Deal Coach

This skill reads five coaching reference files at runtime:

• references/frameworks.md — Resonate / Elevate / Compel: Buyer Mindset + Value Props + Talking Points
• references/coaching-agents.md — 3 coaching agent personas + 2 cross-stage + scoring rubrics
• references/stage-mapping.md — Buyer's Journey → coaching stage mapping + inference rules
• references/html-templates.md — HTML section/slide templates per output mode
• references/messaging-narratives.md — How coaching grounds in GTM context

If reference files are not found, fall back to general coaching methodology and note the limitation.

How this differs from /octave:train:

• /octave:train is generic sales training (objection handling, personas, product knowledge)
• /octave:deal-coach is methodology-specific — every output is structured around Resonate/Elevate/Compel, scored against coaching rubrics, and coached by stage-specific agents

How this differs from /octave:meeting-prep:

• /octave:meeting-prep produces a strategic battle plan for an upcoming meeting
• /octave:deal-coach produces training and coaching materials organized around the three coaching stages

Usage

/octave:deal-coach
/octave:deal-coach [company domain or name]
/octave:deal-coach --mode [roleplay|microsite|deck|quiz]
/octave:deal-coach --stage [resonate|elevate|compel]
/octave:deal-coach [domain] --mode roleplay --stage elevate

Examples

/octave:deal-coach
/octave:deal-coach acme.com
/octave:deal-coach --mode roleplay
/octave:deal-coach acme.com --mode microsite --stage compel
/octave:deal-coach --mode quiz --stage resonate
/octave:deal-coach acme.com --mode deck --stage elevate

Instructions

Follow these steps precisely. Do not skip or reorder them.

Step 1: Choose Output Type (CT-1)

If the user specified --mode, use that. Otherwise, ask:

AskUserQuestion({
  questions: [{
    question: "What kind of deal coaching output do you want?",
    header: "Output Mode",
    options: [
      {
        label: "Role Play",
        description: "Practice a coaching-backed conversation scored against Buyer Mindset, Value Props, and Talking Points. 8-12 exchanges, then a scorecard."
      },
      {
        label: "Coaching Microsite",
        description: "Self-contained HTML coaching page organized around Buyer Mindset / Value Propositions / Talking Points — with deal context, priority actions, and stage-grounded messaging."
      },
      {
        label: "Coaching Deck",
        description: "Slide presentation walking through the coaching framework for a specific deal, with stage-specific content and talk tracks."
      },
      {
        label: "Interactive Quiz",
        description: "Test coaching methodology knowledge with deal-grounded scenarios. Scoring breaks down by Resonate/Elevate/Compel."
      }
    ],
    multiSelect: false
  }]
})

Store the selected mode for routing in Step 5.

Step 2: Identify Deal Context (CT-2)

Determine if coaching should be grounded in a specific deal or run in generic/practice mode.

If the user already provided a domain, name, or email, skip to 2b.

2a. Ask for deal context

AskUserQuestion({
  questions: [{
    question: "Should this be grounded in a specific deal, or do you want generic practice?",
    header: "Deal Context",
    options: [
      {
        label: "Specific Deal",
        description: "Ground coaching in a real account — uses CRM data, findings, events, and your playbook to make coaching deal-specific."
      },
      {
        label: "Generic Practice",
        description: "Practice the methodology with library-level data only (personas, playbook, proof points). No specific account context."
      }
    ],
    multiSelect: false
  }]
})

If Generic Practice: Skip to Step 2c.

If Specific Deal: Ask for the company domain or contact email:

AskUserQuestion({
  questions: [{
    question: "What company domain or contact email should I research?",
    header: "Company",
    options: [
      {
        label: "Enter domain",
        description: "e.g., acme.com"
      },
      {
        label: "Enter email",
        description: "e.g., [email protected]"
      }
    ],
    multiSelect: false
  }]
})

2b. Gather deal-specific context

Run these MCP tool calls to build a complete picture. Run independent calls in parallel:

Company & CRM Context (parallel):

enrich_company({ domain: "<domain>" })
find_crm_records({ domain: "<domain>" })
find_crm_activities({ domain: "<domain>" })
generate_crm_context({ domain: "<domain>" })

Library Context (parallel):

search_knowledge_base({ query: "<company name> OR <industry>" })
list_findings({ domain: "<domain>" })
list_events({ domain: "<domain>" })
list_all_entities({ entityType: "persona" })
list_all_entities({ entityType: "competitor" })
list_all_entities({ entityType: "proofPoint" })

Playbook (after knowledge base search returns):

get_playbook({ oId: "<matched_playbook_oId>" })

If any tool call fails, note the gap and continue. Coach with available data and flag missing context.

