# platform-selection

platform-selection is a Claude Code skill that matches online surveys and experiments to recruitment platforms based on the target population. It activates when choosing among MTurk, Prolific, CloudResearch, and Lucid.

- 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/running-surveys-experiments/platform-selection/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/platform-selection

## What it does

The skill runs in Claude Code and responds to questions like "which platform for my survey" or "MTurk vs. Prolific vs. CloudResearch". The core idea: platform choice is a population choice. MTurk draws from a young, educated US/India pool; Prolific offers pre-screened US and UK participants; Lucid Theorem delivers quota-sampled US adults for short surveys; CloudResearch sits on the same MTurk pool but adds a screening layer and geolocation blocking for server-farm detection.

For each scenario the skill maps the required demographics and behavioral profile to the platform whose available population fits within tolerable error. CloudResearch's repeat-participant tracking matters here — MTurk without that screening layer is rarely the right primary platform on its own.

Two adjacent skills handle adjacent concerns: `fair-pay-and-reputation` covers pay rates and reputation mechanics once you have picked a platform, and `survey-design-checklist` handles questionnaire structure. Install with `npx skills add franklee16/academic-research-skills --skill platform-selection -a claude-code`; the file lands at `~/.claude/skills/platform-selection/SKILL.md`.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install franklee16/academic-research-skills running-surveys-experiments/platform-selection/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/platform-selection/SKILL.md`

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/franklee16/academic-research-skills --path running-surveys-experiments/platform-selection
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/platform-selection/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/running-surveys-experiments/platform-selection/SKILL.md

## When to use it
- match a recruitment platform to the target demographic
- compare MTurk, Prolific, CloudResearch, and Lucid on population profile
- assess whether a current platform fits the research question
- decide whether to switch from MTurk to CloudResearch after data-quality issues
- reach a specific subgroup such as finance professionals or bilingual respondents

## Example prompts
- Which platform gives me a US-representative adult sample for a short behavioral experiment?
- Compare MTurk and Prolific for a study that needs pre-screened US and UK participants
- Should I move from MTurk to CloudResearch given the data-quality problems I'm seeing?

## Similar
- [ad-platform-selection](https://affpapa.org/en/nevibecode/skills/ad-platform-selection.md) — skill · 26700 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/hkustdial-deep-research.md) — skill · 687 installs
- [scientific-problem-selection](https://affpapa.org/en/nevibecode/skills/scientific-problem-selection.md) — skill · 2600 installs
- [survey-generation](https://affpapa.org/en/nevibecode/skills/survey-generation.md) — skill · 1800 installs
- [measure-survey-analysis](https://affpapa.org/en/nevibecode/skills/measure-survey-analysis.md) — skill · 730 installs
- [instrument-designer](https://affpapa.org/en/nevibecode/skills/instrument-designer.md) — skill · 669 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
