Back to Skills Marketplace
Skill pack

Patent Research Assistant

Prior-art strategy, patent database query guidance, claims and citation analysis, and patent evidence quality checks for Deep Research.

v0.1.0 1 skill By Kendr patentprior-artclaimscitationsresearchevidence

How to use it

  1. Open Kendr Desktop.
  2. Go to Skills, then Marketplace.
  3. Search for Patent Research Assistant or patent-research-assistant.
  4. Install the pack, then enable the pack or individual skills you want available in agentic mode.

Kendr Desktop compares the installed version with the hosted catalog version and offers an update when this pack changes.

Install source

Use this hosted archive when installing or updating the pack from Kendr Desktop.

https://api.kendr.org/api/skills/packs/patent-research-assistant/archive

Patent Research Assistant

Prior-art research guidance for patent databases, claim overlap, citation trails, and evidence quality checks.

Patent Research Assistant

Use this skill when the user asks for patent research, prior-art discovery, invention landscape analysis, freedom-to-operate style source gathering, patentability context, claim overlap, citation trails, assignee trends, or patent database query strategy.

Workflow:

  • Start by restating the invention, product, method, material, system, or claim element being researched.
  • Search across synonyms, older terminology, assignee names, inventor names, IPC/CPC classes, and core claim verbs instead of relying on the user's exact wording.
  • Prefer primary patent databases, patent family pages, prosecution or publication records, standards references, technical papers, and product documentation over generic commentary.
  • Separate direct prior art, adjacent art, implementation background, and market or assignee context.
  • Track jurisdiction, publication number, priority date, publication date, assignee, inventor, claim element overlap, cited-by trail, and family members when available.
  • Flag weak evidence when a result only shares keywords but does not disclose the relevant claim element.

Output expectations:

  • Summarize high-confidence prior-art candidates with why each candidate matters.
  • Include a claim-element coverage table when the prompt asks about novelty or patentability.
  • Preserve exact patent numbers, URLs, dates, assignees, and cited references.
  • State unresolved search gaps, missing jurisdictions, and terminology that should be searched next.

Safety:

  • Do not present the output as legal advice.
  • Do not claim freedom to operate, validity, infringement, or patentability as a final legal conclusion.