2c. Generic practice mode context

For generic mode, gather library-level data only:

search_knowledge_base({ query: "playbook" })
list_all_entities({ entityType: "persona" })
list_all_entities({ entityType: "competitor" })
list_all_entities({ entityType: "proofPoint" })

get_playbook({ oId: "<default_playbook_oId>" })

2d. Load coaching reference files

Read the references needed for the inferred or selected stage:

Read: references/frameworks.md
Read: references/stage-mapping.md
Read: references/coaching-agents.md
Read: references/messaging-narratives.md

If generating HTML output (microsite or deck), also read:

Read: references/html-templates.md

Step 3: Infer Coaching Stage + User Override (CT-3)

If the user specified --stage, use that and skip to Step 3b.

3a. Infer stage from signals

Use the weighted inference algorithm from references/stage-mapping.md:

For generic practice mode: Skip inference. Let the user choose:

AskUserQuestion({
  questions: [{
    question: "Which coaching stage do you want to practice?",
    header: "Stage",
    options: [
      {
        label: "Resonate",
        description: "Understand and resonate with the buyer — discovery principles, building trust through understanding"
      },
      {
        label: "Elevate",
        description: "Confirm the fit and elevate the opportunity — disrupt status quo, differentiate on value, build credibility"
      },
      {
        label: "Compel",
        description: "Deliver the value and compel the buyer to action — business case, Why Now, champion enablement"
      }
    ],
    multiSelect: false
  }]
})

3b. Present inference and allow override

Confidence calibration: CRM absence is a data hygiene issue, not a deal health signal. If CRM data is missing but activity signals are strong, redistribute the CRM weight across other signals.

Present the inference:

STAGE INFERENCE
===============
Stage: [Resonate / Elevate / Compel]
Confidence: [High / Medium / Low]
Buyer's Journey Phase: [Phase Name]

EVIDENCE
--------
CRM Stage (40%): "[Stage Name]" → maps to [Stage]  [or "No CRM record — data gap, not deal gap"]
Findings (30%): [Key signals]
Activities (20%): [Key activities]
Time (10%): [Assessment]

Then confirm:

AskUserQuestion({
  questions: [{
    question: "Does this stage assessment look right?",
    header: "Confirm Stage",
    options: [
      {
        label: "Yes — proceed with [Stage]",
        description: "Generate [selected mode] coaching for [Stage]"
      },
      {
        label: "No — let me pick",
        description: "Override the inference and choose a different stage"
      },
      {
        label: "Show all stages",
        description: "See all 3 stages with descriptions before choosing"
      }
    ],
    multiSelect: false
  }]
})

If user picks "No" or "Show all stages," present the full stage list (same as generic mode above).

3c. Stall detection

If time-in-stage signals indicate a stalled deal (>2x expected time), add stall diagnosis:

STALL DETECTION
===============
This deal appears stalled at [Journey Phase].
Time in stage: [X] days (expected: [Y] days)

Root Cause Hypothesis: [Stage] gap
- [Explanation of why this stage gap is likely the root cause]
- [Specific evidence from findings/activities]

Recommendation: Focus coaching on [Root Cause Stage], not the nominal CRM stage.

Route to the root cause stage's coaching agent, not the nominal stage.

Step 4: Route to Coaching Agent (CT-4)

Based on the confirmed stage, activate the appropriate coaching agent from references/coaching-agents.md:

Cross-stage agents (available as supplements):

• Negotiation Strategist — Available when stage is Compel and negotiation dynamics surface
• Objection Handler — Available at any stage when objections surface in findings

Load the agent's persona, coaching criteria, scoring rubric, and grounding instructions from the reference file. Use the grounding map from references/messaging-narratives.md to connect the agent's outputs to the seller's Octave library data.

