AGENT SKILL

to-questionnaire

Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.

License 许可
Apache-2.0
最近更新
2026-10-19
Stars
★ 0
Forks
1

01 前言 Front Matter

name
to-questionnaire
description
Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.

02 资源文件 1

03 SKILL.md 正文

To Questionnaire

Turn something the user can't answer alone into a Markdown questionnaire for one recipient who holds the missing knowledge. Grill the send, not the subject: interview the user only about who it is for and what they need back, which they can always answer. Ask the way the grilling skill does (AskUserQuestion on Claude Code, plain text elsewhere). The questions in the document then aim at the gap between what the recipient knows and what the user needs.

1. Who is it for?

Ask for the recipient's role, expertise, and relationship to the user, in one exchange. Done when you know who they are and what they know that the user doesn't; that fixes the tone and how much context the document must carry.

2. What do you need back?

Ask, in one exchange, for the specific decisions or facts the user can't settle alone. Done when you have a concrete list of what the user must be able to decide or do once the answers come back.

3. Write it

Write to-questionnaire-<topic-slug>.md in the current directory with the template below and report its path. Done when the file exists and every item from step 2 is covered by a question.

Order questions most important first, since an async recipient may give you one pass, and group them under themed headings once there are more than a handful. Each question asks one thing, with an answer stub beneath it. Add a one-line reason only where the question could be misread or invite a throwaway answer.

# <Title>

**Purpose:** why this exists and the decision riding on it.
**From:** <user> · **To:** <recipient> · **Answers will be used for:** <where they go>

## Context

One paragraph for someone 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 what you're unsure of rather than skipping it.

## <Theme>

### What load must the system handle at launch?

_Why this matters: it decides whether we provision for bursts now or later._

>

## Anything else?

Anything we didn't ask that we should know?

04 同仓库更多 Skills

dougborg
dougborg/harness-kit

teach

Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.

教师与教育
★ 0
dougborg
dougborg/harness-kit

svg-logo-designer

Generate SVG logos with multiple concepts, layouts, and color variations.

图像与多媒体
★ 0
dougborg
dougborg/harness-kit

documentation-writer

Writes and revises human-facing documentation — READMEs, contributor and setup guides, reference pages, architecture notes, CLAUDE.md, and changelog entries. Covers picking the right document type for the question being asked, structuring for skimming, writing examples that actually run, and keeping docs from going stale. Use when creating or rewriting docs, when a README has drifted from the code, or when deciding where a piece of information belongs. For SKILL.md and agent files, use /skill-writer instead.

内容创作者写作与文案
★ 0
dougborg
dougborg/harness-kit

adhd-mode

Shapes every response for a reader with ADHD: the next action first, numbered steps, progress restated each turn, tangents held back, concrete time estimates, wins made visible. Stays on for the rest of the session until the reader says "stop adhd mode". On Claude Code, the harness-kit:adhd output style does the same without invoking this skill.

★ 0
dougborg
dougborg/harness-kit

wait-what

That last message didn't land: re-explain it with the missing context.

★ 0
dougborg
dougborg/harness-kit

research

Investigates a question against primary sources (official docs, source code, specs, first-party APIs) and writes the findings, with a citation for every claim, to a Markdown file. Use when the user wants a topic researched or facts gathered from documentation, when a decision waits on facts from outside the repo, and when reading legwork should run while other work continues.

资料检索与研究
★ 0