Tell us who you need answers from and what you're missing
To questionnaire

Tell us who you need answers from and what you're missing; get back a clean form you send them to fill in.
--- 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
Overview
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.
Manual install (npx, ZIP)
npx skills add mattpocock/skills --skill to-questionnaire -g -a claude-codemkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/mattpocock/skills/tar.gz/3cca18b368ae \
| tar -xz -C ~/.claude/skills --strip-components=3 skills-3cca18b368ae/skills/productivity/to-questionnaireNew-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/77464ff2918231573cb0/to-questionnaire.zip" -OutFile "$env:TEMP\to-questionnaire.zip"; Expand-Archive "$env:TEMP\to-questionnaire.zip" -DestinationPath "$HOME\.claude\skills" -ForceConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md2.8 KBagents/1 file · 166 B
Read the files here
Show the full text55 lines
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.
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.
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.
Write the questionnaire. Draft questions aimed at the gap from steps 1–2, following the Document structure below. Write it to
to-questionnaire-<slug>.mdin 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 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.
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>| 1 | |
| 2 | name to-questionnaire |
| 3 | description Turn a decision you can't fully answer into a questionnaire for someone else to fill in. |
| 4 | disable-model-invocation true |
| 5 | |
| 6 | |
| 7 | 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. |
| 8 | |
| 9 | **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. |
| 10 | |
| 11 | |
| 12 | **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. |
| 13 | |
| 14 | **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. |
| 15 | |
| 16 | **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. |
| 17 | |
| 18 | ## Document structure |
| 19 | |
| 20 | 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. |
| 21 | |
| 22 | <questionnaire-template> |
| 23 | |
| 24 | # <Questionnaire title> |
| 25 | |
| 26 | **Purpose:** why this questionnaire exists and the decision riding on it. |
| 27 | |
| 28 | **From:** <the user>, **To:** <the recipient>, **How your answers will be used:** <where they go> |
| 29 | |
| 30 | ## Context |
| 31 | |
| 32 | One paragraph orienting a recipient who wasn't in the user's head. Enough to answer well, not a page. |
| 33 | |
| 34 | ## How to answer |
| 35 | |
| 36 | Deadline and rough effort. Partial answers and "I don't know" are useful: flag anything you're unsure of rather than skipping it. |
| 37 | |
| 38 | ## <Theme heading> |
| 39 | |
| 40 | 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. |
| 41 | |
| 42 | <question-example> |
| 43 | ### What load is the system expected to handle at launch? |
| 44 | |
| 45 | _Why this matters: it decides whether we provision for burst traffic now or defer it._ |
| 46 | |
| 47 | > |
| 48 | </question-example> |
| 49 | |
| 50 | ## Anything else? |
| 51 | |
| 52 | A closing catch-all: anything we didn't ask that we should know? |
| 53 | |
| 54 | </questionnaire-template> |
| 55 |
Details
- Updated
- Sep 18, 2026
- License
- MIT
- Stars on the repo
- ★ 267,278
- Checked
- Source
- mattpocock/skills ↗
- Creator
- mattpocock · 7 listings
Similar skills
See all →
SkillDesign a 360-degree feedback survey or write a structured360-Degree Feedback Template Skill
SkillExtracting first-party expertise from a subject-matterExpert interview
SkillStart of the UGC pipeline for persona researchPersona & Script
SkillExtracts what the user actually wants instead of what theyInterview me
SkillMarketes psychology & mental modelsMarketing Psychology & Mental Models
MCPPodcast guest outreach and coordination specialistGuest outreach coordinatorMore from mattpocock
SkillDiagnosis loop for hard bugs and performance regressionsDiagnosing bugs
SkillImplement the result of /to-spec and /to-tickets in codeImplement spec
SkillWriting a PR body
SkillConduct a retrospective on a coding sessionRetro
SkillHand over your messy notesTurn a pile of notes into an article
SkillGenerate an interactive bash wizard that walks a human