Step 5: Generate Output (CT-5)

Branch based on the output mode selected in Step 1.

Mode 1: Role Play (RP-1 through RP-4)

RP-1: Setup the Scenario

AskUserQuestion({
  questions: [{
    question: "What kind of role play do you want?",
    header: "Scenario",
    options: [
      {
        label: "Single Stage Practice",
        description: "Practice one stage ([Stage]) in a focused 8-12 exchange conversation"
      },
      {
        label: "Full Journey Simulation",
        description: "Walk through Resonate → Elevate → Compel in sequence, simulating the full buying journey"
      }
    ],
    multiSelect: false
  },
  {
    question: "How difficult should the buyer be?",
    header: "Difficulty",
    options: [
      {
        label: "Friendly",
        description: "Buyer is open and receptive. Good for learning the coaching framework."
      },
      {
        label: "Skeptical",
        description: "Buyer pushes back moderately. Tests methodology under pressure."
      },
      {
        label: "Hostile",
        description: "Buyer is resistant, dismissive, or aggressive. Tests advanced skills and composure."
      }
    ],
    multiSelect: false
  }]
})

If in specific-deal mode, identify the buyer persona from entities gathered in Step 2. If generic, let the user choose from available personas:

AskUserQuestion({
  questions: [{
    question: "Which persona should the buyer represent?",
    header: "Buyer Persona",
    options: [
      // Dynamically populated from list_all_entities({ entityType: "persona" })
      {
        label: "[Persona Name]",
        description: "[Persona title/role — from entity data]"
      }
      // ... up to 4 personas
    ],
    multiSelect: false
  }]
})

RP-2: Load Stage-Specific Intelligence

Load the coaching agent's rubric and grounding map for the selected stage.

For deal-specific mode, map all Octave data to coaching output fields using references/messaging-narratives.md.

For generic mode, use playbook-level data to create a representative scenario.

Prepare buyer behavior rules based on stage:

RP-3: Run the Role Play

Set the scene:

=======================================
DEAL COACHING ROLE PLAY: [Stage]
=======================================

THE SCENE
---------
You are a seller from [company/product] meeting with [Persona Name], [Title] at [Company].
[If deal-specific: Brief deal context from CRM]
[If generic: Practice scenario description]

COACHING STAGE: [Resonate / Elevate / Compel]
[Stage subLabel — e.g., "Understand and resonate with the buyer"]

Your goal is to demonstrate strong execution across:
- Buyer Mindset — accurately read and adapt to the buyer
- Value Propositions — deploy the right props for this stage
- Talking Points — execute the stage's methodology naturally

BUYER PROFILE
- Name: [Persona Name]
- Role: [Title]
- Mindset: [Stage-appropriate psychology]
- Difficulty: [Friendly/Skeptical/Hostile]

RULES
-----
1. This is a CONVERSATION — respond naturally as the seller
2. I will play [Persona Name] with [difficulty]-level resistance
3. The conversation will run 8-12 exchanges
4. You'll be scored on Buyer Mindset, Value Props, and Talking Points
5. I'll signal when the conversation is wrapping up
6. Stay in character — no breaking the fourth wall

Ready? I'll start as [Persona Name]...
=======================================

Then begin as the buyer persona:

• Play the buyer with stage-appropriate behavior (see table above)
• Adjust resistance based on difficulty level
• Drop stage-relevant cues that a well-trained seller should pick up on
• Friendly: give verbal rewards when the seller executes methodology correctly
• Skeptical: push back on weak points but yield to strong methodology
• Hostile: resist aggressively; only yield to excellent execution
• Allow natural conversation flow — don't force every principle or beat
• After 8-12 exchanges, signal wrap-up: "I think we're running short on time..."

