agentleFS
timmo001timmo001/skills/to-questionnaire/SKILL.md

to-questionnaire

Skill2 starsChanged todayApache-2.0View on GitHub

Turn a decision the user cannot answer alone into a channel-aware questionnaire draft for one other person. Use when missing knowledge belongs to a colleague, maintainer, or domain expert and the user needs questions for GitHub, Slack, Discord, or a document.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 104 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Identify the recipient: Ask for their role, expertise, relationship to the user, and destination channel.

    line 11
  2. Distinctive:

    Identify the needed result: Ask which facts or decisions the user must get back and what those answers will unblock.

    line 12
  3. Distinctive:

    Draft for the channel: Put the most important questions first, make each question cover one idea, and add a short reason only when it …

    line 13

“Common” is measured: kept by at least 6 in 10 of the 104 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

To Questionnaire

Turn something the user cannot answer alone into questions for the one person who holds the missing knowledge. Grill the send, not the subject: ask only what the user can answer about the recipient and the result they need.

  1. Identify the recipient. Ask for their role, expertise, relationship to the user, and destination channel. Done when the tone, assumed context, and output shape are clear.
  2. Identify the needed result. Ask which facts or decisions the user must get back and what those answers will unblock. Done when every required outcome is concrete.
  3. Draft for the channel. Put the most important questions first, make each question cover one idea, and add a short reason only when it prevents a weak or ambiguous answer.

Channel Shapes

  • GitHub comment: concise Markdown that fits one issue, pull request, or discussion comment. Include enough context for readers who were not in the conversation. Do not include answer stubs.
  • Slack or Discord: a short context message followed by individually answerable numbered questions. Split into several draft messages when one message would be hard to answer.
  • Document: title, purpose, sender and recipient, one context paragraph, answer guidance, themed question sections, and a final "Anything else?" question.

Return the draft in chat by default. Do not write a file, create or edit a GitHub comment, or perform any other external action unless the user explicitly requests that specific action. Slack and Discord output is always draft-only because no integration is available.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.