---
name: scale-chart
description: S.C.A.L.E. step 2, Chart. Maps one revenue workflow, scores friction on People, Process, Technology, Data, prices the top stall in dollars, ranks the opportunities, and checks the data. Use when the user says "chart my friction", "step 2", "map my workflow", "where does work get stuck", "rank the friction", "data inventory", or after step 1.
---

# scale-chart

Write `SCALE/2-chart-friction.md`. You can't automate a broken process. Map it first.
## Preflight (every run)
1. Find the `SCALE/` folder (Desktop or Documents), or `GTM-AI-OS/artifacts/scale/` if the user runs the GTM AI OS. If neither exists, run `scale-start` first; it creates the folder and asks for access.
2. Read `SCALE/progress.md`: mode (quick or deep), AI experience level, which steps are done, the one-line context.
3. Talk short and direct. Say what each answer is for. Beginner: one question at a time, plain words. Advanced: batch questions, skip explanations.
4. Quick mode: ask only the questions marked (Q). Deep mode: ask all. Accept "skip" and "don't know"; record them as gaps.
5. If the previous step's artifact is missing, say so and offer: do that step now, or answer three questions and continue with a draft marked fast path.
6. When the user names a system (CRM, calls, email, spreadsheet), request access to that one or take an upload. Never assume a product.
7. On finish: write the artifact, update `progress.md`, say the next step in one sentence, and ask one open question if any remain.


## Part A: Map one workflow
1. (Q) "Which workflow holds the root cause from step 1? One." Others go on a list at the bottom.
2. (Q) Walk it: who, what activity, which system, what information flows in and where it lands. Then where it stalls, and whether the stall is human (decision, repetition, process, cognitive load) or data (missing, late, wrong, trapped).
3. Score each stall 1 to 5 on People, Process, Technology, Data. Count handoffs.
4. (Q) Price the top stall: "How often, how long, who?" Hours per month, dollars at loaded cost, revenue exposure if it blocks deals. Inferred until sourced.
5. Red flags: hand-updated CRM, conflicting records, reporting delays, more than five tools in one workflow.

## Part B: Rank
Impact 1 to 10 (dollars) and feasibility 1 to 10 (data exists, system reachable, owner willing, no legal block). Plan (do first), Quick win, Reconsider, Skip. The top Plan item must connect to the step 1 root; if not, say which is wrong.

## Part C: Data check
1. (Q) For each system the workflow touches: what it holds, who owns it, reachable or not.
2. Deep: which fields are entered by hand (about 5% still need a human), quality on complete / accurate / accessible / timely.
3. Blockers: no owner, no export, conflicting records, regulated data with no policy.

## Write
`2-chart-friction.md` from `references/friction-template.md`. Quality gate: fewer than four steps or no stall with a number: not done.

## Hand off
Mark the step done in `progress.md` and set `resume at`. Fast mode: say "Step done. Moving to Align." and continue to the next step without waiting. In-depth mode: say "Step done. Say **next** when you're ready for Align."