From research-skills
Read arXiv paper source and add BibTeX entries via ADS API. Use for research that requires reading full paper text and managing citations. Triggers on: "read paper", "cite", "add to bibliography", "bibtex", "ADS", "arXiv", "find paper", "add citation", or any request to read scientific papers or manage references.
npx claudepluginhub cailmdaley/skills --plugin research-skillsThis skill uses the workspace's default tool permissions.
Read scientific papers and manage citations. Two capabilities:
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
Read scientific papers and manage citations. Two capabilities:
Download arXiv LaTeX source to read full paper text:
# Download source (replace ID as needed)
curl -L -o /tmp/2503.19441.tar.gz "https://arxiv.org/src/2503.19441"
# Extract
mkdir -p /tmp/2503.19441 && cd /tmp/2503.19441 && tar -xzf /tmp/2503.19441.tar.gz
# Find the main tex file
ls *.tex
Available after extraction:
Before using citation features, verify $ADS_API_TOKEN is set:
echo $ADS_API_TOKEN
If missing, direct the user to create one at https://ui.adsabs.harvard.edu/user/settings/token and export it. Do not proceed with ADS API calls until the token is available.
When adding a paper to the bibliography:
Web search for the paper using description + "arxiv"
YYMM.NNNNNQuery ADS API to get bibcode using arXiv ID
curl -H "Authorization: Bearer $ADS_API_TOKEN" \
'https://api.adsabs.harvard.edu/v1/search/query?q=arXiv:YYMM.NNNNN&fl=bibcode'
Fetch BibTeX entry with abstract from ADS
curl -H "Authorization: Bearer $ADS_API_TOKEN" \
'https://api.adsabs.harvard.edu/v1/export/bibtexabs/{bibcode}'
Parse BibTeX to extract author names and year:
author = {...} field for last namesyear = YYYY field for publication yearfirstauthor{YY} (e.g., asgari17)firstauthor.secondauthor{YY} (e.g., schneider.kilbinger12)firstauthor.etal{YY} (e.g., wright.etal25)Replace citation key in BibTeX entry
Append to bibliography file
.bib fileReport success
Examples from BibTeX parsing:
author = {{Wright}, Angus H. and {Stölzner}, Benjamin and ...} + year = 2025 → wright.etal25author = {{Schneider}, Peter and {Kilbinger}, Martin} + year = 2012 → schneider.kilbinger12author = {{Asgari}, Marika} + year = 2017 → asgari17bibtexabs endpoint (not bibtex) to include abstractsauthor = {{LastName}, FirstName and {LastName}, FirstName ...}