For Full Journey Simulation:

• Start at Resonate and progress through each stage
• After each stage, pause: "Good — let's fast-forward. [Context for next stage]."
• Score each stage independently, then provide a cumulative scorecard

RP-4: Coaching Scorecard

After the role play ends:

DEAL COACHING SCORECARD
=======================
Stage: [Resonate / Elevate / Compel]
Coaching Agent: [Agent Name]
Difficulty: [Friendly/Skeptical/Hostile]
Persona: [Buyer Name], [Title]

BUYER MINDSET
-------------
| Criterion | Score | Notes |
|-----------|-------|-------|
| Awareness read | [1-5] | [Did they correctly assess where the buyer is?] |
| Adaptation | [1-5] | [Did they adjust their approach based on buyer signals?] |
| Psychology match | [1-5] | [Did they match the buyer's emotional state before trying to move it?] |

Buyer Mindset Score: [avg]/5

VALUE PROPOSITIONS
------------------
| Criterion | Score | Notes |
|-----------|-------|-------|
| Stage appropriateness | [1-5] | [Did they use props fitting for this stage?] |
| Selection quality | [1-5] | [Did they pick the most impactful props available?] |
| Deployment timing | [1-5] | [Did they introduce props at the right moment?] |

Value Propositions Score: [avg]/5

TALKING POINTS
--------------
[Scoring varies by stage — use the stage-specific criteria from coaching-agents.md]

[Resonate:]
| Criterion | Score | Notes |
|-----------|-------|-------|
| Going wide | [1-5] | [Did they map the landscape — stakeholders, history, context?] |
| Going deep | [1-5] | [Did they find root causes, not just symptoms?] |
| Going high | [1-5] | [Did they connect to business and personal impact?] |
| Problem statement quality | [1-5] | [Did they arrive at a crisp, multi-dimensional problem?] |

[Elevate:]
| Criterion | Score | Notes |
|-----------|-------|-------|
| Case for Change delivery | [1-5] | [Did they hit the three beats — Shift, Stakes, Possibility?] |
| Value Framing | [1-5] | [Did they translate to Buyer/Executive voice, not just Product voice?] |
| Differentiation quality | [1-5] | [Did they focus on differentiated value?] |
| Proof point usage | [1-5] | [Did they use specific, credible proof?] |

[Compel:]
| Criterion | Score | Notes |
|-----------|-------|-------|
| Business case quality | [1-5] | [Did they co-create quantified value?] |
| Value chain clarity | [1-5] | [Did they map capability → outcome → dollars?] |
| Why Now execution | [1-5] | [Both dimensions — business and personal urgency?] |
| Champion enablement | [1-5] | [Did they arm the champion?] |

Talking Points Score: [avg]/5

GENERAL SELLING SKILLS
----------------------
| Element | Score | Notes |
|---------|-------|-------|
| Opening / rapport | [1-5] | [Assessment] |
| Active listening | [1-5] | [Assessment] |
| Proof point usage | [1-5] | [Assessment] |
| Call control | [1-5] | [Assessment] |
| Natural delivery | [1-5] | [Assessment] |

OVERALL SCORE: [X]/5
Buyer Mindset: [avg]/5 | Value Props: [avg]/5 | Talking Points: [avg]/5 | General: [avg]/5

KEY MOMENTS
-----------
[Quote from conversation + assessment — what was done well or could improve]
[Repeat for 3-5 key moments]

COACH SAYS
----------
[2-3 paragraphs of specific coaching advice from the stage's coaching agent persona.
Reference specific Talking Points from frameworks.md.
Ground in the seller's playbook messaging.
Identify #1 area for improvement and give a concrete example of what to say instead.]

VALUE PROPS YOU COULD HAVE USED
-------------------------------
[List 3-5 value props from the library that would have strengthened the conversation, with:
- The prop itself
- When to deploy it (which moment in the conversation)
- How to frame it for this stage (Buyer/Executive voice, not feature pitch)]

After the scorecard:

Want to:
1. Run this role play again (same stage, same difficulty)
2. Try a harder difficulty level
3. Practice the next stage ([Next Stage])
4. Practice objection handling for this stage
5. Get a coaching microsite for this stage
6. Switch to a different output mode
7. Done

Mode 2: Coaching Microsite (MS-1 through MS-3)

MS-1: Style Selection

Reference the style preset system from skills/deck/references/STYLE_PRESETS.md.

