customer-card-render

Convert Design Thinking markdown artifacts into PowerPoint content YAML for deck generation.

1.4k|284|Updated Nov 2, 2025
One-click install
npx skills add https://github.com/microsoft/hve-core --skill customer-card-render
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: customer-card-render
Source: https://github.com/microsoft/hve-core/tree/main/.github/skills/experimental/customer-card-render
Command: npx skills add https://github.com/microsoft/hve-core --skill customer-card-render

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Turning Design Thinking workshop outputs (vision statements, problem statements, scenarios, use cases, personas) into presentation-ready customer cards normally requires manual copy-paste into slides. This Skill automates the mapping from canonical DT markdown artifacts into structured PowerPoint content YAML.

Core Features & Use Cases

  • Canonical Artifact Parsing: Reads DT markdown files, detects artifact type from frontmatter and folder structure, and extracts required sections with regex-based parsing.
  • Template-Driven YAML Emission: Fills quoted-placeholder content.yaml templates for each artifact type, with YAML escaping to prevent injection and text normalization that unwraps hard-wrapped prose.
  • Multi-Slide Use Case Expansion: Splits each Use Case artifact into 4 consecutive slides covering overview, execution, quality context, and extensions/evidence.
  • PowerPoint Pipeline Handoff: Delegates the actual deck build to the experimental powerpoint skill via Invoke-PptxPipeline.ps1.
  • Use Case: After a DT coaching session produces canonical artifacts under .copilot-tracking/dt/<project-slug>/canonical, run the generator to produce slide content files, then hand them to the powerpoint skill to build a customer-cards.pptx deck.

Quick Start

Ask the AI to generate customer card slides from the canonical Design Thinking artifacts in your DT project folder and build the PowerPoint deck using the powerpoint skill.

Frequently Asked Questions about customer-card-render

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate PowerPoint slides from Design Thinking markdown artifacts?

Run scripts/generate_cards.py with --canonical-dir pointing at your canonical DT markdown folder and --output-dir for the generated content.yaml files. Then activate the powerpoint skill and hand it the content directory, style path, and output path to build the deck.

What artifact types does the customer card generator support?

It supports Vision Statement, Problem Statement, Scenario, Use Case, and Persona artifacts. Vision, Problem, Scenario, and Persona each produce one slide, while each Use Case expands into 4 consecutive slides covering overview, execution, quality context, and extensions.

Does the customer-card-render skill build the PPTX file itself?

No. It only generates content.yaml slide definitions. The actual deck build is delegated to the experimental powerpoint skill, which owns Invoke-PptxPipeline.ps1, theming, validation, and export. If that skill is unavailable, the build step cannot run.

What Python version and dependencies are required?

The skill requires Python 3.11 or later and the uv package manager for environment setup and testing. The generator script itself uses only the Python standard library, so it has no runtime package dependencies.

Why is my generated slide content empty or missing sections?

Empty output usually means the canonical directory path is wrong or the markdown files lack frontmatter. Missing sections occur when headings do not match the expected names in the mapping spec, such as 'Use Case Description' or 'How Might We'.

How does the skill prevent YAML injection from artifact content?

Every dynamic value passes through a yaml_escape function that escapes backslashes, double quotes, and newlines, and every template placeholder is wrapped in double quotes. Frontmatter is parsed by string partitioning rather than a YAML loader, so no arbitrary object construction occurs.