team has access to the process, machine, or system where the defect occurred
  • Physical evidence or production records are available

Use within 8D — Occurrence and Escape

When used for 8D D4, two separate Why chains are required:

ChainStarting questionWhat it finds
Occurrence chain"Why did the defect happen?"Root Cause of Occurrence (RCO) — the process or design failure that created the defect
Escape chain"Why was the defect not detected before reaching the customer?"Root Cause of Escape (RCE) — the detection system failure

Run each chain independently. Do not mix occurrence and escape causes in the same chain — they have different corrective actions. The occurrence chain addresses prevention; the escape chain addresses detection.


Workflow

Step 1 — State the symptom precisely

Start with a factual, measurable problem statement. Not "the part was bad" but "dimension X measured 23.5mm; specification is 25.0 ± 0.5mm on part number Y, batch 2026-05-12."

The first Why answers: "Why did [specific symptom] occur?"


Step 2 — Build the Why chain

For each Why, follow these rules:

Rule 1: Each answer must be supported by evidence

  • Acceptable evidence: measurement data, production records, machine logs, direct observation, physical samples
  • Not acceptable: "probably," "maybe," "someone said"

Rule 2: Each answer must logically lead to the next Why

  • Test reversibility: "Because [Why N], therefore [Why N+1]"
  • If the sentence doesn't make logical sense, the chain is broken

Rule 3: Keep the chain focused

  • One Why chain = one cause path
  • If you reach a fork (two possible causes), investigate both separately

Rule 4: Stop at a systemic root cause

  • You have reached root cause when: fixing it would prevent the defect from ever recurring
  • Typical systemic root causes: missing procedure, inadequate training system, process design gap, absence of poka-yoke, measurement system failure

Step 3 — Validate the chain

Work backwards through the completed chain:

"Because [Why 5], therefore [Why 4]. Because [Why 4], therefore [Why 3]..."

If any step does not logically follow, revise that step.


Step 4 — Validate the root cause

The root cause is correct if:

  • Reproducibility test: can you deliberately create the defect by triggering the root cause? Yes → validated
  • Elimination test: if you fix the root cause, does the defect disappear? (trial run or logical test)

If neither test is possible, the root cause is not confirmed — it is a hypothesis. Do not close the investigation on a hypothesis. Either obtain evidence to confirm it, or investigate alternative cause paths.


Show full SKILL.md (439 more words)Show less

Example

Problem: Connector pin bent at incoming inspection, 12/200 parts (6%).

#WhyEvidenceValidated?
1Why are pins bent?Pins deformed during insertion into housingMicroscopy confirmed deformation pattern
2Why during insertion?Insertion force exceeded pin yield strengthForce measurement: 48N, pin rated to 35N
3Why was force 48N?Operator used incorrect insertion tool (hand press vs. pneumatic jig)Tool log: jig under maintenance since 05-10
4Why was incorrect tool used?No instruction specifying which tool to use when jig is unavailableWork instruction reviewed — no contingency
5Why no contingency?Tool maintenance downtime not considered in work instruction designProcess FMEA missing this scenario

Root cause: Work instruction design does not cover tool substitution contingency; FMEA does not identify tool maintenance as a failure scenario.

Reversal check: "Because FMEA doesn't cover tool maintenance → therefore no contingency instruction → therefore wrong tool used → therefore excess force → therefore pins bent." ✓ Logical.


Common mistakes — reject these

"Human error" as a final answer → Ask: why was the error possible? What in the system allowed it?

"Operator didn't follow the procedure" → Ask: why didn't they follow it? Was it unclear? Not trained? Impossible to follow?

"Machine was out of calibration" → Ask: why? What is the calibration interval? Was it missed? Why?

Circular reasoning → "The part was defective because it didn't meet spec, because it was defective." → reframe the first Why as the physical mechanism.

Stopping at a symptom, not a cause → "The defect occurred because the part was wrong" — that IS the defect, not a cause.

Branching the chain prematurely → Each Why step should have one answer. If you have two, run two separate 5-Why chains.