Each coaching stage has a default style preset:

Present the default with option to override:

AskUserQuestion({
  questions: [{
    question: "The default style for [Stage] is [preset name] ([rationale]). Want to use it or pick a different style?",
    header: "Style",
    options: [
      {
        label: "[Default Preset] (Recommended)",
        description: "[Preset description]"
      },
      {
        label: "Pick a different style",
        description: "Choose from available presets"
      },
      {
        label: "Auto-pick from brand",
        description: "Extract colors from the company's website and generate a custom theme"
      }
    ],
    multiSelect: false
  }]
})

If user picks "Pick a different style," present mood-based preview options (follow the pattern from deck/SKILL.md Step 4).

MS-2: Generate Content Outline

Before generating HTML, present the content plan:

COACHING MICROSITE OUTLINE
==========================
Company: [Company Name]
Stage: [Resonate / Elevate / Compel] — [Stage subLabel]
Coaching Agent: [Agent Name]
Style: [Preset Name]

STRUCTURE
---------
Header + Deal Brief    — Company name, industry, date, coaching stage badge,
                         deal-specific subtitle, deal stats grid
Priority Actions       — 3 quick-hit actions before the next meeting (collapsible)
Deal Activity          — Compact vertical timeline of deal events with dates (collapsible)
Journey Map            — 3-phase coaching journey (Resonate → Elevate → Compel) showing
                         where the deal is and why, with generic phase explanations AND
                         deal-specific context for each phase (collapsible)
Section 01: Stage Assessment     — How stage was inferred, evidence, confidence
Section 02: Buyer Mindset        — Buyer psychology assessment, awareness level, trigger,
                                   constraints, adaptation guidance
Section 03: Value Propositions   — Stage-appropriate props from library with deployment
                                   guidance, evidence inline, usage notes (deploy now vs.
                                   save for later stage vs. already shared)
Section 04: Talking Points       — Stage-specific talk tracks organized by conversation
                                   flow, with strategic point + sample quote + evidence.
                                   Do NOT use framework labels as headers (e.g., "The Shift").
                                   Use practical, deal-specific language.
Section 05: Objection Handling   — Likely objections grounded in buyer's actual decision
                                   frame, with stage-appropriate responses
Section 06: Next Stage Preview   — Transition checklist + next coaching agent preview
[Optional] Section 07: Deal Gaps (MEDDPICC) — Coverage assessment with gap-to-action mapping
The Play               — Strategic one-liner + concrete "your next move is X" action

DESIGN PRINCIPLES
-----------------
- The three coaching outputs (Buyer Mindset, Value Props, Talking Points) are the
  organizing principle
- Evidence (proof points, metrics) is folded INTO the relevant sections inline,
  not in a standalone section
- Objections go in Section 05, grounded in the buyer's actual decision frame
  (build vs. buy, do-nothing vs. act, this vendor vs. that)
- MEDDPICC is available as an optional section — not the primary structure
- Talk tracks use a two-layer structure: strategic point (bold, practical deal
  language — NOT framework labels) then sample quote (italic, one way to express it).
  Each includes "Use when..." guidance for timing.
- No duplicate content between sections. Each piece of information appears once.
- Use "perspective-shifting question" framing — tone is collaborative and consultative
- This is a selling tool. Orient language around advancing the deal.

OCTAVE SOURCES
--------------
- Playbook: [Playbook Name]
- Personas: [N] loaded
- Proof Points: [N] loaded
- Findings: [N] loaded
- Competitors: [N] loaded
- CRM: [Stage, Amount, Close Date or "Generic mode — no CRM data"]

Generate this microsite?
1. Yes — generate
2. Adjust sections
3. Change style
4. Start over

MS-3: Generate HTML

Use templates from references/html-templates.md to generate a self-contained HTML file.

