# paper-reading-research-question

paper-reading-research-question turns an existing field map into testable research questions: candidate angles, an evidence check and question cards.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 240 repo stars
- Author: franklee16
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/franklee16/academic-research-skills/tree/HEAD/lit-review/Paper-Reading-Skills-main/skills/02-research-question/SKILL.md
- Updated: 2026-09-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/paper-reading-research-question

## What it does

The skill carries you from a finished field map to research questions you can act on. It works from a single Field Map Workspace that holds `field_boundary.md`, `research_clusters.md`, `research_opportunities.md` and at least one paper record, then narrows the opportunity candidates into Candidate Angles. Every angle gets a contribution type: benchmark, method, system, human study, theory or measurement.

Before any angle is proposed, the skill settles your Writing Intent — one main goal, up to two secondary ones, plus practical limits such as time, collaborators, data access or compute. Then comes an evidence sufficiency check, collection of missing support into `evidence/`, and one Research Question Card per supported angle. Artifacts live under `{workspace-root}/research-questions/{field-slug}/`; the root defaults to `workspace/`.

It will not start from a blank slate. Complete workspaces are looked up in `{workspace-root}/field-maps/`, and when none qualifies the skill points you to `paper-reading-field-map` first. A missing `research_opportunities.md` also blocks the cards. Read papers first, then ask this skill for questions.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill paper-reading-research-question -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/02-research-question/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/02-research-question/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill paper-reading-research-question -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/02-research-question/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill paper-reading-research-question -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/02-research-question/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install franklee16/academic-research-skills lit-review/Paper-Reading-Skills-main/skills/02-research-question
```

2. **Manually: put the files in place**
- File: `.github/skills/02-research-question/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill paper-reading-research-question -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/franklee16/academic-research-skills --path lit-review/Paper-Reading-Skills-main/skills/02-research-question
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/02-research-question/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/franklee16/academic-research-skills/tree/HEAD/lit-review/Paper-Reading-Skills-main/skills/02-research-question/SKILL.md

## When to use it
- turn a list of opportunities into one concrete research question
- narrow a topic to an angle with a stated contribution type
- spot which evidence is missing before committing to an angle
- keep the reasoning on disk so you can resume weeks later
- align the question with your writing goal and your deadline

## Example prompts
- Use the workspace at `workspace/field-maps/graph-nlp` and draft research question cards from it
- List the candidate angles from `research_opportunities.md` and ask me which contribution type fits
- Run the evidence check on the benchmark angle and gather what is missing into `evidence/`

## Similar
- [analyzing-research-papers](https://affpapa.org/en/nevibecode/skills/analyzing-research-papers.md) — skill · 564 installs
- [ArXiv Scout](https://affpapa.org/en/nevibecode/mcp/arxiv-scout.md) — MCP server · 3426 installs
- [academic-search](https://affpapa.org/en/nevibecode/skills/academic-search.md) — skill · 6300 installs
- [semanticscholar-skill](https://affpapa.org/en/nevibecode/skills/semanticscholar-skill.md) — skill · 3500 installs
- [paper-search](https://affpapa.org/en/nevibecode/skills/paper-search.md) — skill · ★ 67 repo stars
- [firecrawl-research-index](https://affpapa.org/en/nevibecode/skills/firecrawl-research-index.md) — skill · 25900 installs

From the same set: [franklee16/academic-research-skills](https://affpapa.org/en/nevibecode/by/franklee16/academic-research-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
