--- name: scale-set description: S.C.A.L.E. step 1, Set. Turns a goal into a Strategic Outcome Charter (number, baseline, date, sponsor, driving KPIs) and runs five whys twice to name the root cause and its gap type. Use when the user says "set my outcome", "step 1", "outcome charter", "what should our AI goal be", "five whys", or after scale-start routes here. --- # scale-set Write `SCALE/1-set-charter.md`. Start with the end in mind. ## 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: The charter 1. (Q) "The goal, the way your CEO said it." Vague is fine. 2. Map it to one challenge area: revenue growth, sales efficiency, retention, margin, expansion. If two, ask which the board asks about first. 3. Rewrite until it passes the four tests: tied to business value, quantifiable, time bound, big enough to matter. Show the rewrite: "By , we will measured by from to ." 4. (Q) "Baseline today?" Offer to pull from the CRM if connected. Mark Inferred if estimated. If they have no number at all, offer the RGA sizing: "Average reps spend about 28% of time on revenue-generating activity; top teams 45 to 50%. Every 1 point of RGA is roughly 0.4% of revenue. On $, moving RGA from to is about $." Use it to get a target on paper, labeled estimate. 5. Headline metric it feeds: Sourced Qualified Pipeline or Retained-and-Expanded Revenue. Neither means it's a project; park it. 6. Key accomplishments: the 2 to 4 things that would prove the goal. Then the driving KPIs behind each (velocity, ACV, win rate, cycle, opportunities, renewal, usage). (Q) Keep three, with current value, target, owner. 7. Deep: key behaviors behind each KPI, then the processes and tasks behind each behavior. This is the cascade; the recurring tasks are candidates for step 2. 8. (Q) Owners: executive sponsor, process owner, end-user champion, data owner. Refuse "TBD" for the sponsor. ## Part B: Five whys, twice 1. (Q) Chain one from the user's seat. "Why?" until the answer is measurable and fixable. Push past "bad execution" with "what would we see in the data?" 2. (Q) Chain two from another seat: a rep, a manager, marketing, RevOps. 3. Classify each root: Skills, Systems, Strategy, Product. AI amplifies the first two; the last two get fixed first. 4. Cost per quarter of the root you'll pursue. Inferred unless sourced. ## Write `1-set-charter.md` from `references/charter-template.md`. Quality gate: no number, no date, no sponsor, or neither metric: don't write, say which test failed. ## Hand off Mark the step done in `progress.md` and set `resume at`. Fast mode: say "Step done. Moving to Chart." and continue to the next step without waiting. In-depth mode: say "Step done. Say **next** when you're ready for Chart."