- Home
- Skills
- Research & Analysis
- Paper Metadata
Paper Metadata
Batch-extract original titles, authors, affiliations, abstracts, and keywords from PDF/Word papers into JSONL or CSV.
Free
Works with the AI Agents you already use
Paper Metadata
Example session with this skill installed
Extract original metadata from a local folder of papers into CSV and JSONL. Report missing fields, failed files, and pending work.
- Read your context and instructions
- Compiled the paper metadata
Structured per-paper metadata with ok, needs_review, error, and pending counts, plus export paths.
Connects securely to your tools. The creator never sees your data.
About this skill
Extract original paper metadata using the current assistant session and local Python helpers for PDF/Word reading, checkpoints, validation, and JSONL/CSV export. English instructions, help text, and optional API-mode prompts are included. Default use needs no separate model API key. Commercial internal use and client outputs are permitted under LICENSE.txt; redistribution, resale, or third-party product/service embedding of the Skill itself requires separate written authorization.
Scanned PDFs need separate OCR. Initial page limits may omit abstracts. Structural validation does not guarantee accurate extraction. The host assistant reads excerpts and consumes its normal usage; the workflow is not fully offline. Optional API mode incurs provider charges and is never required for default use.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 3 days ago
- Free with an Agensi account
Requires
Permissions
File Scopes
Default helpers read documents locally without model API calls; excerpts are read by the host assistant. Optional legacy API mode requires explicit user selection and separately configured credentials. No real keys or papers are included.