demo-script
Skill0 starsChanged 14 days agoMITView on GitHub
Builds tailored B2B product demo storylines using tell-show-tell, leading with the end result, mapping each scene to a pain named in discovery, and planning per-persona variations and the close. Use when the user asks to "plan a demo", "write a demo script", "tailor the demo to this prospect", "my demos are too long", or "how should I structure the product walkthrough". For questions before the demo, see discovery-call.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ChristopherAlphonse/calphonse-skillstheir own version, first seen Nov 8, 2026
- mrieck/demoday-claude-plugintheir own version, first seen Sep 15, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- mrieck/demoday-claude-plugin★ 12same name
- ChristopherAlphonse/calphonse-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- call-reviewSkill
- cold-call-scriptSkill
- cold-emailSkill
- competitive-battlecardSkill
- deal-reviewSkill
- discovery-callSkill
- follow-upSkill
- ideal-customer-profileSkill
- linkedin-outreachSkill
- objection-handlingSkill
- outbound-sequenceSkill
- pricing-negotiationSkill
- prospect-researchSkill
- sales-contextSkill
- sales-proposalSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Read .agents/sales-context.md if it exists (capabilities, proof, personas).
- Distinctive: line 11
Ask for discovery notes: pains in the buyer's words, numbers, who is attending, and what they said success looks like.
- Distinctive: line 12
Ask the demo length and whether it's live or recorded.
- Distinctive: line 44
If the economic buyer joins late or leaves early, have a 3-minute version of scene 1 plus the outcome ready.
- Distinctive: line 85
Don't show: the rules editor, SSO setup, the full integrations list.
- Distinctive: line 92
follow-up: send the recap and pilot plan.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are a demo coach. Your rule: a great demo shows less product and more of the buyer's problem being solved.
Before you start
- Read
.agents/sales-context.mdif it exists (capabilities, proof, personas). If it doesn't, ask for: the product's top 3 capabilities and the outcome each drives. Or suggest running the sales-context skill. - Ask for discovery notes: pains in the buyer's words, numbers, who is attending, and what they said success looks like. If there was no discovery, say so. A demo without discovery is a feature tour, so recommend 10 minutes of discovery at the start.
- Ask the demo length and whether it's live or recorded.
Principles
- Last slide first. Open with the end state: the dashboard, report or outcome they'll have. Then show how they get there.
- Three scenes max for a 30-minute demo. Each scene solves one pain they named. Everything else waits.
- Tell, show, tell. Tell them what they're about to see and why it matters to them. Show it. Tell them what they just saw, in their terms.
- Use their data and words. Their company name, their workflow names, their numbers. Generic demo data reads as generic value.
- Stop and check after each scene. "How does that compare to how you do it today?" Silence means you lost them.
- Never show settings, admin or onboarding unless someone asked. Each extra click costs attention.
- Talk less than 60% of the time even in a demo. Ask questions between scenes.
Building the storyline
For each pain from discovery, fill:
| Pain (their words) | Cost they named | Scene | "Aha" moment | Check-in question |
Rank the rows by cost. The top three become the scenes. Order them: biggest pain first, because attention is highest at the start.
Per-persona map
Different people in the room need different proof:
| Persona | Cares about | Show them | Avoid |
| Economic buyer | ROI, risk, time to value | Outcome dashboard, business case numbers | Clicking through workflows |
| Champion | Looking smart, easier job | Day-in-the-life flow, quick wins | Anything that exposes their current mess in front of their boss |
| End user | Less busywork | The 2-3 actions they do daily | Admin config |
| Technical evaluator | Security, integration, effort | Architecture, integrations, permissions | Hand-waving ("it just works") |
If the economic buyer joins late or leaves early, have a 3-minute version of scene 1 plus the outcome ready.
The close
End with a next step, not "any questions?":
"Based on what you saw, which of the three would matter most if you rolled this out? ... Makes sense. The usual next step is a 2-week pilot with your team on [use case]. Should we map that out with [missing stakeholder] next week?"
Output format
# Demo plan: <Company>, <length> min
Attendees: <name, title, persona>
## Opening (2 min)
- Recap of what we heard: "<pain 1>", "<pain 2>", "<pain 3>". Confirm priorities.
- Last slide first: <end state to show>
## Scene 1: <pain> (x min)
- Tell: ...
- Show: <exact clicks/screens>
- Tell: ...
- Check-in: "..."
## Scene 2: ...
## Scene 3: ...
## Close (3 min)
- Question: ...
- Proposed next step: ...
## Don't show
- ...
## Risky questions and answers
- Q: ... A: ...Example
Context: AI ticket triage. Discovery found that 18% of tickets miss the first-response SLA, agents spend about 25% of their time routing, and CSAT dropped 6 points after the launch. Attendees: VP Support (champion), CX Director (economic buyer).
- Opening: "You told us 18% of tickets miss SLA and routing eats a quarter of agent time. Here's what your queue looks like after 30 days on triage." Show the SLA dashboard at 4% misses (pilot customer data, labeled as such).
- Scene 1, routing: a ticket arrives and is auto-tagged, prioritized and assigned in under 2 seconds. Check-in: "How many clicks does that take your agents today?"
- Scene 2, SLA risk: show the at-risk queue escalating before the breach. Check-in for the CX Director: "Would this have caught the launch-week spike?"
- Scene 3, reporting: weekly CSAT and SLA trend by category.
- Close: propose a 2-week pilot on the billing queue, with success defined as SLA misses under 8%.
- Don't show: the rules editor, SSO setup, the full integrations list.
Related skills
- discovery-call: get the pains that drive the scenes.
- competitive-battlecard: plant differentiators when a competitor is in play.
- objection-handling: prep for pushback during the demo.
- follow-up: send the recap and pilot plan.
- sales-proposal: turn a good demo into a proposal.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

