Skills for curating and maintaining KG-Registry resource pages from a local clone of the repository: expand and edit a resource, curate the next batch of stubs, validate a curated page, and update a stale product URL.
Plugin kg-registry-curation from marketplace kg-registry in Knowledge-Graph-Hub/kg-registry. Commands read from the repo's manifest — today.
curate-nextUse when asked to curate the next N KG-Registry stub resources. Selects uncatalogued stub pages not already listed in reports/curation_problems.tsv and dispatches single-resource curation in parallel.
find-downstream-usagesUse when asked everywhere a given resource is used or consumed downstream — which knowledge graphs, aggregators, or products draw on it, and any recorded real-world uses — based on what KG-Registry records. Reads the live hosted KG-Registry Parquet files over HTTP (no local clone needed), combining
find-similar-resourcesUse when asked to find KG-Registry resources similar to a given one — alternatives, related graphs, or near-duplicates. Reads the live hosted KG-Registry Parquet files over HTTP (no local clone needed), combining structured signals (shared domains, taxa, category, node/edge scale, shared upstream so
kg-registry-curationUse when curating or expanding a KG-Registry resource page. Applies to stub resources and incomplete existing pages stored as Markdown with YAML front matter under resource/.
kg-registry-product-url-updateUse when updating the URL for a specific KG-Registry product, especially when the original URL is dead, redirected, versioned, or replaced by a newer canonical landing or download page.
kg-registry-validationUse when validating or quality-checking KG-Registry resource pages after curation, especially for schema compliance, provenance slot correctness, and stub-cleanup issues.
search-resourcesUse when asked to find KG-Registry resources about a topic, subject area, or domain (e.g. "everything about RNA interactions", "what proteomics knowledge graphs are there", "find resources mentioning Reactome"). Queries the live hosted KG-Registry Parquet files over HTTP — no local clone needed — ma
trace-upstream-sourcesUse when asked what upstream data sources a given resource (usually a knowledge graph) is built from — its inputs, dependencies, or provenance — based on what KG-Registry records. Reads the live hosted KG-Registry Parquet files over HTTP (no local clone needed), walks each product's original_source
Read-only skills for exploring the KG-Registry over HTTP (no local clone needed): search resources by topic or domain, trace a resource's upstream data sources, find everywhere a resource is used, and find similar resources. Each queries the published Parquet files at https://kghub.org/kg-registry/registry/parquet/ via DuckDB.
8 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.