Recipe academic literature review

Skill flowleap-ai/flowleap-plugins/plugins/flowleap/skills/recipe-academic-literature-review

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.From its SKILL.md

Install

npx -y skills add flowleap-ai/flowleap-plugins --skill recipe-academic-literature-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 437 tokens by cl100k_base, as published. Nobody here has run it

Recipe: Academic Literature Review

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

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

flowleap patent build-query "<research topic>" --allow-external-processing
flowleap --json patent search --query "<CQL from build-query>" --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

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.