← ClaudeAtlas

flowleap-patstatlisted

Portfolio Analytics over the PATSTAT snapshot — structured-criteria aggregation by named applicant, CPC/IPC class, office, year, family, and grant status, with harmonized entity resolution and Data Edition provenance. Trigger when an agent needs a named applicant's filing portfolio, structured-criteria corpus counts (not free-text search), or any number that must carry a PATSTAT edition citation.
flowleap-ai/flowleap-plugins · ★ 0 · AI & Automation · score 72
Install: claude install-skill flowleap-ai/flowleap-plugins
# FlowLeap Patstat (Portfolio Analytics) Auth and global flags: see `flowleap-shared`. ## Topic Analytics vs Portfolio Analytics — routing rule FlowLeap runs two aggregate-analytics engines, split by *criteria shape*, not by metric: - **Topic Analytics** (`flowleap analytics`, the Google-Patents corpus engine) — the question's essential criterion is **free-text keywords** over title/abstract ("quantum computing filings over time"). Publication-level counts, substring name matching, per-query cost. - **Portfolio Analytics** (`flowleap patstat`, this skill, the PATSTAT engine) — the question is expressible in **structured criteria**: named applicant (entity-resolved, harmonized names), CPC/IPC class, office, year, family, grant status. Family-level counting, zero marginal cost. Routing rule: if the question needs free text, use `flowleap analytics`; if it is structured criteria — especially a named company — use `flowleap patstat`. Individual documents (one known publication or application) are neither — use the search/retrieval skills (`flowleap-patent`, `flowleap-uspto`, `flowleap-ops`). ## Portfolio ```bash flowleap --json patstat portfolio "Siemens AG" --from-year 2015 --to-year 2023 ``` Response shape: a quotable `summary` line first — relay it verbatim before adding any narrative — then filings-by-year/office/grant-status aggregate tables, then a `data_edition` provenance line. ## Ambiguous applicant (422) An unresolved applicant name returns HTTP 42