Content grounding rules (from references/messaging-narratives.md):

• Every Value Proposition must reference specific playbook messaging — never generic claims
• Every proof point must cite a specific library entity, appear inline in the section it supports, and include a usage note (deploy now / save for later / already shared)
• Every Talking Point must be grounded in the deal context (if available) and connected to the Buyer Mindset
• Every objection response must be grounded in the specific decision the buyer is making — not generic competitive objections
• Use "perspective-shifting question" framing — collaborative, not adversarial
• This is a selling tool — orient language around advancing the deal

Structural rules:

• Header + Deal Brief is NOT collapsible — full-width gradient hero with deal stats
• Priority Actions, Deal Activity, and Journey Map are collapsible <details> with +/− toggle
• Sections 01-06 (07 if MEDDPICC included) are collapsible <details> elements
• ALL collapsible sections start COLLAPSED by default (no open attribute)
• The Play is NOT collapsible — full-width gradient footer
• No duplicate content between sections
• Evidence goes inline (not standalone)
• Do NOT use framework labels as visible headers in Talking Points (e.g., "The Shift", "The Stakes"). Use practical deal-specific language. The framework informs content structure internally.
• Do NOT include both "Elevate" and "Evaluate" badges in the header — use "Coaching Stage: [Name]" only. The Journey Map section explains the buyer journey mapping.

Content density limits:

Output location:

.octave-deal-coach/
  [company-kebab]-[stage]-[YYYY-MM-DD]/
    [company-kebab]-[stage].html

Example:
.octave-deal-coach/acme-corp-elevate-2026-03-03/acme-corp-elevate.html

For generic mode, use practice instead of company name:

.octave-deal-coach/practice-resonate-2026-03-03/practice-resonate.html

After writing the file, open it:

open "[file path]"

Mode 3: Coaching Deck (DK-1 through DK-3)

DK-1: Style Selection

Same as MS-1. Use stage-appropriate default presets.

DK-2: Generate Slide Outline

Present the slide outline for approval. Slide content varies by stage:

Resonate (~7 slides):

1. Title Slide — "[Company] — Resonate" + stage badge
2. Stage Context — Deal position, buyer's journey phase, buyer mindset assessment
3. Buyer Mindset Deep Dive — Awareness level, trigger, constraints, adaptation guidance
4. Discovery Principles — Go wide, go deep, go high — applied to this deal
5. Value Propositions — Stage-appropriate props with deployment guidance
6. Talking Points — Discovery questions and conversation starters with listening cues
7. Next Steps — Transition checklist to Elevate

Elevate (~9 slides):

1. Title Slide — "[Company] — Elevate" + stage badge
2. Stage Context — Deal position, competitive landscape, buyer mindset
3. Buyer Mindset Deep Dive — Status quo attachment, change readiness, evaluation mode
4. The Case for Change — The Shift → The Stakes → The Possibility for this deal
5. Differentiated Value — What's unique AND important to this buyer
6. Value Propositions — Value Framing examples (Product → Buyer → Executive voice)
7. Talking Points — Case for Change talk tracks + differentiation delivery
8. Proof Points — Evidence grid with deployment guidance
9. Next Steps — Transition checklist to Compel

Compel (~9 slides):

1. Title Slide — "[Company] — Compel" + stage badge
2. Stage Context — Decision dynamics, stakeholder positions, buyer mindset
3. Buyer Mindset Deep Dive — Decision process, champion strength, detractors, risk appetite
4. Before vs. After — Side-by-side with quantified delta
5. Value Chain — Capability → workflow improvement → business outcome → financial result
6. Value Propositions — ROI-focused props with quantified outcomes per stakeholder
7. The Why Now Case — Business urgency + personal urgency
8. Talking Points — Business case narration + champion enablement scripts
9. Next Steps — Decision pathway and timeline

Present outline and ask:

Generate this deck?
1. Yes — generate
2. Adjust slides
3. Change style
4. Start over

DK-3: Generate HTML Deck

Use slide templates from references/html-templates.md for a self-contained HTML file with scroll-snap slide architecture.

