Borrowing it
Nothing to install: this file belongs to MicrosoftLearning/trainer-demo-deploy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MicrosoftLearning/trainer-demo-deploy/main/.github/prompts/generate-demoguide.prompt.mdgit clone --depth 1 https://github.com/MicrosoftLearning/trainer-demo-deployWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/microsoftlearning/trainer-demo-deploy/generate-demoguide)<a href="https://agentmods.dev/commands/microsoftlearning/trainer-demo-deploy/generate-demoguide"><img src="https://agentmods.dev/badge/commands/microsoftlearning/trainer-demo-deploy/generate-demoguide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/microsoftlearning/trainer-demo-deploy/generate-demoguide"><img src="https://agentmods.dev/badge/commands/microsoftlearning/trainer-demo-deploy/generate-demoguide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01013 |
| Opus 5.5 | $0.00000 | $0.00405 |
| Sonnet 5.5 | $0.00000 | $0.00203 |
| Haiku 4.5 | $0.00000 | $0.00101 |
Grade A, and why
generate-demoguide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to varcheck — 112 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
---
description: "Generate an audience-aware demo guide for a deployed Azure project"
agent: "az-07-DemoGuide"
model: "GPT-5.3-Codex"
tools:
- read/readFile
- edit/createFile
- edit/editFiles
- execute/runInTerminal
- search/codebase
- search/listDirectory
- "microsoft/playwright-mcp/*"
- "azure-mcp/*"
- agent
argument-hint: Provide the project name to generate a demo guide for
---
# Generate Demo Guide
Create a comprehensive, audience-aware demonstration guide for a deployed
Azure infrastructure project. Includes pre-demo validation, step-by-step
demo guide, talking points, and contingency playbook.
## Mission
Read all project artifacts, ask about audience format, validate environment
readiness, and generate a professional demo guide that a presenter can
follow to deliver a successful live demonstration.
## Scope & Preconditions
- `generated-scenarios/${input:projectName}/02-architecture-assessment.md` must exist
- `generated-scenarios/${input:projectName}/05-implementation-reference.md` should exist (or `04-implementation-plan.md` at minimum)
- `generated-scenarios/${input:projectName}/06-deployment-summary.md` should exist (deployed resources and outputs feed the demo guide)
- Read `.github/skills/az-consolidated/SKILL.md` for naming conventions, template H2 structure, and demo patterns/personas
- Output saved to `generated-scenarios/${input:projectName}/demoguide/demoguide.md`
- Include Playwright MCP generated screenshots of the different demo steps; store these in `generated-scenarios/${input:projectName}/demoguide/images/` and reference them in the demoguide.md. To make this possible, prompt the user for an authenticated Playwright browser session. Use that session to loop through the demo steps.
## Inputs
| Variable | Description | Default |
| ---------------------- | ------------------------------------------------ | --------- |
| `${input:projectName}` | Project name matching the `generated-scenarios/` folder | Required |
## Workflow
### Step 1: Read Source Artifacts
Read all available project artifacts in order:
1. `01-requirements.md` — business context, stakeholders
2. `02-architecture-assessment.md` — resources, WAF scores
3. `04-implementation-plan.md` — resource inventory, dependencies
4. `05-implementation-reference.md` — deployment details, file structure
5. `06-deployment-summary.md` — deployed resources, outputs, endpoints
6. `generated-scenarios/{projectName}/infra/` or `generated-scenarios/{projectName}/infra/terraform/` — actual templates
### Step 2: Generate Pre-Demo Checklist
Create validation commands for every resource in the architecture.
Include Azure CLI commands that the presenter can copy-paste to verify
the environment before going live.
### Step 3: Generate Demo Script
For each major feature or resource:
1. Title with time estimate
2. What to show (Portal / CLI / code)
3. What to say (talking point for the audience)
4. Expected result
5. Failure recovery reference
### Step 4: Create relevant demo screenshots
Use Playwright MCP tools to capture screenshots of the deployed resources in the Azure Portal. Store these in `generated-scenarios/${input:projectName}/demoguide/images/` and reference them in the demo guide next to the relevant steps.
### Step 5: Validate screenshot files
If Playwright capture was used, validate required screenshots exist in
`generated-scenarios/${input:projectName}/demoguide/images/` before finalizing.
Minimum required files:
- `resource-group-overview.png`
- `firewall-overview.png`
- `network-topology.png` (if applicable)
- One screenshot per major demo step
If Playwright is unavailable or declined, require:
- `<img>` placeholders with `TODO: capture screenshot` alt text
- A brief note describing why screenshots were not captured live
### Step 6: Save Artifact
Save to `generated-scenarios/{projectName}//demoguide/demoguide.md` following the
exact H2 structure defined in the azure-artifacts skill.
## Quality Checklist
- [ ] All source artifacts read before generation
- [ ] Audience format confirmed with user
- [ ] H2 headings match template structure exactly
- [ ] Every demo step has a time estimate
- [ ] Every CLI command uses actual resource names
- [ ] Pre-demo checklist covers all critical resources
- [ ] Playwright-generated screenshots included and properly referenced
- [ ] Required screenshot files exist on disk, or fallback placeholders + reason are present
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 112 lines · 0 tokens per session scan A fab27740b4e1
generate-demoguide is a command published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,013 tokens. A static security scan graded it A with 0 findings. It is 100% identical to varcheck, differing in 112 lines, and is treated as a copy.
generate-demoguide compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| generate-demoguideMicrosoftLearning/trainer-demo-deploy | Command | 31 | 11d ago | MIT | A | 0 | GitHub Copilot |
| setup-bigquery.esminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| setup-bigqueryminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| start-13-5.enminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| start-13-5.esminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| start-13-5minicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| setup-line-harnessminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 19 | Claude Code |