to-questionnaire is a user-invoked skill that produces a discovery questionnaire: a Markdown document you hand to one person to fill in async or to work through together in a meeting. The recipient holds knowledge you lack, and the questions pull it out of them.
The agent interviews you about the send, which you can always answer. It asks who the recipient is and what you need back, then drafts questions aimed at the gap between what they know and what you need.
What You Get
- A Markdown file named to-questionnaire-<slug>.md in the current directory
- Questions ordered most important first, grouped under theme headings
- A context paragraph and a how-to-answer section for a recipient who was not in your head
- An answer stub under every question and a closing catch-all question
Common Use Cases
- Collecting requirements from a domain expert before you write a spec
- Asking an engineer on another team about constraints you cannot see
- Preparing a meeting where you and a stakeholder fill in the answers together
What Makes It Unique
Most interview skills grill you about the subject. This one grills you only about the send, who it goes to and what you need back, because those are questions you can always answer. The questionnaire then targets the gap between the recipient’s knowledge and your need, and it is ordered for a single async pass.
Under The Hood
The skill is a single SKILL.md with no scripts. It has three steps, each with a stated done condition: learn who the recipient is, learn what you need back, then write the file. It carries a Markdown template for the document and one example question. The only write is the questionnaire file in the current directory. It sets disable-model-invocation, so only you can fire it.