agentleFS
flowleap-aiflowleap-ai/flowleap-cli/skills/flowleap-academic/SKILL.md

flowleap-academic

Skill1 starsChanged 4 months agoMITView on GitHub

Search academic literature (Semantic Scholar + arXiv) through the FlowLeap backend with per-source and publication-year filters. Trigger when an agent needs scholarly papers as prior art or technical background — topic searches, restricting to arXiv or Semantic Scholar, or bounding results by publication year. For OpenAlex-backed NPL search see flowleap-npl.

The file

Files
SKILL.md

FlowLeap Academic

Auth and global flags: see flowleap-shared.

In a chat client with the FlowLeap connector or in the FlowLeap Patent AI app, call the tools named in the flowleap-shared tool table instead of these commands, and never run a flowleap command there.

Usage

flowleap academic search <query> [flags]

Runs the search_academic tool on the Tools facade. Returns academic papers with title, authors, year, and source. No patent-data key is needed, so this corpus stays live while EPO or USPTO is key-gated — offer it as different data (literature, not patents), never as a substitute (see flowleap-keys).

Flags

FlagDescriptionDefault
--limitMaximum results10
--sourceSource to search: scholar or arxiv (repeat the flag for both)all sources
--from-yearOnly papers published in or after this yearnone
--to-yearOnly papers published in or before this yearnone

Examples

# Basic search
flowleap academic search "machine learning patent classification"

# With limit
flowleap academic search "CRISPR gene editing applications" --limit 20

# arXiv only, bounded by publication year
flowleap academic search "transformer attention mechanisms" --source arxiv --from-year 2020 --to-year 2024

# Both sources explicitly
flowleap academic search "solid state electrolyte" --source scholar --source arxiv

# JSON output for agents
flowleap academic search "neural network optimization" --json

Tools-facade equivalent: search_academic (query=, sources=, max_results=, filter=). Its sources values are semantic-scholar and arxiv; papers still come back tagged scholar or arxiv.

Response Format (JSON)

The CLI prints the tool's data payload — { query, total, papers, sources }. The envelope fields (success, executionTimeMs, cached) sit outside it; add --verbose to see the cache verdict and timing on stderr.

{
  "query": "machine learning patent classification",
  "total": 1,
  "papers": [
    {
      "title": "Machine Learning in Patent Analysis",
      "authors": ["Smith, J.", "Doe, A."],
      "year": "2024",
      "source": "arxiv",
      "url": "https://example.com/paper",
      "abstract": "...",
      "doi": "10.1000/example",
      "alsoIn": ["scholar"]
    }
  ],
  "sources": [
    { "source": "scholar", "status": "rate_limited", "returned": 0, "retryAfter": 30 },
    { "source": "arxiv", "status": "ok", "returned": 1, "totalHits": 214 }
  ]
}

sources[] reports every requested source: ok, rate_limited or error. A source that failed contributed no papers, so its absence is a gap, never "no literature exists"; the human and table output name it on stderr. total is the number of papers returned; totalHits is a source's own match count. Duplicates across sources are merged (alsoIn names the other one).

For a broad NPL sweep run flowleap npl (OpenAlex) first and use this command as the second pass (see flowleap-npl).

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.