# seeds

The seeds Claude Code prompt derives fresh research directions from gaps in the literature. Each one comes with a practical starting point that can be tested within a week.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 159 repo stars
- Author: saideao
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/saideao/research-idea-review/tree/HEAD/src/idea_review/prompts/en/seeds.md
- Updated: 2026-11-02
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/seeds

## What it does

seeds turns a research landscape and its identified gaps into new directions. Each proposal must differ in substance from the original idea; renaming the same problem or swapping in another dataset does not count. The prompt links every direction to a gap by its ID.

Each direction also gets a hands-on test that can be attempted within a week. Supply the original idea, the landscape and its gaps, the requested number of directions, and the output language. The response follows a required JSON format.

The gap IDs need to come from the supplied research landscape.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/seeds.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/saideao/research-idea-review/tree/HEAD/src/idea_review/prompts/en/seeds.md

## When to use it
- derive research topics from gaps in the literature
- discard proposals that restate the original research problem
- map each direction to a gap ID
- give each proposal a testable first step for the coming week

## Example prompts
- Generate 3 research directions from this idea and the gaps in the literature review.
- Suggest directions that tackle different core problems, and link each one to a gap ID.
- Return the new directions as JSON in English, with a practical test for each one.

## Similar
- [idea-generation](https://affpapa.org/en/nevibecode/skills/lingzhi227-idea-generation.md) — skill · 1900 installs
- [idea-creator](https://affpapa.org/en/nevibecode/skills/idea-creator.md) — skill · 635 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/imbad0202-deep-research.md) — skill · 8200 installs
- [paper-search-mcp-openai-v2](https://affpapa.org/en/nevibecode/mcp/paper-search-mcp-openai-v2.md) — MCP server · 7042 installs
- [Academic Research MCP — ArXiv & Google Scholar](https://affpapa.org/en/nevibecode/mcp/academic-research-mcp-arxiv-google-scholar.md) — MCP server · 6779 installs
- [academic-search](https://affpapa.org/en/nevibecode/skills/academic-search.md) — skill · 6300 installs

From the same set: [saideao/research-idea-review](https://affpapa.org/en/nevibecode/by/saideao/research-idea-review.md) — 8 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
