---
name: scale-five-whys
description: Runs a Five Whys root-cause analysis on the outcome charter, at least twice from different vantage points, and classifies the root cause as a Skills, Systems, Strategy, or Product gap. Use when the user says "why is this happening", "run five whys", "find the root cause", "why is win rate down", or after scale-outcome-charter completes.
---

# scale-five-whys

Produce `artifacts/scale-five-whys.md` and fill the Root cause section of `artifacts/scale-charter.md`.

## Preflight (every run)
1. Confirm `GTM-AI-OS/` is accessible. If not: "I need access to your GTM-AI-OS folder. Select it in Cowork's folder picker, or run `os-install` from the core plugin." Stop until it is.
2. Read `CLAUDE.md`, `INDEX.md`, and the last 20 lines of `signals/log.md`.
3. Check the prerequisites below. For anything missing, ask the cold-start questions and offer: (a) run the earlier skill now, or (b) fast path: answer the questions and this skill writes a minimal version of the missing artifact marked `status: draft (fast path)`.
4. On finish, update the artifact row in `INDEX.md` and append one line to `signals/log.md`: `<date> | <skill> | <produced> | <human changed> | <open question>`.

## Prerequisites
- `artifacts/scale-charter.md` with an outcome statement.
Cold-start: "State the problem in one sentence with a number, e.g. 'new-business win rate is 11%, needs to be 20%'." Write it to `context/outcome.md` as `status: draft (fast path)` and proceed.

## Step 1: Chain one, the user's view
Start from the outcome gap. Ask "why?" and write the answer. Ask again on that answer. Continue until the answer is both measurable and fixable. Five is a minimum. Push past vague answers ("bad execution") by asking "what would we see in the data if that were true?"

## Step 2: Chain two, a different seat
Ask: "Whose view haven't we taken? A rep, a manager, marketing, CS, RevOps?" Run the chain again from that seat. If the user can, have them message that person and paste the reply. Different roots are common and useful.

## Step 3: Classify each root
For each chain, label the root cause:
- Skills gap: people don't know how, or enablement is missing (AI amplifies)
- Systems gap: tools don't talk, swivel-chair work, data stuck (AI amplifies)
- Strategy gap: wrong market, ICP, pricing, positioning (AI advises; fix the strategy first)
- Product gap: the offer doesn't deliver (AI can't fix; escalate)
State plainly which gaps AI can and cannot help with.

## Step 4: Quantify
For the root you'll pursue: "What is this costing per quarter?" Estimate in dollars or hours converted to dollars. Mark the estimate `Inferred` unless the user gives a sourced number.

## Step 5: Write
Write `artifacts/scale-five-whys.md` with both chains, gap types, the quantified cost, and a one-line recommendation of which chain to pursue into Module 2. Update the charter's Root cause section. Set `context/outcome.md` to `status: verified` if the sponsor has signed.

## Quality gate
Do not stop at a root that is a restatement of the symptom. Do not accept one chain as final.

## Hand off
Say: "Module 2 maps the workflow that contains this root cause. Install `scale-chart / os-know` and say 'map my friction'."