# paper-reading-experiment-design

The paper-reading-experiment-design skill turns a research method’s claims into an experiment plan, covering evidence, metrics, baselines, and checks. Use it once the method has a clear thesis and target.

- 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/07-experiment-design/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-experiment-design

## What it does

The skill helps plan experiments around a method’s central claims. It links claims to observable evidence and measurement protocols, then guides choices about tasks, datasets, baselines, and metrics. When the thesis, target failure, or intervention point is still unsettled, it routes the work back to method definition.

The workflow creates an experiment folder under `workspace/experiment-designs/` and builds a set of planning artifacts: a claim-evidence map, experiment design, baseline matrix, metric map, and ablation and control plan. Decisions are handled in small steps, with user confirmation before dependent choices proceed. A fully automatic run produces a provisional sketch, not a final plan.

Install it in Claude Code with `npx skills add franklee16/academic-research-skills --skill 07-experiment-design -a claude-code`. An uncommitted method keeps the resulting design provisional, so it is not ready to present as a finalized experiment plan.

## Install

### Claude Code (native platform)

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

2. **Manually: put the files in place**
- File: `~/.claude/skills/07-experiment-design/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/07-experiment-design/

### Codex

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

2. **Manually: put the files in place**
- File: `.agents/skills/07-experiment-design/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

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

2. **Manually: put the files in place**
- File: `.cursor/skills/07-experiment-design/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/07-experiment-design
```

2. **Manually: put the files in place**
- File: `.github/skills/07-experiment-design/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill paper-reading-experiment-design -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/07-experiment-design
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/07-experiment-design/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/07-experiment-design/SKILL.md

## When to use it
- connect a method’s claims to observable evidence
- choose tasks, datasets, and baselines for an experiment
- map claims to metrics and measurement protocols
- plan ablations, confound checks, and stress tests
- prepare a study plan that addresses likely reviewer objections

## Example prompts
- Design experiments for my committed method, and show me the source decision first.
- Map the method’s main claims to metrics, measurement protocols, and validity risks.
- Draft a provisional experiment sketch and flag decisions that still need review.

## Similar
- [experiment-design](https://affpapa.org/en/nevibecode/skills/microsoft-experiment-design.md) — skill · ★ 1627 repo stars
- [paper-planning](https://affpapa.org/en/nevibecode/skills/paper-planning.md) — skill · 434 installs
- [ccf-experiment-designer](https://affpapa.org/en/nevibecode/skills/ccf-experiment-designer.md) — skill · 2300 installs
- [measure-experiment-design](https://affpapa.org/en/nevibecode/skills/measure-experiment-design.md) — skill · 846 installs
- [experiment-design-kit](https://affpapa.org/en/nevibecode/skills/experiment-design-kit.md) — skill · ★ 450 repo stars
- [research-data-analysis](https://affpapa.org/en/nevibecode/skills/research-data-analysis.md) — skill · ★ 26 repo stars

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
