flowleap

32 skills in this pack

• flowleap

  Start here — the umbrella skill for the FlowLeap Patent AI CLI. Maps every command family (patent/USPTO/OPS/academic/NPL/legal/citation reads, analytics, OCR, one-call patent verbs, the tools facade, and the raw API escape hatch) and routes to the specialist skills. Trigger when a user asks an agent to use FlowLeap, query the FlowLeap backend, verify local or deployed FlowLeap API health, run patent research commands, or debug FlowLeap CLI/API behavior.

• flowleap-academic

  Search academic literature (Semantic Scholar + arXiv) through the FlowLeap backend with per-source and publication-year filters. Trigger when an agent needs scholarly papers as prior art or technical background — topic searches, restricting to arXiv or Semantic Scholar, or bounding results by publication year. For OpenAlex-backed NPL search see flowleap-npl.

• flowleap-auth

  Authenticate the FlowLeap CLI — OAuth 2.0 device flow login (user code + verification URL), long-lived fl_pat_ personal API tokens for headless agents, status checks, and targeted logout. Trigger when a FlowLeap command fails with 401/unauthenticated, when setting up credentials for an agent or CI, or when the user asks to log in to FlowLeap or mint, list, or revoke API tokens.

• flowleap-citation

  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.

• flowleap-keys

  Manage BYOK patent-data keys (EPO OPS consumer key/secret, USPTO ODP API key) for the FlowLeap CLI — check status, validate live, hand off to a human for the interactive setup wizard, and apply the key-gate doctrine (a gated office is a user-action stop, never an exhausted route). Trigger when a FlowLeap command fails with provider_keys_required or provider_keys_invalid, when patent data calls error about EPO/USPTO credentials, or when the user asks to configure provider keys.

• flowleap-legal

  Hybrid semantic/keyword search over patent-law reference documents (EPC, EPO Guidelines, MPEP, EU and WIPO materials) with jurisdiction filters. Trigger when an agent needs legal grounds, examination-guideline citations, statute text, or authoritative references for patent-law questions.

• flowleap-npl

  Search non-patent literature (scholarly works via OpenAlex) with year, open-access and publication-type filters. Trigger when an agent needs journal articles, conference papers or preprints as prior art or scientific background — complementary to flowleap-academic (Semantic Scholar/arXiv).

• flowleap-ops

  Direct EPO Open Patent Services access through the FlowLeap backend — CQL search plus per-document bibliography, claims, description, family, legal status, and abstract. Trigger when an agent needs authoritative EPO document data for a known publication number, full claims or description text, family members, legal-status events, or a raw OPS CQL search. For query-building or ranked discovery use flowleap-patent; use OPS for authoritative per-document data.

• flowleap-patent

  Search EPO patents with CQL you write yourself — field reference, the discriminating-term rule, and the mandatory count probe. Trigger when an agent needs European or worldwide patent search results, needs to turn an invention description into a CQL query, or wants to tune a query for recall versus precision. For US-specific ODP searches see flowleap-uspto.

• flowleap-patstat

  Portfolio Analytics AND guarded SQL 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; plus agent-written SELECTs against the flowleap.* semantic views for any aggregate the typed commands don't cover (landscapes, grant rates, citation impact, inventor analytics). Trigger when an agent needs a named applicant's filing portfolio, structured-criteria corpus counts (not free-text search), any other PATSTAT aggregate, or any number that must carry a PATSTAT edition citation.

• flowleap-patstat-graph

  Graph Analytics over the PATSTAT snapshot — a named node and the relationships around it. Worldwide DOCDB citation networks (who cites a patent, examiner vs applicant origin), citation/family paths between two patents, family coverage, and an applicant's co-applicant network with top CPC and jurisdictions, every edge carrying a confidence tag (EXTRACTED/INFERRED/AMBIGUOUS) and a PATSTAT row provenance ref. Trigger when an agent needs a traversal answer about a specific patent or applicant — "who cites EP3477840", "how are patent X and patent Y connected", "why does this patent matter", "who does this company file with", where a family has coverage — as opposed to corpus aggregate counts (flowleap-patstat), free-text keyword analytics (flowleap analytics), or document retrieval (flowleap-patent/flowleap-ops).

• flowleap-shared

  Shared reference for every FlowLeap skill — authentication (OAuth device flow, fl_pat_ personal API tokens), credential storage, config precedence, global flags, and output formats. Trigger when a FlowLeap command needs credentials set up, a global flag explained, config file locations, or output-format guidance; for the overall command map start from the `flowleap` skill.

• flowleap-tools

  Discover and run FlowLeap backend tools through the agent-first /v1/tools facade — one stable contract (search_patents, get_bibliography, get_claims, get_patent_summary, compare_patents, reference_search, …) instead of provider-specific endpoints. Trigger when an agent needs patent data and wants a uniform tool interface, needs to discover what the backend can do, or wants compound operations like patent summaries, comparisons, or prosecution timelines.

• flowleap-uspto

  Search USPTO Open Data Portal records with Lucene queries you write yourself, fetch granted patents, applications, continuity chains, and file-wrapper data (prosecution transactions, assignments, foreign priority, PTA, attorney of record), and list IFW documents and read office actions as OCR-extracted text. Trigger when an agent needs US application/prosecution metadata, grant lookups, continuity (parent/child) chains, office-action text, chain of title, or USPTO-specific searches.

