agentleFS
niyaznurbhashaniyaznurbhasha/claude-skills/research-gap-finder/SKILL.md

research-gap-finder

Skill0 starsChanged 7 months agoMITView on GitHub

Discovers confirmed-open research gaps from academic papers in any domain. Use when user says "find research gaps", "scan research gaps", "what's unsolved in", "open problems in", "research ideas for", or asks about academic frontiers and unsolved problems in a field. Requires the discovery-dashboard package.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If 0 results, try broader/shorter terms

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Gap Finder

Searches arxiv + Semantic Scholar for survey papers, open-problems papers, and research agendas in any domain. Extracts "Future Work" / "Limitations" sections from papers via ar5iv HTML. Validates that gaps are confirmed unsolved.

Requires: discovery-dashboard installed with its conda environment.

Instructions

Step 1: Run the scan

conda run -n discovery python research_gaps.py --domain "<domain>" --max-papers 40

Parameters:

  • --domain (required): 1-3 words works best. Long queries return fewer results.
  • --max-papers: Max papers to process (default 30, recommended 40).
  • --max-extract: Max papers for ar5iv full-text extraction (default 15).
  • --skip-ar5iv: Skip full-text extraction, abstracts only (faster).

Tips:

  • Short domains work best: "AI safety", "world models", "continual learning"
  • Multiple runs on related terms build richer coverage
  • If 0 results, try broader/shorter terms

Step 2: Check results

The script outputs a summary with paper counts and validation breakdown.

Results saved to:

  • data/research_gaps/{domain-slug}_papers.json — raw paper data
  • data/research_gaps/{domain-slug}.json — dashboard display file

Step 3: Re-render dashboard

conda run -n discovery python dashboard.py

Results appear in Edges tab → Research Ideas.

Step 4: Report findings

Summarize: paper count, validation breakdown, top confirmed-open gaps, connections to user's work.

How It Works

  1. DISCOVER: 6 search strategies across arxiv + S2 (surveys, open problems, position papers, workshop papers, limitations). Filters by authority.
  2. EXTRACT: Fetches ar5iv HTML, extracts Future Work / Limitations sections. Abstract fallback.
  3. VALIDATE: Recency (last 2 years = confirmed), cross-referencing (2+ papers = confirmed), addressing-paper search.

Troubleshooting

  • 0 papers: Domain query too long — try shorter terms
  • Mostly uncertain: Papers older than 2 years with many addressing papers — normal for mature fields
  • Slow (5-10 min): S2 rate limiting — use --skip-ar5iv or --max-papers 20

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.