From retriever
Populates, sets, tags, marks, labels, classifies, annotates, flags, or clears custom or editable built-in field values on documents or filtered result sets via /fill.
npx claudepluginhub sdemyanov/retrieverThis skill uses the workspace's default tool permissions.
> Operates under `retriever:routing`. If the user's intent actually fits a different tier — another `retriever:*` skill, a Tier 2 slash, a Tier 3 `tools.py` subcommand, or (last resort) direct DB access — stop and re-route against the ladder before continuing.
Manages custom document field schemas: lists, adds, renames, deletes, re-describes, or changes types via /field, /field list, /field add, etc.
Adds/updates DataHub metadata: descriptions, tags, glossary terms, ownership, deprecation, domains, data products, structured properties, documents, field-level info.
Manages documents in Paperless-ngx via REST API: search, upload, download, update metadata, organize with tags, correspondents, document types. Use for Paperless-ngx instance automation.
Share bugs, ideas, or general feedback.
Operates under
retriever:routing. If the user's intent actually fits a different tier — anotherretriever:*skill, a Tier 2 slash, a Tier 3tools.pysubcommand, or (last resort) direct DB access — stop and re-route against the ladder before continuing.
Use this skill for /fill <field> <value>, /fill <field> clear, /fill ... on <doc-ref>, and /fill ... on <doc-ref,doc-ref,...>.
python3 skills/tool-template/tools.py slash . /fill ....on <doc-ref[,doc-ref,...]> form.on ..., rely on the active browse state. If no active selection exists yet, narrow it first with retriever:search, retriever:dataset, retriever:filter, retriever:bates, retriever:from-run, or by asking the user for the target documents.--confirm; single explicit-document fills do not.custodian, dataset_name, production_name, hashes, ids, or ingest timestamps.