Viewport fitting rules (from deck/SKILL.md):

• ALL font sizes use clamp() — never fixed px
• ALL spacing uses clamp()
• Strict content per slide: Title = 1 heading + 1 subtitle; Content = 1 heading + 4-6 bullets; Grid = max 6 cards
• If content exceeds limits, split into additional slides
• overflow: hidden on every .slide
• Media queries at 700px, 600px, 500px for short viewports

Animation:

• Staggered entrance via Intersection Observer
• .animate-in class with opacity + translateY
• nth-child stagger delays
• Respect prefers-reduced-motion

Navigation:

• Keyboard: ArrowDown/Up, Space, PageDown/Up
• Scroll snap for touch/trackpad
• Progress bar + nav dots
• Print: page-break-after: always, remove snap

Output location:

.octave-deal-coach/
  [company-kebab]-deck-[stage]-[YYYY-MM-DD]/
    [company-kebab]-deck-[stage].html

After writing, open in browser:

open "[file path]"

Mode 4: Interactive Quiz (QZ-1 through QZ-4)

QZ-1: Choose Quiz Type

AskUserQuestion({
  questions: [{
    question: "What type of coaching quiz do you want?",
    header: "Quiz Type",
    options: [
      {
        label: "Stage Recognition",
        description: "A buyer says X — which coaching stage? Tests your ability to diagnose where a deal is."
      },
      {
        label: "Methodology Application",
        description: "You're in [Stage] — what's the right Buyer Mindset, Value Props, and Talking Points approach? Tests methodology knowledge."
      },
      {
        label: "Talk Track Completion",
        description: "Buyer says [objection/question]. Using the coaching methodology, what's your response?"
      },
      {
        label: "Full Review",
        description: "Mix of all categories covering Resonate, Elevate, and Compel. Comprehensive assessment."
      }
    ],
    multiSelect: false
  },
  {
    question: "How many questions?",
    header: "Length",
    options: [
      {
        label: "Quick (5 questions)",
        description: "Fast check — 5-10 minutes"
      },
      {
        label: "Standard (10 questions)",
        description: "Thorough assessment — 15-20 minutes"
      },
      {
        label: "Deep (15 questions)",
        description: "Comprehensive review — 25-30 minutes"
      }
    ],
    multiSelect: false
  }]
})

QZ-2: Load Quiz Material

Load coaching content from reference files. If deal-specific, ground questions in actual deal data. If generic, use playbook-level data.

Build question bank by category:

Stage Recognition:

• Present a buyer quote or scenario → ask which stage
• Use findings and CRM data for realistic scenarios
• Include red herrings (scenarios that seem like one stage but are actually another)

Methodology Application:

• Name a stage → ask for the right approach
• E.g., "You're in Elevate. What are the three beats of the Case for Change?"
• E.g., "A buyer says they're evaluating competitors. Which coaching output fields should you focus on, and what goes in each?"
• Include application questions that test Buyer Mindset → Value Props → Talking Points mapping

Talk Track Completion:

• Present a buyer statement → ask for the methodology-backed response
• E.g., "Buyer: 'We're happy with what we have.' Using the Elevate methodology, what do you say next?"
• Score on methodology adherence AND natural delivery

Full Review:

• Mix all categories
• Weight toward the selected/inferred stage
• Ensure coverage across all three stages

QZ-3: Run the Quiz

Present questions one at a time:

QUESTION [N]/[Total]
Category: [Stage Recognition / Methodology Application / Talk Track Completion]
Stage: [Resonate / Elevate / Compel]
[If deal-grounded: "Based on your [Company] deal"]

[Question text]

[For multiple choice: Present 4 options]
[For open-ended: Ask the user to type their response]

After each answer:

[Correct / Partially Correct / Incorrect]

[Brief explanation referencing specific coaching elements]
[If deal-grounded: How this applies to their specific deal]

Score so far: [X]/[N]

QZ-4: Quiz Results

COACHING QUIZ RESULTS
=====================
Score: [X]/[Total] ([Percentage]%)
Category: [Quiz Type]
Grounding: [Deal-specific: Company Name / Generic Practice]

BREAKDOWN BY COACHING STAGE
----------------------------
| Stage | Questions | Correct | Score | Assessment |
|-------|-----------|---------|-------|------------|
| Resonate | [N] | [N] | [X]% | [Strong/Adequate/Needs Work] |
| Elevate  | [N] | [N] | [X]% | [Strong/Adequate/Needs Work] |
| Compel   | [N] | [N] | [X]% | [Strong/Adequate/Needs Work] |

BREAKDOWN BY COACHING DIMENSION
---------------------------------
| Dimension | Questions | Correct | Score |
|-----------|-----------|---------|-------|
| Buyer Mindset | [N] | [N] | [X]% |
| Value Propositions | [N] | [N] | [X]% |
| Talking Points | [N] | [N] | [X]% |

