Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ar9av/literature-review-agent
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to flag hallucinated citations, build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the or
Passed 13 of 18 test cases with the skill, and 6 of 18 without it.
and 8 more in the full report
11 fixed8 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/18/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When executing Phase 2 sequential citation verification using unauthenticated requests to the Semantic Scholar REST API, what maximum request frequency must be maintained?
| Checked | Without skill | With skill |
|---|---|---|
| Throttles unauthenticated live API calls to 1 request per second. | Missed | Passed |
The instructions your model reads when the skill loads.
Faithful implementation of the Hybrid Literature Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, §4 Step 3, App. D.3, App. F.1 p.46).
Cost: ~20–30 LLM calls. This is one of the two longest steps (the other is plotting). Wall-time floor is set by Semantic Scholar's 1 QPS verification limit.
workspace/outline.json — specifically intro_related_work_plan with the
Introduction search directions and the 2-4 Related Work methodology
clustersworkspace/inputs/conference_guidelines.md — used to derive cutoff_dateworkspace/inputs/idea.md, workspace/inputs/experimental_log.md — for
framing the Intro and grounding the Related Work positioningworkspace/citation_pool.json — verified Semantic Scholar metadata for
every paper that survived verificationworkspace/refs.bib — BibTeX file generated from the verified poolworkspace/drafts/intro_relwork.tex — drafted Introduction and Related
Work sections, written into the template, with the rest of the template
preserved verbatimPHASE 1 — Parallel Candidate Discovery
For each search direction in introduction_strategy.search_directions:
For each limitation_search_query in each related_work cluster:
- Use the host's web search tool to discover up to ~10 candidate papers.
- Run up to 10 discovery queries in parallel (host-permitting).
- Collect (title, snippet, url) tuples — no verification yet.
→ PRE-DEDUP before Phase 2 (see Step 1.5 below)
PHASE 2 — Sequential Citation Verification (1 QPS, with cache)
For each candidate (after pre-dedup), sequentially:
test cases passed, vs 6 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.