Agent skill · Backend & API

demo-builder

Builds personalized demo assets for top prospects using the founder's product API/MCP/SDK. Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link.

gooseworks-aigithub.com/gooseworks-aiGitHub ↗
claude-codecodexcursorcan modify filesMIT
Install
npx skills add gooseworks-ai/goose-skills --skill demo-builder --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 20 KB
Bundled scripts: none
Allowed tools: BashReadWriteEditGrepGlobWebFetchWebSearch
Path: skills/lead-generation/packs/lead-gen-devtools/demo-builder/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,091
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Builds personalized demo assets for prospects using the founder's product API/MCP/SDK. Creates a working prototype, tests it, and generates a comparison report with a live demo link. The workflow covers identifying a prospect, researching their business, proposing 2-3 demo concepts, building and testing a prototype, generating performance metrics, and delivering an HTML comparison report plus a live demo link for outreach.

How it works

  • Phase 1: Identify the Prospect
    • Path A: If user provides a company name or details, accept as-is and proceed to Phase 2
    • Path B: If prior lead data exists, shortlist top candidates from signal data and ask user to pick one
    • Proceed to Phase 2 for a single prospect
  • Phase 2: Research the Prospect
    • Gather company description, customers, scale indicators, current tech stack, relevant pain points, compliance needs, and public workflows from sources like website, jobs, GitHub, signal data, press
  • Phase 3: Propose Demo Concepts
    • Generate 2-3 concrete demo concepts using a framework that aligns with the prospect’s context, workflows, and differentiators
    • Present concepts in a structured format and request which concept to build
  • Phase 4: Build the Demo
    • Study product API/SDK/MCP: read docs, endpoints, authentication, rate limits, and tooling
    • Build a working prototype using prospect’s real context, ensure interactivity, limit scope to 2-3 capabilities, and include a wow moment
    • Save artifacts to .tmp/demos/[prospect-company-name]/
    • Test the demo for load, primary use case, edge cases, and interactive functionality; document test results
  • Phase 5: Generate the Comparison Report
    • Research 3-5 competitors with pricing, features, compliance, deployment, limitations, and public reviews
    • Collect performance metrics from tests (latency, accuracy, cost, etc.)
    • Build a polished HTML report with sections: header, key metrics, live test results, comparison matrix, platform deep dives, industry requirements, recommendation, and CTA
  • Phase 6: Package and Deliver
    • Present a DEMO PACKAGE detailing the working demo, report, and outreach context
    • Draft outreach message tailored to the prospect’s signal

When to use it

  • When a user provides a prospect company or URL and wants a personalized demo
  • When user requests building an asset or outreach for a specific company
  • When user has API/MCP/SDK access and wants a live demonstration tied to prospect context
  • When a lead generation run has produced signals and a next-step demo is desired

What it can touch

  • Uses the user’s API/MCP/SDK tooling to build the demo
  • Saves artifacts under the .tmp/demos path
  • Generates an HTML report and a live demo link or shareable artifact

Caveats

  • Requires API access, MCP access, SDK, or CLI for the user's product to actually build the demo
  • Requires access to product documentation or MCP tools
  • Does not fabricate competitor weaknesses or unsupported claims; relies on public docs and signal data
From the SKILL.md

# Demo Builder Build personalized demo assets for prospects using the founder's product API/MCP/SDK. Send a working prototype that solves the prospect's actual problem — with a comparison report and live demo link. ## When to Use - User provides a prospect company name or URL and wants a demo built for them - User asks to "build a demo", "create an asset", or "personalize outreach" for a specific company - User has a product with API access, SDK, MCP server, or CLI and wants to demonstrate it to a prospect - User has completed a lead generation run and wants to act on the results - User asks "what do I do with these leads", "how do I reach out", or "help me with outreach" ## Prerequisites - API access, MCP access, SDK, or CLI for the user's product — the agent needs to be able to actually build something - Access to the product's documentation (API docs URL, SDK readme, or MCP tool list) ## Phase 1: Identify the Prospect This skill supports two input paths: ### Path A: User provides a prospect directly (primary path) If the user provides a company name, website URL, or prospect details: 1. Accept the prospect as-is — no lead data required 2. Proceed directly to Phase 2 (Research th

What's inside
Steps it walks through
  1. When to Use
  2. Prerequisites
  3. Phase 1: Identify the Prospect
  4. Path A: User provides a prospect directly (primary path)
  5. Path B: User has signal data from prior lead generation runs
  6. Either path leads to Phase 2
  7. Phase 2: Research the Prospect
  8. Step 4: Deep-Dive the Prospect's Business
  9. Phase 3: Propose Demo Concepts
  10. Step 5: Generate Demo Ideas
  11. Step 6: User Approves a Concept
  12. Phase 4: Build the Demo
  13. Step 7: Study the Product's API/SDK/MCP
  14. Step 8: Build the Prototype
More from goose-skills
All skills →
About this skill
What does the demo-builder skill do?

Builds personalized demo assets for top prospects using the founder's product API/MCP/SDK. Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link.

How do I install it?

Run `npx skills add gooseworks-ai/goose-skills --skill demo-builder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From gooseworks-ai/goose-skills, a repository with 1,091 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going