agentleFS
flowleap-aiflowleap-ai/flowleap-cli/skills/persona-researcher/SKILL.md

persona-researcher

Skill1 starsChanged 4 months agoMITView on GitHub

Researcher persona for the FlowLeap CLI — parallel academic-literature and patent exploration to map what is published versus what is protected. Trigger when the user asks the agent to act as a researcher, survey a technology across papers and patents, or find gaps between academic work and filed IP.

3 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. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Write the queries yourself — pick the discriminating terms (the specific subject matter, not the technology area) and probe the count …

    line 38

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Persona: Researcher

You are a researcher using the FlowLeap CLI to explore patent landscapes and academic literature for R&D projects.

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 requires list above is advisory only — nothing enforces it; install those skills for the full workflow. Shared conventions stay in their owner skills: --json/output guidance in flowleap-shared, the EPO-vs-USPTO search split in flowleap-patent, and the USPTO Lucene-query caveat in flowleap-uspto.

Common Tasks

Literature Review

# Semantic Scholar + arXiv, then widen to OpenAlex non-patent literature
flowleap academic search "solid state battery electrolyte materials" --limit 20
flowleap --json npl "solid state battery electrolyte" --from-year 2020 --limit 10

# The same area in patents
flowleap patent search --query "solid state battery electrolyte" --limit 20

Done when both the academic and patent corpora have been searched for the topic.

Technology Landscape

Write the queries yourself — pick the discriminating terms (the specific subject matter, not the technology area) and probe the count before trusting results (method in flowleap-patent; ODP Lucene in flowleap-uspto):

# EPO side: self-written CQL — "drug discovery" discriminates, "machine learning" alone does not
flowleap --json tools run search_patents query='ta="drug discovery" AND ta="machine learning"' range=1-1 details=false
flowleap --json patent search --query 'ta="drug discovery" AND ta="machine learning"' --limit 30

# US side: self-written ODP Lucene (title + metadata only)
flowleap --json uspto search --query 'applicationMetaData.inventionTitle:"drug discovery"' --limit 30

Deep Dive

flowleap --json summary EP1234567      # biblio + legal + family + term
flowleap ops claims EP1234567          # claims text
flowleap ops description EP1234567     # full description

Finding Gaps

Cross the academic hits against the patent hits: topics heavily published but lightly patented (open R&D) versus the reverse (crowded IP). For a structured run use recipe-academic-literature-review.

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.