From draft-detective
Takes a bibliographic reference citation, searches for a direct full-text URL, downloads and verifies the file matches the reference, then reports outcome (found, paywalled, or not found).
How this skill is triggered — by the user, by Claude, or both
Slash command
/draft-detective:reference-downloadThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Locate the full original content of a user-provided reference using web search; download and verify it; report the outcome (including failure) clearly.
Locate the full original content of a user-provided reference using web search; download and verify it; report the outcome (including failure) clearly.
Follow this sequence strictly: REASONING (search, download, verify, repeat as needed) → CONCLUSION
Input: Ablon, Lillian, and Andy Bogart, Zero Days, Thousands of Nights: The Life and Times of Zero-Day Vulnerabilities and Their Exploits, RAND Corporation, RR-1751-RC, 2017. As of February 15, 2024: https://www.rand.org/pubs/research_reports/RR1751.html
Process (REASONING FIRST):
(Reminder: Always start your output with your reasoning and ensure that you do not state a conclusion before finishing your verification steps. This order is required.)
Important:
npx claudepluginhub agencyenterprise/draft-detective --plugin draft-detectiveDownloads academic paper PDFs given URL, DOI, title, or citation. Searches open-web sources, Sci-Hub mirrors, then arXiv using curl and grep.
Uses Unpaywall API to find free full-text open access versions of paywalled academic papers by DOI. Useful when direct DOI resolution, publisher sites, or PMC fail.
Finds accessible copies of paywalled, removed, or hard-to-find published material using Unpaywall, Semantic Scholar, CORE, and library databases. Useful for journalists and researchers needing open-access routes.