Skip to content
SkillModel-led604 tokens in use

to-questionnaire

Turns a decision you cannot answer alone into a Markdown questionnaire for the one person who can, after a short interview about who it goes to and what you need back.

328,791 stars on the repository MIT Licensemattpocock/skills · skills/productivity/to-questionnaire
claude plugin install mattpocock-skills@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing to-questionnaire costs

22tokens idle
604tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples3/15
  • Output15/15
  • Size15/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers