skills.rest
Rimagination
RimaginationCOMMUNITY
Explore all skills by this author →
GitHub

scansci-sort

Triage academic paper lists into open-access, repository, and institutional download queues.

819|83|Updated May 2, 2026
Search Tags:#open access#batch download#source classification#reference list#doi validation#literature triage#Academic papers
One-click install
npx skills add https://github.com/Rimagination/scansci-pdf --skill scansci-sort
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scansci-sort
Source: https://github.com/Rimagination/scansci-pdf/tree/main/skills/scansci-sort
Command: npx skills add https://github.com/Rimagination/scansci-pdf --skill scansci-sort

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Large literature lists are expensive to download blindly: some papers are open access, some sit in repositories, and others require institutional access. This Skill classifies a big reference list into source buckets before any downloading happens, so retrieval runs only against the right channels.

Core Features & Use Cases

  • Identifier Hygiene: Normalizes, deduplicates, and validates DOIs and other identifiers before probing any source.
  • Source Triage: Classifies entries into open-access, repository, institutional, and user-selected source queues, checking free channels first.
  • Accurate Hit Classification: Distinguishes hit, miss, turnstile, and blocked outcomes instead of treating every HTTP 200 as a full-text success.
  • Use Case: Given a spreadsheet of 1,000 references, produce bucket files and a report that route each bucket to the appropriate download lane without fetching a single PDF during triage.

Quick Start

Sort my reference list into open-access, repository, and institutional buckets and give me a report with the recommended download route for each bucket.

Frequently Asked Questions about scansci-sort

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I sort a large reference list by access type before downloading?▼

Feed the list to the triage workflow, which normalizes and validates identifiers, then probes open-access and repository sources first. It outputs bucket files per access channel plus a report with a recommended download route for each bucket.

What is the best way to prepare a thousand-paper literature list for batch download?▼

Run classification separately from retrieval: deduplicate and validate DOIs, then bucket entries into open-access, repository, and institutional queues. This avoids wasting requests on paywalled sources and lets each bucket use its optimal download lane.

Does triage download the papers while classifying them?▼

No. Classification only probes source availability and never downloads the input list. Retrieval is a separate step that consumes the bucket files produced by triage.

Why does an HTTP 200 response not count as a full-text hit?▼

Publisher pages often return 200 for landing pages, CAPTCHA walls, or Cloudflare challenges rather than the actual PDF. The workflow distinguishes hit, miss, turnstile, and blocked statuses so only genuine full-text responses count as hits.

What input formats does reference list triage accept?▼

The pipeline accepts DOI lists, BibTeX or APA reference lists, and spreadsheet inputs such as xlsx or csv. Identifiers are normalized and deduplicated, and missing DOIs can be completed before source probing begins.

Related Skills

Explore More Education & Research Skills→
Estrella-231Estrella-231

citation-management

Generate validated BibTeX citations from DOIs, PMIDs, and arXiv IDs.

Community
Advanced
jdidionjdidion

/cu:request-paper

Route paywalled paper requests through an institutional library service.

Community
Advanced
hanuminhanumin

crossref-mcp

Verify DOIs and retrieve metadata and citations via the Crossref API.

Community
Intermediate
Mr-Fang-VLSIMr-Fang-VLSI
8

eda-paper-fetch

Fetch primary-source paper metadata and generate local manifests and download queues.

Community
Advanced