agentleFS
flowleap-aiflowleap-ai/flowleap-cli/skills/recipe-claim-analysis/SKILL.md

recipe-claim-analysis

Skill1 starsChanged 4 months agoMITView on GitHub

Decompose a patent's claims into elements, keywords, and search queries with full supporting context — claims text, abstract, bibliography, description, and family. Trigger when the user asks to analyze what a patent claims, break claims into elements, or interpret claim scope against its specification.

The file

Files
SKILL.md

Recipe: Claim Analysis

Extract a patent's claims with full context, then decompose them into elements.

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.

Steps

Step 1: Extract Claims

flowleap --json ops claims <patent-number>

Done when you have the full claim set, independent claims identified. For an office with no text source, use the family-member workaround in flowleap-shared.

Step 2: Get Context

flowleap --json ops abstract <patent-number>
flowleap --json ops biblio <patent-number>
flowleap --json ops description <patent-number>

Step 3: Check Related Patents

flowleap --json ops family <patent-number>

Step 4: Decompose Every Independent Claim — Yourself

There is no backend claim analyzer: you do the decomposition, one independent claim at a time.

  1. Split the claim into preamble, transition (comprising / consisting of), and body. Element boundaries fall at the semicolons and at wherein / configured to clauses.
  2. Keep the claim language verbatim per element — paraphrase in a second column if useful, but the verbatim text is what later maps against prior art. Tag each element structural or functional.
  3. Derive keywords and synonyms per element from the element's own nouns, checking the description (Step 2) for the applicant's own alternative wording — the specification is the claim's dictionary.
  4. Write a search query per key element combination with the self-written query method in flowleap-patent (extract terms, discriminating term, count probe). The element pairs, not single elements, usually carry the discrimination. Show the statement as a Search Statement block — see flowleap-patent references/search-statement.md.

Repeat for every independent claim. For each dependent claim, note how it narrows its parent (the added element). Done when every independent claim has an element breakdown and each dependent claim's added limitation is recorded.

Output

Complete claim data with supporting context:

  • Full claims text (independent and dependent)
  • Abstract, bibliographic data, and description for interpretation
  • Family members by office (the extended family)
  • Element breakdown (verbatim language, structural/functional tag, keywords) and self-written follow-up search queries per independent claim, plus the narrowing limitation added by each dependent claim

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.