agentleFS
flowleap-aiflowleap-ai/flowleap-cli/skills/flowleap-citation/SKILL.md

flowleap-citation

Skill1 starsChanged 4 months agoMITView on GitHub

USPTO enriched citation data from office actions — citations by application, forward citations of a document, citation statistics and X-category novelty-destroying references. Trigger when an agent assesses novelty risk, examiner-cited prior art, or how often a patent is cited against later applications.

The file

Files
SKILL.md

FlowLeap Citation Search (USPTO enriched citations)

Auth and global flags: see flowleap-shared.

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.

Which citation universe?

FlowLeap exposes two, and neither is a superset of the other:

  • This skill — USPTO office-action enriched citations: US only, drawn from examiner reasoning, with X/Y/A relevance categories. Use it for novelty risk, what an examiner actually cited, and how often a document is cited against later US applications.
  • flowleap-patstat-graph — the worldwide DOCDB citation network from the PATSTAT snapshot, with examiner-vs-applicant origin, confidence tags, and row-level provenance. Use it for citation structure across offices, the path between two patents, or a patent's whole citation picture in one call.

Pick by whether the question is about US examiner reasoning (here) or worldwide citation structure (there). PATSTAT answers are snapshot data with a Data Edition; these are live USPTO records.

By application

flowleap --json citation search 16123456 --size 20
flowleap --json citation search 16123456 --category x --examiner-cited-only
flowleap --json citation search 16123456 --from 2020-01-01 --to 2023-12-31

--from/--to bound the office-action date range (YYYY-MM-DD) — when the examiner cited the reference, not when either document published.

Forward citations (who cites this document)

flowleap --json citation forward US10123456 --size 20

Analysis shortcuts

flowleap --json citation stats 16123456      # counts by category/source
flowleap --json citation novelty 16123456    # X-rated novelty-destroying citations

Categories: x (novelty-destroying), y (inventive-step with combination), a (background), all.

Tools-facade equivalents: search_office_action_citations (by application), search_enriched_citations (forward, by cited document) and get_citation_stats (aggregate counts only). citation novelty has no tool of its own — it is a recipe over search_office_action_citations with category: "X" and examiner_cited_only: true.

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.