| name | cost-discovery-coach |
| description | Turns the cost-of-inaction calculator's inputs into tight, killer discovery questions per vertical — JTBD job, Never-Split calibrated question, Challenger insight. Use when: discovery questions, how to ask, calculator discovery, cost of inaction questions, SDR call prep, what do I ask, qualify the room count, broadcast/live-events/corporate discovery. |
Teach a new SDR (Edgar, Vasil, Nyasha) to run discovery that fills the cost-of-inaction calculator —
using questions that are short, sayable, and **spec-true**. Each calculator input becomes one killer
question. The rep masters tonality, pace, and inflection; the words are already right. Pairs with
`jobs-to-be-done-skill`, `never-split-the-difference-skill`, `challenger-sale-skill`. Full question
bank: `reference/discovery-by-input.md`.
<quick_start>
Trigger: "discovery questions", "what do I ask", "cost of inaction questions", "SDR call prep".
Do this:
- Identify the vertical + the calculator inputs still missing (rooms, equipment age, failed captures, downtime, tickets, staff).
- Pull the matching questions from
reference/discovery-by-input.md — for each input, pick one of the four layers (Killer Q / Label / Job / Insight) that fits the moment.
- Coach delivery with the Riff rules: one question per breath, mirror, go quiet after the number.
Every spec cited must be verified (Epiphan Knowledge MCP / catalog) — never improvise a spec.
</quick_start>
The principle (read this first)
- Concise & killer. One breath. If it needs a comma to survive, cut it.
- Easy to riff. A frame they can say five ways, not a line they recite.
- Spec-true. Every fact in a question is verified (Epiphan Knowledge MCP / catalog). Reps never
get caught out: Pearl-2 = 6 isolated full-HD channels; Pearl Nexus = 2 recommended (3 max); EC20
publishes straight to your CMS, no encoder in the path; Edge fleet management is free.
- Master the voice, not the script. The skill's job is to make the words bulletproof so the rep's
only job is delivery.
The method: each input is a question
The calculator can't compute until the rep earns these answers. For every input, the bank gives four
layers — pick the one that fits the moment:
| Layer | Source | What it does |
|---|
| Killer Q | Never Split the Difference | a calibrated, no-oriented question — short, opens the room |
| Label | Never Split the Difference | "It sounds like… / It seems like…" — names the pain, gets a "that's right" |
| Job | Jobs To Be Done | the outcome the buyer is really hiring for |
| Insight | Challenger | the reframe that teaches them something about their own cost |
The flow (one call)
- Open with a label, not a pitch ("Sounds like the older rooms are the ones eating your week.").
- Earn the inputs with killer questions — rooms, equipment age, failed captures, downtime,
tickets, staff (and per vertical: events/yr, headcount, time-to-first-frame).
- Teach with the cost-of-inaction number the calculator returns (Challenger reframe).
- Tease the cheaper path — "there may be a more affordable path; not every room records at once"
— a starting point, not a quote. Never name the mechanism.
- Hand off with
ae_handoff once a Manager+ economic buyer is in play.
Riff rules (so it stays natural)
- Drop the number, then go quiet. Let the silence work.
- Mirror their last 1–3 words to keep them talking before the next question.
- One question at a time; never stack two.
- If they're junior (Coordinator/Technician), your real goal is the name of whoever signs — thread up.
Guardrail — internal only
This coaches the rep; it is not buyer copy. In anything the prospect sees, never name the AV-matrix
mechanism (matrix/switchboard/routing switch) or third-party brands — "your CMS / LMS," pooled =
"a more affordable path, a starting point, not a quote." The AE owns fit, pricing, POC.
See epiphan-ai-mcp-guide-skill.
<success_criteria>