Output content

A validated 5-Why must include:

  1. Problem statement (measured, quantified)
  2. Each Why with: the answer, the supporting evidence, and validated (Yes/No)
  3. Root cause statement
  4. Reversal check (one sentence confirming logical flow)
  5. Validation method (how the root cause was confirmed)
  6. Corrective action direction — what type of action addresses this root cause (used as direct input to 8D D5 or CAPA)

Output Format

At the start of each use, ask the user:

"How would you like to receive the output? A — Structured Markdown (formatted tables and sections, ready to copy) B — Plain tables (simplified structure for Excel or Word) C — Narrative report (flowing text for a formal document or email)

Default: A."

Adapt all output sections to the chosen format. If the platform or session context already defines a format preference, skip this question.

Reference files

Changelog

VersionDateAuthorChange
1.02026-06-01@RBraga01Initial release
1.12026-06-03@RBraga01Added dual-chain requirement (occurrence + escape), evidence status tracking

© hashgraph-online, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/RBraga01/Quality-Engineering-Skills/skills/problem-solving/5why-root-cause of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/chain-validation.md

Open the folder on GitHubat commit 78497e5

Compare with similar skills

5why Root Cause next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

5why Root Cause compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
5why Root Cause this skillhashgraph-online/awesome-codex-plugins1.2k—~2kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
OpenLogi macOS Permissions TriageAprilNEA/OpenLogi23k—~2.5kAutomated safety check: NotesApache-2.0
Bug Finder for daisyUIsaadeghi/daisyui43k—~2.3kAutomated safety check: PassMIT
Root Cause Debugginggarrytan/gstack136k—~1.4kAutomated safety check: PassMIT
Review PRapache/shardingsphere21k—~6.4kAutomated safety check: PassApache-2.0

Similar skills

  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes
  • Bug Finder for daisyUI

    saadeghi/daisyui

    Investigates suspected bugs in the daisyUI monorepo through read-only analysis, then writes a decision-ready fix plan in tmp/bugs without changing any product code.

    43k GitHub stars~2.3k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Root Cause Debugging

    garrytan/gstack

    Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.

    136k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Review PR

    apache/shardingsphere

    Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or authorized repository evidence.

    21k GitHub stars~6.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    DevelopmentAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 686 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated today
    Auto-check passed
  • Manuscript Engagement Analytics

    hashgraph-online/awesome-codex-plugins

    Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…

    1.2k GitHub stars~875 tokensUpdated today
    Auto-check passed

Categories

Questions about 5why Root Cause

What does 5why Root Cause do?

Drill into root cause with a 5-Why why chain, why analysis, or structured root cause investigation. 5why Root Cause is an agent skill from hashgraph-online/awesome-codex-plugins. Drill into root cause with a 5-Why why chain, why analysis, or structured root cause investigation.

When should I use 5why Root Cause?

5why Root Cause fits situations like: FMEA cause analysis; any quality investigation requiring confirmed root cause identification.

How do I install 5why Root Cause in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill 5why-root-cause -a claude-code`. Or copy the skill folder (plugins/RBraga01/Quality-Engineering-Skills/skills/problem-solving/5why-root-cause in hashgraph-online/awesome-codex-plugins) into .claude/skills/5why-root-cause in your project. Claude Code loads it when a task matches its description.

How do I install 5why Root Cause in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill 5why-root-cause -a codex`. Or copy the skill folder (plugins/RBraga01/Quality-Engineering-Skills/skills/problem-solving/5why-root-cause in hashgraph-online/awesome-codex-plugins) into .agents/skills/5why-root-cause in your project. Codex loads it when a task matches its description.

Can I use 5why Root Cause in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill 5why-root-cause -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/5why-root-cause, .gemini/skills/5why-root-cause, .github/skills/5why-root-cause and .opencode/skills/5why-root-cause in your project.

What does 5why Root Cause need to run?

SKILL.md names no scripts, command-line tools or credentials: 5why Root Cause is instructions for the agent only.

Does 5why Root Cause access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is 5why Root Cause safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does 5why Root Cause use?

5why Root Cause is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does 5why Root Cause use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to 5why Root Cause?

Skills that share tags, products or a category with 5why Root Cause: Code Design Rationale Investigator (cursor/plugins, 10k stars), OpenLogi macOS Permissions Triage (AprilNEA/OpenLogi, 23k stars), Bug Finder for daisyUI (saadeghi/daisyui, 43k stars) and Root Cause Debugging (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 5why Root Cause?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.