BREAKDOWN BY CATEGORY
----------------------
| Category | Questions | Correct | Score |
|----------|-----------|---------|-------|
| Stage Recognition | [N] | [N] | [X]% |
| Methodology Application | [N] | [N] | [X]% |
| Talk Track Completion | [N] | [N] | [X]% |

STRENGTHS
---------
[2-3 areas of strong knowledge with specific examples]

GAPS TO FOCUS ON
----------------
[2-3 areas needing improvement with specific coaching references]

[For each gap:]
- Recommended: Practice [Stage] role play with [difficulty]
- Study: Review [specific section] of frameworks.md
- Exercise: Try building a [Buyer Mindset / Value Props / Talking Points] for a real deal

RECOMMENDED NEXT STEPS
----------------------
1. [Primary recommendation]
2. [Secondary recommendation]
3. [Optional stretch recommendation]

After results:

Want to:
1. Retake this quiz
2. Take a quiz focused on your weakest area ([Stage])
3. Practice a role play for your weakest area
4. Get a coaching microsite for your weakest area
5. Try a different output mode
6. Done

Step 6: Delivery + Next Actions (CT-6)

After delivering any output, offer iterations:

For Role Play and Quiz: Next actions are included in RP-4 and QZ-4 above.

For Microsite and Deck: After opening the HTML file, present:

Coaching [microsite/deck] generated and opened in your browser.

File: [file path]
Company: [Company Name or "Generic Practice"]
Stage: [Resonate / Elevate / Compel] — [Stage subLabel]
Coaching Agent: [Agent Name]
Style: [Preset Name]

Want to:
1. Practice this stage with a role play
2. Add MEDDPICC deal gap analysis [if not already included]
3. Move to the next stage ([Next Stage]: [subLabel])
4. Try a different output mode for this stage
5. Regenerate with a different style
6. Done

If the user picks option 3 (next stage), return to Step 3b with the next stage pre-selected and flow through Steps 4-5 again.

Output Directory

All HTML outputs go to .octave-deal-coach/ in the project root:

.octave-deal-coach/
  [company-kebab]-[stage]-[YYYY-MM-DD]/
    [company-kebab]-[stage].html            # Microsite
  [company-kebab]-deck-[stage]-[YYYY-MM-DD]/
    [company-kebab]-deck-[stage].html       # Deck

This directory should be in .gitignore.

MCP Tools Used

Research & Enrichment

Library — Fetching

Library — Searching

Content Generation

Error Handling

No CRM data found: "I couldn't find CRM records for [domain]. I'll proceed with library-level data only. Stage inference will rely on findings and events. You can also manually select a stage."

No playbook found: "No matching playbook found. I'll use general coaching methodology without playbook-specific grounding. Talk tracks will reference the framework but won't include your specific messaging. Consider running /octave:library to check your playbook setup."

No findings/events: "No conversation findings or events found for [domain]. Stage inference will rely primarily on CRM stage. For more accurate coaching, ensure conversation data is synced to Octave."

Reference file not found: "Could not load [reference file]. Falling back to general coaching methodology. For full coaching, ensure reference files are in skills/deal-coach/references/."

Stage inference low confidence: "I'm not confident about the coaching stage — multiple stages scored similarly. I'd recommend selecting manually. Here are all options: [present all three stages]."

MCP connection failed: "Could not connect to Octave. Check your connection with /octave:workspace. Deal coaching requires Octave MCP tools for deal context and library data."

HTML write failed: "Could not write the HTML file. Check that .octave-deal-coach/ is writable. Try: mkdir -p .octave-deal-coach"

Related Skills

• /octave:train — Generic sales training (role play, quiz, guided learning) without deal coaching methodology
• /octave:meeting-prep — Strategic meeting battle plan as HTML
• /octave:deck — General-purpose slide deck builder
• /octave:pipeline — Deal coaching and pipeline management
• /octave:enablement — Sales enablement materials (cheat sheets, objection guides)
• /octave:battlecard — Competitive intelligence and battlecards
• /octave:research — Account and person research