Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xuzhougeng/literature-review
Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.
Passed 4 of 12 test cases with the skill, and 4 of 12 without it.
1 fixed6 passed either way13 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
What is the original paper for the transformer architecture in deep learning? I just need the primary citation to reference in a grant application.
| Checked | Without skill | With skill |
|---|---|---|
| The response cites the original primary research paper rather than secondary review articles. | Passed | Passed |
| The citation includes a direct hyperlinked DOI URL. | Missed | Passed |
The instructions your model reads when the skill loads.
Work through six steps: scope, sweep, expand, verify, write, lint. The failure modes this skill exists to prevent are all silent — a fabricated DOI, a retracted headline result, a reading list dressed up as a synthesis — so each step below names the check that catches it.
Different phrasings want different deliverables:
| Request shape | Deliverable |
|---|---|
| "the paper for X" / "the original/seminal…" | one or two primary citations |
| "what's the evidence on X" | thematic synthesis |
| "compare A and B" | trade-off analysis ending in a recommendation |
| "where are the gaps" | named gaps, each anchored to what establishes it |
A vague lay query gets the scope a domain expert would default to, stated explicitly ("taking this as human RCT evidence; animal work is separate"). Clarify with the user only when the answer would change what you retrieve.
Never write from recall. Recall chooses the framing and the search terms;
retrieval supplies every citation. Start with search_openalex /
crossref_lookup from this skill's kernel.py, a PubMed query, or any
literature connector advertised in the session (search_skills with
{"query":"literature PubMed Semantic Scholar bioRxiv ClinicalTrials"} finds
installed guidance; load matches with use_skill).
For a named-paper lookup, the target is the highly cited primary publication that later work cites — not a review of it, not a news piece. Even when you know the paper cold, resolving its DOI is one tool call; skipping it turns a citation into a claim about a citation.
Keyword sweeps miss two things systematically: the foundational paper a field builds on, and the newest work that extends or contests your top hits. Take
test cases passed, vs 4 / 12 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.