skills

Use when stress-testing a product idea before committing — interviews the user on six PM lenses and produces a conviction brief alongside the session.

Builds a self-contained interactive HTML visualisation that makes a process, algorithm, decision logic, or system visually and experientially understandable. Primary input is a linear walkthrough, but works directly from code, documents, or concept descriptions too — and can invoke the linear-walkthrough skill as an intermediate step if the source material lacks sufficient clarity or structure. Use when the user wants to "see how this works", wants an interactive version of a walkthrough, wants to explain a process visually to an audience, or asks to "visualise", "animate", or "build an interactive explanation" of anything. Richer and more interactive is always preferred, as long as it makes the logic clearer rather than decorating it.

Generates a linear, narrative walkthrough of source material — code, documents, architecture diagrams, meeting notes, Jira tickets, or any combination. Produces a step-by-step guide that explains logic, purpose, and connections between components in a readable sequence. Use when the user wants to understand how something works, wants to explain a system to others, asks to "walk through" or "explain" code or docs, or needs to document a system's logic for learning or onboarding. Also trigger when the user provides files or code and asks "how does this work?" or "take me through this."

Converts Markdown files to Google Docs-friendly DOCX format using Pandoc (via a helper script).

Use the Obsidian CLI to interact with the vault natively—search, read, create, manage tasks, properties, daily notes, and more. Prefer CLI over raw file I/O for vault-aware operations.