# Roleplay Scenario Generator > Turn any deal, framework, or objection into a live AI roleplay partner a rep can practice against before the real call. Builds the buyer persona, the scenario, the objections they will actually hit, and a scorecard that grades the rep against the framework, so the first real attempt is not the first attempt. Built for sales managers, enablement, and reps, works from a framework or a real deal. Trigger on "build a roleplay", "practice this call", "roleplay partner", "let me rehearse the objection", "certify this rep", "mock discovery call", "practice the demo", "roleplay the renewal", "train the reach-up", or any request to rehearse a sales conversation before it happens. - Skill: `heath-gtm/roleplay-scenario-generator` (Agent Skill) - Install (CLI): `npx skillmds@latest add heath-gtm/roleplay-scenario-generator` - Raw SKILL.md: https://api.skillmd.com/api/skills/heath-gtm/roleplay-scenario-generator/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Product & Planning - Author: heath-gtm (https://skillmd.com/u/heath-gtm) - Updated: 2026-09-08 - Page: https://skillmd.com/skills/heath-gtm/roleplay-scenario-generator --- # Roleplay Scenario Generator ## What this does Takes a conversation a rep is about to have, discovery, demo, an objection, a renewal, a reach-up to the economic buyer, and turns it into a live roleplay they can practice against. It builds the buyer persona with a real concern, runs the scenario in character, throws the objections that seat actually throws, and then grades the rep against the framework with a specific, coachable score. It turns "read the deck and wing it" into reps you can measure, so the first live attempt is not the first attempt. ## What you'll need You do not need to connect anything to get value today. Name the scenario and the framework and the roleplay runs now. Connect the tools below and it grounds the persona and the objections in your real deals and calls. - Works today with: the motion (discovery, demo, objection, renewal, reach-up), the framework you run, and who the rep is selling to. Describe it and the roleplay starts. - More powerful connected to a CRM: it builds the persona from a real open deal, the stakeholders, the stage, the stated problem, and the notes and activity your reps actually logged, so the buyer is this account, not a generic one. - Sharper with a call tool: it pulls the objections your buyers actually raise, so reps rehearse the real ones, not generic ones. - Sharper with email and conversation history: the real back-and-forth with the account, so the buyer in the roleplay sounds like the one in the thread, tone and all. - Sharper with product analytics: how the account actually uses you, so the value story and the objections are grounded in real usage instead of guesses. - Sharper with a docs or LMS tool: it saves the scenario and the scorecard as a reusable module, so a good roleplay becomes a certification other reps can take. ## How this runs at your connection level This skill is never reliant on a connector. It runs on the scenario you give it today and gets sharper as you connect your deals and calls. It never invents a buyer detail it cannot see. A gap is a prompt, not a guess. - **Bring your data**: describe the call and the framework. The skill builds the persona, runs the roleplay, and scores the rep today. No connection required. - **Connect your tools**: the same skill pulls the real deal, the real stakeholders, and the objections your buyers actually raise. Same roleplay, grounded in the record. - **Just exploring**: no deal yet? Get a worked scenario on a sample deal, so you can see the persona, the objections, and the scorecard before you point it at a real one. Every run ends with the one thing that would sharpen the next rep: an objection to add, a stakeholder to bring in, or a tool to connect. ## Customize this for yourself This was built for a B2B SaaS team running a named methodology. Set these to your motion: | Set this | What it is | Default / Example | |---|---|---| | MOTION | the conversation being practiced | discovery, demo, objection, renewal, reach-up | | FRAMEWORK | what the rep is graded against | SPRINT discovery, CLEAN demo, LEARN objections, PLAN, VALUE | | PERSONA | who the buyer is | the seat, their concern, their pressure | | DIFFICULTY | how hard the buyer pushes | warm, neutral, skeptical, hostile | | CERT_BAR | the score a rep must clear to go live | a passing scorecard on the framework | | CRM | your CRM connector | Salesforce, HubSpot, Pipedrive | | CALL_TOOL | where real objections live | Gong, Chorus, Fireflies | ## The method ### Build the buyer, not a cardboard cutout A useful roleplay starts with a real persona: the seat, the concern that seat actually carries, and the pressure they are under. A CFO stalls on a different thing than a champion does. The buyer has a point of view and defends it, so the rep has to earn the room. ### Run the scenario in character