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

recipe-academic-literature-review

Skill1 starsChanged 4 months agoMITView on GitHub

Map the gap between published research and filed patents — a scholarly sweep across Semantic Scholar, arXiv, and OpenAlex aligned against a matching patent search, output centered on the published-versus-protected gap rather than a ranked novelty list. Trigger when the user asks for a literature review, a state-of-the-art survey, or a comparison of academic research against patents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer academic (Semantic Scholar + arXiv) for CS/ML papers and preprints.

    line 16
  2. Very specific:

    Write the CQL yourself from the topic's discriminating terms (the specific subject matter, not the field name — method in flowleap-patent), …

    line 37

≈ “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

Recipe: Academic Literature Review

Combine academic and patent searches to map what a field has published against what it has protected.

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. The steps stay the same.

Prefer academic (Semantic Scholar + arXiv) for CS/ML papers and preprints; prefer npl (OpenAlex) for broad cross-disciplinary journal coverage and open-access filtering.

Steps

Step 1: Academic Search

flowleap --json academic search "<research topic>" --limit 20
flowleap --json academic search "<research topic>" --source arxiv --from-year 2020

Step 2: Widen to OpenAlex NPL

flowleap --json npl "<research topic>" --from-year 2020 --limit 10

Step 3: Patent Search for the Same Topic

Write the CQL yourself from the topic's discriminating terms (the specific subject matter, not the field name — method in flowleap-patent), probe the count, then search:

flowleap --json tools run search_patents query='<self-written CQL>' range=1-1 details=false
flowleap --json patent search --query "<self-written CQL>" --limit 20

Step 4: Synthesize the Gap

Align the academic themes against the patent CPC and assignee clusters. Flag topics heavily published but lightly patented (open R&D space) and topics heavily patented but lightly published (crowded IP). Done when each major theme is classified on the published-versus-protected axis.

Visual deliverable

To hand off Step 4's published-versus-protected map as a shareable artifact, follow this recipe's analysis through to the end, then render it with recipe-custom-dashboard — the filing-trends template (multi-series comparison over time) is the closest fit, adapted to plot academic output against patent filings per theme rather than per applicant. Analysis logic stays here; the dashboard skill only owns presentation.

Output

  • Academic papers (title, authors, year, source, citation counts)
  • Related patents (publication number, title, applicant, date, CPC)
  • A published-versus-protected map: themes tagged as open R&D space or crowded IP

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.