• persona-ip-analyst

  IP-analyst persona for the FlowLeap CLI — technology-landscape mapping, portfolio assessment, white-space identification, and filing-trend analytics. Trigger when the user asks the agent to act as an IP analyst, map a landscape, assess a competitor portfolio, or report patent filing trends.

• persona-patent-attorney

  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.

• persona-researcher

  Researcher persona for the FlowLeap CLI — parallel academic-literature and patent exploration to map what is published versus what is protected. Trigger when the user asks the agent to act as a researcher, survey a technology across papers and patents, or find gaps between academic work and filed IP.

• persona-startup-founder

  Startup-founder persona for the FlowLeap CLI — novelty sanity checks, freedom-to-operate scans, and competitor-patent monitoring. Trigger when the user asks the agent to validate a startup's IP position, check whether an idea is already patented, or scope competitor patents before building.

• recipe-academic-literature-review

  Map the gap between published research and filed patents — a scholarly sweep across Semantic Scholar, arXiv, and OpenAlex aligned against a matching patent search, output centered on the published-versus-protected gap rather than a ranked novelty list. Trigger when the user asks for a literature review, a state-of-the-art survey, or a comparison of academic research against patents.

• recipe-audit-report

  Governance recipe for producing an auditable record of AI-assisted patent research — reproducible command log, data provenance for every finding, portfolio status verification, and an AI-usage disclosure section suitable for internal or filing-adjacent records. Trigger when the user asks for an audit trail of patent research, an AI-assistance disclosure, or a verifiable methodology write-up of analysis work.

• recipe-claim-analysis

  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.

• recipe-claim-drafting

  Prosecution recipe for drafting patent claims grounded in prior art — search the closest art, study its claim language, decompose the invention into elements, iterate drafts through claim analysis, and check formal drafting rules against MPEP/EPO guidelines. Trigger when the user asks to draft or improve patent claims, write independent and dependent claims, or stress-test draft claims against known art and formal requirements.

• recipe-custom-dashboard

  Presentation-craft recipe for turning verified FlowLeap patent data into a disposable, self-contained HTML dashboard — the agent writes one small zero-dependency Node program per question that fetches through the CLI, computes every number in code, and emits an offline single-file dashboard with inline SVG charts and a full provenance footer. Trigger when the user asks to make, build, generate, or visualize a dashboard, chart, or visual report of patent data — a company's portfolio, filing trends across competitors, a technology landscape / white-space map, or citation impact.

• recipe-freedom-to-operate

  Freedom-to-operate clearance for a product or technology — per-feature query generation, dual-database blocking-patent search, and legal-status, family, and all-elements claim checks on every live candidate. Trigger when the user asks whether a product or technology can launch without infringing, or requests an FTO/clearance search.

• recipe-infringement-charting

  Litigation recipe for an element-by-element infringement claim chart — verify the patent is in force where it matters, decompose the asserted claims, extract accused-product evidence (OCR datasheets and manuals), and map every element with literal and doctrine-of-equivalents columns. Trigger when the user asks whether a product infringes a patent, wants a claim chart, or needs element-by-element infringement mapping.

• recipe-invalidity-analysis

  Litigation recipe for building an invalidity case against a target patent — pin the priority date, decompose claims into elements, hunt patent and non-patent prior art per element, and assemble an invalidity chart with X/Y/A reference tagging (single-reference novelty vs. combination obviousness vs. background). Trigger when the user asks to invalidate a patent, find 102/103 or Art. 54/56 prior art against granted claims, or assess how strong a patent really is.

• recipe-invention-disclosure

  Prosecution recipe for turning an inventor conversation into a complete invention disclosure form (IDF) — structured technical capture, bar-date audit, novelty pre-check across patents and literature, landscape context, and a filing recommendation. Trigger when the user asks to document an invention, create an invention disclosure, or run a pre-filing novelty sanity check.

• recipe-maintenance-fees

  Check US patent maintenance-fee status and deadlines — compute the 3.5/7.5/11.5-year windows from the grant date, read which fees were actually paid from USPTO transaction events, and report the next docketable deadline with surcharge dates. Trigger when the user asks whether maintenance fees are due or paid, when the next fee deadline is, whether a US patent is still in force fee-wise, or for a fee-status sweep over a portfolio. Dates and status only — never fee amounts.

• recipe-office-action-response

  Prosecution recipe for turning an office action into a structured draft response — OCR the OA, pull every cited reference's claims and bibliography, map rejections element-by-element, and ground arguments in MPEP/EPO guideline citations. Trigger when the user asks to respond to an office action, analyze examiner rejections, or prepare arguments against novelty/obviousness (102/103, Art. 54/56) objections.

• recipe-patent-landscape

  Patent-landscape analysis for a technology area — scoped dual-database search, key-player identification, full-corpus filing analytics, and CPC-versus-year white-space detection. Trigger when the user asks to map a technology space, identify who patents in an area, or report filing trends and white space.

• recipe-patent-to-report

  Formatted single-patent dossier — pull bibliography, abstract, claims, description, family, legal status, prosecution timeline, figures, and related art into one structured Markdown report. Trigger when the user asks for a complete profile, dossier, or report on a specific patent.

• recipe-prior-art-search

  Comprehensive prior-art / novelty search before filing — natural-language query generation, dual EPO/USPTO patent search, an academic literature sweep, and X/Y/A tagging of the closest hits. Trigger when the user asks to find prior art for an invention, run a novelty search, or check what already exists before filing.