# Cost Discovery Coach

> 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.

- Skill: `scientiacapital/cost-discovery-coach` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds add scientiacapital/cost-discovery-coach`
- Raw SKILL.md: https://api.skillmd.com/api/skills/scientiacapital/cost-discovery-coach/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: scientiacapital (https://skillmd.com/u/scientiacapital)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/scientiacapital/cost-discovery-coach

---


<objective>
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`.
</objective>

<quick_start>
**Trigger:** "discovery questions", "what do I ask", "cost of inaction questions", "SDR call prep".
**Do this:**
1. Identify the vertical + the calculator inputs still missing (rooms, equipment age, failed captures, downtime, tickets, staff).
2. 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.
3. 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)
1. **Open** with a label, not a pitch ("Sounds like the older rooms are the ones eating your week.").
2. **Earn the inputs** with killer questions — rooms, equipment age, failed captures, downtime,
   tickets, staff (and per vertical: events/yr, headcount, time-to-first-frame).
3. **Teach** with the cost-of-inaction number the calculator returns (Challenger reframe).
4. **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.
5. **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>
- [ ] Every calculator input the rep needs is covered by exactly one killer question (plus a Label / Job / Insight fallback layer)
- [ ] Questions are one breath long, sayable five ways, and spec-true (all facts verified — Pearl-2 = 6 channels, Nexus = 2 rec/3 max, EC20 direct-to-CMS, Edge free)
- [ ] The flow ends with a Challenger reframe on the cost-of-inaction number and, when a Manager+ EB is in play, an `ae_handoff`
- [ ] No buyer-facing copy names the AV-matrix mechanism or third-party brands; pooled = "a more affordable path, a starting point, not a quote"
- [ ] Junior contact? The coached goal shifts to threading up to whoever signs
</success_criteria>