Automate Paperless-ngx document uploads, searches, tagging, and bulk edits via REST API.
npx skills add https://github.com/jmagar/claude-homelab --skill paperless-ngx
Please help me install this Agent Skill. Skill: paperless-ngx Source: https://github.com/jmagar/claude-homelab/tree/main/skills/paperless-ngx Command: npx skills add https://github.com/jmagar/claude-homelab --skill paperless-ngx
Paperless-ngx provides automated OCR, full-text search, and metadata-driven document management for private archives, but lacks ready-to-run programmatic control in Claude workflows. This skill offers a read-write interface to the Paperless-ngx API, enabling uploading, searching, tagging, updating metadata, archiving, and exporting documents from a self-hosted instance.
Install Paperless-ngx, generate an API token, configure ~/.claude-homelab/.env with PAPERLESS_URL and PAPERLESS_API_TOKEN, then begin using the provided scripts to manage documents.
High-intent search queries and answers about installing and using this skill.
Automating document management in Paperless-ngx involves using REST API endpoints to upload, search, tag, and bulk edit files. It requires curl and jq for scripting, token-based authentication, and environment configuration.
Yes, you can bulk tag and update metadata for documents in a private archive. Provided scripts like bulk-api.sh and tag helpers execute batch operations to apply tags, correspondents, and document types across large libraries.
Yes, you need curl and jq to interact with the Paperless-ngx API for uploads and searches. Curl handles the HTTP requests to the endpoints, while jq parses the JSON responses returned by the REST API.
The best way to search a self-hosted document archive by content and tags is through REST API filtering. You can retrieve documents by full-text content, tags, correspondent, and date using API queries parsed with jq.
OCR works automatically when uploading documents to a Paperless-ngx instance via the API. The self-hosted server processes the uploaded files to extract text, enabling full-text search and metadata-driven management without manual intervention.
Limitations of managing large document libraries through the Paperless-ngx API include relying on token-based authentication and environment configuration. Bulk operations depend on script orchestration, and you must ensure your self-hosted instance handles the API load.
damacusSearch Paperless-ngx documents via REST API with text, tag, and correspondent filters.
HyunjunJeonSearch arXiv and Semantic Scholar for scholarly articles by keywords, author, category, or boolean syntax.
jeremylongshoreGenerate backup configurations and setup scripts for databases and applications.
ricableStore embeddings and metadata for semantic document retrieval.
