Five Whys

Run an evidence-grounded five-whys RCA: claims verified by fact-checker subagents, causal links stress-tested by a cynic subagent. For internal RCAs, post-mortems, "why did this happen". Not for customer-facing incident write-ups.

280 stars 15 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add intercom/2x-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add intercom/2x-skills --skill five-whys
Manual install
git clone --depth 1 https://github.com/intercom/2x-skills.git /tmp/2x-skills
mkdir -p ~/.claude/skills
cp -r /tmp/2x-skills/plugins/incident-tools/skills/five-whys ~/.claude/skills/five-whys

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Five whys — grounded and adversarially verified

Build a causal chain from impact to actionable root cause using the classic
five-whys technique (https://en.wikipedia.org/wiki/Five_whys), with two
additions the classic method lacks: every fact is verified against a primary
source, and the finished chain must survive an adversarial review before it
ships. The output is only done when a skeptical expert reading it can re-derive
every claim from the cited evidence.

## Ground rules (non-negotiable)

1. **Every factual claim cites a primary source.** A metric query you ran, a
   code line (`file:line`), a log entry, a config value read from the live
   system, a timestamped event. "The incident doc says" and "everyone knows"
   are not sources. Keep the query, link, or path next to the claim so a
   reader can re-run it.
2. **Label every claim's epistemic status.**
   - **Measured** — you or a subagent observed it directly during this
     investigation.
   - **Derived** — arithmetic on measured values; show the arithmetic.
   - **Inferred** — a best-fit mechanism not yet directly observed. An
     inferred claim MUST name the observation that would confirm or refute it
     ("inference, pending X"). Never present an inference as fact.
3. **Re-verify inherited numbers.** Figures from earlier write-ups, tickets,
   dashboards, or drafts get re-measured, not copied. Stale blast-radius
   numbers and wrong mechanisms survive in RCA docs precisely because nobody
   re-checks them.
Read the full skill on GitHub

Details

Skill name
five-whys
Path
plugins/incident-tools/skills/five-whys/SKILL.md
License
MIT
Repo updated
11 November 2026

FAQ

What does the Five Whys skill do?

Run an evidence-grounded five-whys RCA: claims verified by fact-checker subagents, causal links stress-tested by a cynic subagent. For internal RCAs, post-mortems, "why did this happen". Not for customer-facing incident write-ups.

How do I install the Five Whys skill?

Claude Code plugin: /plugin marketplace add intercom/2x-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Five Whys popular?

It lives in intercom/2x-skills, which has 280 GitHub stars and 15 forks.

Related skills

Attach Github Assets

280

intercom/2x-skills

Upload local files (screenshots, screen recordings, images, videos) to GitHub as user-attachment assets and return markdown-ready URLs for PR descriptions, issue bodies, or PR/issue comments.

Git & Code Review15

Audit Memory

280

intercom/2x-skills

Audit Claude's saved memories for claims that no longer hold true — verify each against current code, PRs and tickets, then archive the stale ones with your approval, and name the MCPs needed for anything unverifiable.

Productivity & Notes15

Cc Cost Analysis

280

intercom/2x-skills

Analyze Claude Code usage costs from OpenTelemetry data — per-user spend, expensive sessions, context bloat, and model/token cost breakdowns — with a structured framework, ready-to-use query shapes, and cost-model formulas. Triggers on "analyze Claude Code costs", "break down the Claude Code bill", "find expensive sessions", "identify context bloat".

AI, LLMs & Agents15

Permissions Analyzer

280

intercom/2x-skills

Vet a Claude Code permission allowlist against a GREEN/YELLOW/RED safety model and reduce permission prompts. Runs on top of the built-in /fewer-permission-prompts scan (and permission auto mode): filters proposed auto-allow commands through a GREEN/YELLOW/RED safety model — never auto-allowing interpreters or package-manager executors — before merging the safe ones into ~/.claude/settings.json. Also turns the proactive "reduce your prompts" suggestions off or on (disable/enable).

AI, LLMs & Agents15

Skill Review

280

intercom/2x-skills

Review Claude Code skills against substantive quality standards — an 8-category rubric with JSON output, single-pass full-rubric review, and a determinism contract. Complements Anthropic's `plugin-dev:skill-reviewer` (structural checks). Use for: "review a skill", "check skill quality", "does this skill need evals", "review skill quality".

AI, LLMs & Agents15

Sylph Setup Agent

220

getnao/sylph

Set up an AI agent by validating her scope, schedule, and delivery channel. Run as `/sylph-setup-agent <agent-name>` or `/sylph-setup-agent all`.

AI, LLMs & Agents67

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.