explaingit

pillarpaheat/good-question-171

15PythonAudience · researcherComplexity · 2/5LicenseSetup · easy

TLDR

An AI coding-agent skill that guides researchers from a vague idea to a well-formed, falsifiable research question. It diagnoses your stage, applies domain adapters for fields like ecology or biomedicine, and outputs a structured Good Question Card with hypotheses, a pilot plan, and falsifiability checks.

Mindmap

mindmap
  root((good-question))
    Modes
      Mentor
      Reviewer
      Collaborator
      Grant Panel
    Question Card
      Working Title
      Rival Hypotheses
      Two Week Pilot
      Falsifiability Check
    Domain Adapters
      Ecology
      Remote Sensing
      AI for Science
      Biomedicine
    Quality Checks
      Evidence Backed
      Specific Enough
      Negative Result Value
    Languages
      English
      Chinese
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Turn a rough research direction or literature gap into a structured, falsifiable research question ready for a proposal.

USE CASE 2

Get an AI mentor or grant-panel critique of your early research idea before investing weeks of work.

USE CASE 3

Check whether your question has rival hypotheses and a concrete two-week pilot you could actually start.

USE CASE 4

Use in Chinese or English to sharpen questions in fields like ecology, biomedicine, or AI for science.

Tech stack

PythonClaude CodeOpenAI Codex CLI

Getting it running

Difficulty · easy Time to first run · 5min

Install as a skill in Claude Code or OpenAI Codex CLI. No external API keys or databases required. Works in English and Chinese out of the box.

MIT license, free to use, modify, and share for any purpose, including commercial projects, as long as you keep the license notice.

In plain English

good-question is a skill for AI coding agents (tested with Claude Code and OpenAI Codex CLI) that helps researchers sharpen a vague idea into a well-formed research question. It is most useful when you have a rough direction, a literature gap, or an early proposal sketch but are not sure whether the question is actually worth pursuing. The skill is bilingual, with full support for Chinese and English. The tool starts by diagnosing where you are in the research process: do you have only a broad interest, a spotted gap, an early idea, a proposal draft, or a stalled project? It then operates in one of four modes (mentor, reviewer, collaborator, or grant-panel) depending on the context. If the question depends on current knowledge in a field, the skill first builds a brief from public-source information and labels claims as either evidence-backed or inferred. For specialized fields like ecology, remote sensing, AI for science, social science, and biomedicine, it loads a lightweight domain adapter with relevant norms and common pitfalls. The main output is a structured card called a Good Question Card. It contains a working title, the research question itself, why it matters, which default assumption it challenges, at least two competing hypotheses, a discriminating observation or experiment that could tell the hypotheses apart, what result would falsify the question, a concrete two-week pilot someone could actually start, the strongest reviewer objection, and the best next action. The point of the card is not to produce polished wording but to give the researcher enough structure to decide whether the question deserves real investment. For a question to pass the project's internal standard, it must satisfy seven checks: it matters to someone, it is specific enough for evidence to touch it, it has rival explanations, it can be falsified, a pilot is feasible, a negative result still teaches something useful, and any field-context claims trace back to public sources. The project is licensed under MIT and includes field guides, evaluation cases, and a release checklist.

Copy-paste prompts

Prompt 1
I have a vague interest in [topic]. Act as a research mentor and help me diagnose which stage I am at, then guide me through building a Good Question Card with rival hypotheses and a two-week pilot.
Prompt 2
Review my draft research question as a grant-panel reviewer: identify the strongest objection, check whether it is falsifiable, and suggest a discriminating experiment that could separate competing hypotheses.
Prompt 3
I am studying [field, e.g. remote sensing / biomedicine]. Load the relevant domain adapter and flag common pitfalls in my proposed research question, labelling any field-context claims as evidence-backed or inferred.
Prompt 4
My research project has stalled. Walk me through the seven quality checks in good-question and tell me which ones my current question fails, then suggest the best next action.
Prompt 5
Generate a complete Good Question Card for this idea: [paste idea]. Include a working title, why it matters, the default assumption it challenges, at least two competing hypotheses, and what result would falsify it.
Open on GitHub → Explain another repo

← pillarpaheat on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.