# idea-generation

A skill that generates research ideas, refines them over several rounds and checks novelty against the literature. Useful before you commit to a paper topic.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1800 installs · ★ 433
- Author: lingzhi227
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lingzhi227/agent-research-skills/tree/HEAD/skills/idea-generation/SKILL.md
- Updated: 2026-02-27
- HTML: https://affpapa.org/en/nevibecode/skills/lingzhi227-idea-generation

## What it does

\`idea-generation` takes a research area or task description and produces 3–5 distinct ideas. Each one comes with a name, a title, an experiment plan and ratings. Then comes iterative refinement: the idea gets critiqued and sharpened while its core stays intact. The loop runs until convergence or 5 rounds.

Novelty checking runs against Semantic Scholar. The bundled `novelty_check.py` script performs a multi-round literature search and returns a binary verdict — novel or not — with justification. You can also search Semantic Scholar and arXiv by hand. Finally, ideas are ranked on three 1–10 scales: interestingness, feasibility and novelty.

The script needs Python, and the search itself goes out to Semantic Scholar. The skill's own rules insist ideas stay feasible with available resources — no new datasets, no massive compute. It advises against overfitting an idea to one dataset or model, and tells the agent to be a harsh critic on novelty.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill idea-generation -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill idea-generation -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill idea-generation -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lingzhi227/agent-research-skills idea-generation
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill idea-generation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lingzhi227/agent-research-skills --path skills/idea-generation
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill idea-generation -a opencode
```

### 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/lingzhi227/agent-research-skills/tree/HEAD/skills/idea-generation/SKILL.md

## When to use it
- brainstorm directions for a new paper
- check whether a similar result is already published
- drop ideas you cannot afford to run
- get an experiment plan for a chosen hypothesis
- compare ideas by interestingness and novelty

## Example prompts
- Generate research ideas around adaptive attention head pruning
- Run `novelty_check.py` on this idea
- Score these ideas on interestingness, feasibility and novelty

## Similar
- [idea-discovery](https://affpapa.org/en/nevibecode/skills/idea-discovery.md) — skill · 580 installs
- [idea-discovery-robot](https://affpapa.org/en/nevibecode/skills/idea-discovery-robot.md) — skill · 501 installs
- [semanticscholar-skill](https://affpapa.org/en/nevibecode/skills/semanticscholar-skill.md) — skill · 3400 installs
- [literature-review](https://affpapa.org/en/nevibecode/skills/collaborative-deep-research-literature-review.md) — skill · 732 installs
- [paper-navigator](https://affpapa.org/en/nevibecode/skills/paper-navigator.md) — skill · 357 installs
- [idea-evaluator](https://affpapa.org/en/nevibecode/skills/idea-evaluator.md) — skill · 735 installs

## Other versions with the same name
- [idea-generation · anthropics](https://affpapa.org/en/nevibecode/skills/anthropics-idea-generation.md) — 1200 installs

From the same set: [lingzhi227/agent-research-skills](https://affpapa.org/en/nevibecode/by/lingzhi227/agent-research-skills.md) — 30 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