Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. **First action for any "get me this paper" request:** `python3 <skill-path>/scripts/fetch_paper.py <DOI|arXiv-ID|PMID>` — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction (Nature/APS/AIP/IOP/Cambridge) → authorized institutional publisher → LibGen and saves the paper, metadata, and a resumable manifest under `papers/{slug}/`. Rea
Passed 18 of 20 test cases with the skill, and 11 of 20 without it.
and 9 more in the full report
8 fixed12 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I only have keyword queries like 'dark matter direct detection' and want to know which API to pick. Which reference document guides API selection by academic discipline?
| Checked | Without skill | With skill |
|---|---|---|
| Directs to reference/decision-tree.md for discipline-based API selection. | Missed | Passed |
The instructions your model reads when the skill loads.
Nested swiss-knife reference. A modular skill: try the bundled script first, then load specific reference files only when you need to escape it.
For 80% of "get me this paper" requests, the bundled script is the right answer. It walks the open-access ladder, falls back automatically, and writes a manifest the next session can resume from.
# Fetch by any identifier
python3 <skill-path>/scripts/fetch_paper.py 10.1103/PhysRevLett.125.015001
python3 <skill-path>/scripts/fetch_paper.py arXiv:2301.00001
python3 <skill-path>/scripts/fetch_paper.py PMID:12345678
# Batch (one identifier per line in the file)
python3 <skill-path>/scripts/fetch_paper.py --batch dois.txt --out papers/
# Resolve metadata only (no PDF download)
python3 <skill-path>/scripts/fetch_paper.py 10.1038/nature12373 --dry-run
# Skip LibGen (e.g. legal-sensitive environment)
python3 <skill-path>/scripts/fetch_paper.py <id> --no-libgen
Output layout (idempotent — re-runs skip entries with status: ok):
papers/{first-author-year-firstword}/
├── paper.pdf | paper.md # full-text artifact
├── metadata.json # CrossRef-normalized
└── manifest.json # {status, tier, source, ts, doi}
Tier ladder (script stops at first hit):
| Tier | Source | Best for |
|---|
test cases passed, vs 11 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.