The skill plays the buyer and stays in character through the call. It does not hand the rep the answer. It pushes where a real buyer pushes, goes quiet where a real buyer goes quiet, and raises the objection at the moment it actually lands. ### Throw the objections they will really hit Objections are drawn from the motion and, when connected, from your real calls: price, low usage, "we already have this", a champion who left, no compelling event. The rep practices the turn (LEARN: listen, empathize, anchor, respond, next step) against the ones that actually show up. ### Score against the framework When the roleplay ends, the rep gets a scorecard tied to the framework, not a vibe. Each element scored, the specific moment it was won or missed, and the one thing to fix before the live call. A cert bar makes it a pass or a not-yet, so "ready" is a decision, not a hope. ### Save it as a reusable module A good scenario is worth running more than once. Saved, it becomes a certification other reps take, so enablement is a library that compounds, not a one-off session that evaporates. ## Quality gates - The buyer stays in character and never coaches the rep mid-scene. The lesson is in the score, not the scene. - Objections are real to the motion, and grounded in actual calls when a call tool is connected, never generic filler. - The score is tied to the framework element by element, with the specific moment cited, not a single number. - The cert bar is an explicit pass or not-yet, so readiness is decided, not assumed. - No buyer detail is invented past what you gave or what a connected record shows. A gap is named. ## Example chat You do not just say "run it." You give it the real call, then you actually roleplay. Here is a full one. **You:** I have a discovery call tomorrow with the VP of Ops at a mid-market logistics company. They churned off a competitor last year after a painful rollout, so they are gun-shy about switching. Play them, skeptical, and grade me on SPRINT. **Buyer, VP Ops:** I have got fifteen minutes. We tried a tool like yours last year and it blew up three weeks in. My team still has not forgiven me. So tell me why this is not the same mistake. **You:** Fair, and I am not here to sell you a migration. What actually broke last time, the setup, the adoption, or the support after go-live? **Buyer, VP Ops:** Honestly all three. But mostly nobody used it, so we paid for a year and got nothing. **You:** That is the part I would want to fix first. If we could not get your team using it in the first month, I would rather not sell it to you. What would "people are actually using it" look like for you? **Buyer, VP Ops:** ...okay, that is a better question than the last three vendors asked me. **Coach, SPRINT 23/30, READY (cert bar 22):** Situation 4/5 good context, did not confirm their current workaround Problem 5/5 got the real problem in their words: adoption, not features Risk 5/5 named the churn fear and disarmed it Impact 4/5 tied it to a year of wasted spend Next steps 2/5 earned trust, never locked a dated next step Timeline 3/5 asked about the first month, did not anchor a date Fix before the live call: you earned the room, now land a dated mutual next step. That 2/5 is the only thing between this and a 27. ## Where the inputs come from The persona, the difficulty, and the cert bar are yours to set. The objections are drawn from the motion and from your connected calls when available. The score is computed against the framework you name, element by element. Nothing about the buyer is invented past what you provide or what a connected record shows. ## Go further This runs today as a text roleplay. Here is where an operator takes it next, and none of it is science fiction. - **Voice-to-voice reps.** Wire the scenario to an ElevenLabs voice agent so the rep practices out loud, against a buyer that interrupts, stalls, and pushes back in real time. The scorecard still grades the framework; the rep just rehearses with their voice, not their keyboard. - **A roleplay that builds itself from last week's calls.** A small tool, vibecoded in a day in Lovable and shipped on Vercel, pulls every rep's recorded calls from Gong, finds the objections and the moments they lost, and generates next month's roleplay slate automatically, each scenario tuned to the exact gap that rep keeps hitting. - **A coach that assigns the work.** Turn that into a monthly plan per rep: the tool reads the calls, writes the plan, and hands each rep an ElevenLabs agent loaded with their accounts and their weak spots, so practice is personal and on the calendar, not a generic SKO. The skill is the seed. The build is yours. ## Make it yours Fork it. Change the framework, the difficulty curve, the cert bar, the personas your team actually sells to. The point is not to run someone else's mock call. It is to make sure the rep's first real attempt is not their first attempt. Built by an operator. Customize it, break it, make it better.