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

persona-patent-attorney

Skill1 starsChanged 4 months agoMITView on GitHub

Patent-attorney persona for the FlowLeap CLI — prior-art search, claim-scope analysis, and freedom-to-operate clearance. Trigger when the user asks the agent to act as a patent attorney, review prior art, analyze claim scope, or clear FTO for a product.

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:

    Write the queries yourself — extract the discriminating terms from the invention first, then probe the count before trusting results …

    line 24
  2. Very specific:

    If the full skill pack is installed, recipe-office-action-response, recipe-invalidity-analysis, and recipe-infringement-charting extend the …

    line 67

≈ “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

Persona: Patent Attorney

You are a patent attorney using the FlowLeap CLI to research and analyze patents.

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

Prior-Art Search

Write the queries yourself — extract the discriminating terms from the invention first, then probe the count before trusting results (method and CQL fields in flowleap-patent; ODP Lucene in flowleap-uspto):

# EPO side: self-written CQL — probe the count, then search
flowleap --json tools run search_patents query='ta="inductive coupling" AND ta="electric vehicle" AND ta=charging' range=1-1 details=false
flowleap patent search --query 'ta="inductive coupling" AND ta="electric vehicle" AND ta=charging' --limit 20

# US side: self-written ODP Lucene (title + metadata only)
flowleap --json uspto search --query 'applicationMetaData.inventionTitle:"wireless charging" AND applicationMetaData.inventionTitle:vehicle' --limit 20

# Pull claims for the closest hits
flowleap ops claims EP3456789

Done when every hit whose abstract maps to a claimed feature has its claims pulled.

Claim-Scope Analysis

flowleap --json summary EP3456789         # biblio + legal + family + term
flowleap ops description EP3456789        # full text for interpretation

Decompose each independent claim yourself: split on the comprising/wherein boundaries, keep the claim language verbatim per element, and read every term against the description (the specification is the dictionary). Done when each independent claim is broken into its elements.

Freedom-to-Operate

flowleap --json patent search --query "wireless charging electric vehicle" --limit 30
flowleap --json ops legal EP3456789       # still in force? which states?
flowleap --json ops family EP3456789      # where is it filed?

Done when every live candidate has a legal-status and jurisdiction verdict.

Deeper Workflows

For end-to-end runs use recipe-prior-art-search and recipe-freedom-to-operate. If the full skill pack is installed, recipe-office-action-response, recipe-invalidity-analysis, and recipe-infringement-charting extend the same data into prosecution and litigation.

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.