MCP.Market

decision-questionnaire skill

by NousResearch·NousResearch/hermes-agent·263k stars·MIT

Turn an unanswerable decision into a questionnaire doc.

A100/100content scan

Is the decision-questionnaire skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-10-25.

No findings.

Install the decision-questionnaire skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/NousResearch/hermes-agent.git /tmp/hermes-agent
mkdir -p ~/.claude/skills
cp -r /tmp/hermes-agent/optional-skills/productivity/decision-questionnaire ~/.claude/skills/decision-questionnaire
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Decision Questionnaire

Turns 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 in a meeting. The recipient holds knowledge the user lacks; the questionnaire pulls it out of them.

Ported from mattpocock/skills' MIT-licensed to-questionnaire skill.

When to Use

expert, a stakeholder, a vendor contact, ops)

  • A decision blocks on facts or judgment held by someone else (a domain

pending someone else's input

  • The user says "I need to ask X about this" or keeps deferring a decision
  • Preparing for a meeting where specific answers must come back

Do NOT use when the answer is discoverable from the environment (codebase, docs, web) — find it yourself first.

Core Principle: Interview the Send, Not the Subject

The user cannot answer the subject-matter questions (that's the point), but they can ALWAYS answer questions about the send. Interview them only about that, in two short exchanges:

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.

  1. Who is it going to? Role, expertise, relationship to the user. This

can't resolve alone. Done when you have a concrete list of what the user must walk away able to do or decide.

  1. What do you need back? The specific decisions or facts the user

Then write the questionnaire: draft questions aimed at the gap between what the recipient knows and what the user needs, following the structure below. Write it to decision-questionnaire-.md in the current directory (slug from the topic) and report the absolute path. Done when the file exists and every item from step 2 is covered by a question.

Document Structure

Frame it as a discovery questionnaire: the user lacks context, the recipient holds it. Order questions most-important-first (async means you may only get one pass). Group under ## headings by theme once there are more than a handful.

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 question — a single idea, never compound>

_Why this matters: <one line, only where the question could be misread or
invite a throwaway answer>._

>

## Anything else?

A closing catch-all: anything we didn't ask that we should know?

Every question gets an answer stub (>) directly beneath it.

Pitfalls

why the document exists. Only interview the send.

  1. Grilling the user about the subject. They can't answer it — that's

recipients fade.

  1. Compound questions. One idea per question; split "and/or" questions.
  2. Burying the critical question. Most-important-first; async

what turns a throwaway answer into a useful one — but don't add it to questions that are already unambiguous.

  1. Context dump. One orienting paragraph, not the whole history.
  2. Skipping the "why this matters" line on ambiguous questions. It's

Verification

exchanges before drafting

  • [ ] Recipient's role/knowledge and the needed outcomes captured in two
  • [ ] Every step-2 item covered by at least one question
  • [ ] Questions single-idea, most-important-first, answer stubs present
  • [ ] File written and absolute path reported to the user

More skills from NousResearch/hermes-agent

  • A1passwordSet up op CLI, sign in, and read or inject secrets.
  • A3-statement-modelBuild integrated IS/BS/CF financial workbooks in Excel.
  • AaccelerateRun PyTorch training across GPUs with minimal changes.
  • Cactual-setupSet up Actual Computer (actual.inc) inference in Hermes.
  • Aadversarial-ux-testRoleplay a hostile user to find and triage UX pain points.
  • Aagent-merge-conflict-arbiterNeutral arbiter for merge conflicts between two agents.
  • AagentmailUse when an agent needs AgentMail CLI email inboxes.
  • Aai-presenter-videoMake a verified AI presenter video from script + image.
  • AairtableAirtable REST API via curl. Records CRUD, filters, upserts.
  • AanatomyExplain an idea as an interactive isometric machine figure.
  • Cantigravity-cliOperate the Antigravity CLI (agy): plugins, auth, sandbox.
  • Aapple-notesManage Apple Notes via memo CLI: create, search, edit.

All agent skills → · MCP servers