to-questionnaire — Claude Code skill: questionnaires and setup
Turns a decision you cannot answer alone into a Markdown questionnaire for someone with the missing context. Use it to collect answers asynchronously or work through questions in a meeting.
/plugin marketplace add mattpocock/skills
/plugin install mattpocock-skills@mattpocockWhat to-questionnaire does
The skill identifies what you need to learn and who can provide it. It asks about the recipient and the decisions or facts you need, then writes to-questionnaire-<slug>.md in the current directory.
The document gives the recipient context, states its purpose, and groups questions by theme when there are more than a handful. Questions appear in order of importance, with an answer stub beneath each one. The skill adds a brief explanation when a question could be misunderstood or prompt a throwaway answer.
You can send the questionnaire to one person to fill in asynchronously or complete it together in a meeting. Model invocation is disabled, so you need to run the skill explicitly. Decide who will receive the document and what you need from them before starting.
What it helps with
- Collect facts another person has before making a decision
- Ask a colleague for missing context asynchronously
- Prepare focused questions for a meeting about an unresolved decision
Example prompts for the agent
- Create a questionnaire for my teammate to clarify the requirements behind this decision.
- Draft questions for the person who knows the system history; I need to decide whether to change the design.
- Make a Markdown questionnaire for our meeting and save it in the current directory.
How to install to-questionnaire
1Plugin marketplace
/plugin marketplace add mattpocock/skills/plugin install mattpocock-skills@mattpocockThis installs the whole mattpocock-skills plugin with all its skills
2Skills CLI (Vercel)
npx skills add mattpocock/skills --skill to-questionnaire -a claude-code3Manually: put the files in place
~/.claude/skills/to-questionnaire/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/to-questionnaire/
Manually: put the files in place
.agents/skills/to-questionnaire/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/to-questionnaire/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mattpocock/skills to-questionnaire2Manually: put the files in place
.github/skills/to-questionnaire/SKILL.mdPlatform CLI
gemini skills install https://github.com/mattpocock/skills --path skills/productivity/to-questionnaireManually: put the files in place
.devin/skills/to-questionnaire/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set32
The whole set →Similar
Questions about to-questionnaire
How do I install to-questionnaire in Claude Code?
Run /plugin marketplace add mattpocock/skills, then run /plugin install mattpocock-skills@mattpocock.
What does to-questionnaire do?
It works out what you need to learn and who can answer, then creates a Markdown questionnaire aimed at that information gap.
Where does the skill save the questionnaire?
It writes to-questionnaire-<slug>.md to the current directory.
Source text
SKILL.md · MIT
--- name: to-questionnaire description: Turn a decision you can't fully answer into a questionnaire for someone else to fill in. disable-model-invocation: true --- Turn something the user can't answer alone into a **questionnaire**: a Markdown document they hand to one person to fill in async, or fill out together over a meeting. The recipient holds knowledge the user lacks; the questionnaire pulls it out of them. **Grill the send, not the subject.** Interview the user only about the _send_, which they can always answer: who it goes to, and what they need back. The questions in the document then target the **gap** between what the recipient knows and what the user needs. 1. **Who is it going to?** Ask, in one exchange, the recipient's role, expertise, and relationship to the user. This fixes the questionnaire's tone and how much context it must carry. Done when you know who the recipient is and what they know that the user doesn't. 2. **What do you need back?** Ask, in one exchange, the specific decisions or facts the user can't resolve alone and needs from this person. Done when you have a concrete list of what the user must walk away able to do or decide. 3. **Write the questionnaire.** Draft questions aimed at the gap from steps 1–2, following the Document structure below. Write it to `to-questionnaire-<slug>.md` in the current directory (slug from the topic) and report the path. Done when the file exists and every item the user named in step 2 is covered by a question. ## Document structure Frame the document as a **discovery questionnaire**: the user lacks context, the recipient holds it. Order questions most-important-first, since async means you may only get one pass, and group them under `##` headings by theme once there are more than a handful. Write it using the template below. <questionnaire-template> # <Questionnaire title> **Purpose:** why this questionnaire exists and the decision riding on it. **From:** <the user>, **To:** <the recipient>, **How your answers will be used:** <where they go> ## Context One paragraph orienting a recipient who wasn't in the user's head. Enough to answer well, not a page. ## How to answer Deadline and rough effort. Partial answers and "I don't know" are useful: flag anything you're unsure of rather than skipping it. ## <Theme heading> One `##` section per theme. Under each, its questions, most-important-first. Every question is one idea, never compound, with an answer stub directly beneath, and a one-line _why this matters_ only where the question could be misread or invite a throwaway answer. <question-example> ### What load is the system expected to handle at launch? _Why this matters: it decides whether we provision for burst traffic now or defer it._ > </question-example> ## Anything else? A closing catch-all: anything we didn't ask that we should know? </questionnaire-template>
© Matt Pocock · MIT · mattpocock/skills