# mine_gaps

The mine_gaps Claude Code prompt maps a research field and identifies gaps supported by paper notes. Each gap needs evidence tied to a paper and page numbers.

- 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/mine_gaps.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/mine-gaps

## What it does

The prompt builds a field overview from notes on papers, first describing the state of the research and then grouping papers by approach. It looks for untested assumptions, conflicting findings, author-stated limitations, missing settings or data, weaknesses in evaluation, and methods that could transfer across studies.

Each proposed gap must cite a paper ID and relevant pages, and be labelled as author-admitted or inferred. The prompt also asks for up to three papers that come closest and two or three English search queries for independent checking. Low-quality papers cannot serve as the sole basis for an argument. Supply a research idea and paper notes; `$max_gaps` sets the gap limit and `$language` sets the response language.

## Install

### Claude Code (native platform)

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

## When to use it
- group papers by their research approach
- spot conflicting findings across studies
- surface untested assumptions and stated limitations
- tie each proposed gap to papers and page numbers

## Example prompts
- \`/mine_gaps` — map these paper notes and identify evidence-backed research gaps.
- Review these notes: outline the field, group the papers, then list gaps with supporting page references.
- For each gap, name nearby papers and write English search queries to check for related work.

## Similar
- [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
- [literature-review](https://affpapa.org/en/nevibecode/skills/lingzhi227-literature-review.md) — skill · 4100 installs
- [systematic-literature-review](https://affpapa.org/en/nevibecode/skills/systematic-literature-review.md) — skill · 2500 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
