Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Systematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.
KEY PRINCIPLES: (1) Disambiguate first (2) Right-size deliverable (3) Grade every claim T1-T4 (4) All sections mandatory even if "limited evidence" (5) Source attribution for every claim (6) English-first queries, respond in user's language (7) Report = deliverable, not search log
Search PubMed/EuropePMC FIRST before reasoning. A published paper beats memory.
Factoid search strategy:
EuropePMC_search_articles(query="term1 term2 term3", limit=5)When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.
Phase 0: Clarify + Mode Select → Phase 1: Disambiguate + Profile → Phase 2: Literature Search → Phase 3: Report
| Mode | When | Deliverable |
|---|---|---|
| Factoid | Single concrete question | 1-page fact-check report + bibliography |
| Mini-review | Narrow topic | 1-3 page narrative |
| Full Deep-Research | Comprehensive overview | 15-section report + bibliography |
# [TOPIC]: Fact-check Report
## Question / ## Answer (with evidence rating) / ## Source(s) / ## Verification Notes / ## Limitations
| Pattern | Domain | Action |
|---|---|---|
| Gene/protein symbol | Biological target | Full bio disambiguation |
| Drug name | Drug | Drug disambiguation (1.5) |
| Disease name | Disease | Disease disambiguation (1.6) |
| CS/ML topic | General academic | Skip bio tools, literature-only |
| Cross-domain | Interdisciplinary | Resolve each entity in its domain |
tooluniverse-target-researchtooluniverse-drug-researchtooluniverse-disease-researchUse this skill for literature synthesis. Use specialized skills for entity profiling. For max depth, run both.
UniProt_search → UniProt_get_entry_by_accession → UniProt_id_mapping
ensembl_lookup_gene → MyGene_get_gene_annotation
Check first 20 results. If >20% off-topic, build negative filter: NOT [collision1] NOT [collision2].
Gene family: "ADAR" NOT "ADAR2" NOT "ADARB1". Cross-domain: add context terms.
InterPro_get_protein_domains, UniProt_get_ptm_processing_by_accession, HPA_get_subcellular_location,
GTEx_get_median_gene_expression, GO_get_annotations_for_gene, Reactome_map_uniprot_to_pathways,
STRING_get_protein_interactions, intact_get_interactions, OpenTargets_get_target_tractability_by_ensemblID
GPCR targets: delegate to tooluniverse-target-research.
Identity: OpenTargets_get_drug_chembId_by_generic_name, ChEMBL_get_drug, PubChem_get_CID_by_compound_name, drugbank_get_drug_basic_info_by_drug_name_or_id
Targets: ChEMBL_get_drug_mechanisms, OpenTargets_get_associated_targets_by_drug_chemblId, DGIdb_get_drug_gene_interactions
Safety: OpenTargets_get_drug_adverse_events_by_chemblId, OpenTargets_get_drug_indications_by_chemblId, search_clinical_trials
OpenTargets disease search → EFO/MONDO IDs
DisGeNET_get_disease_genes, DisGeNET_search_disease
CTD_get_disease_chemicals
Resolve both entities, then cross-reference via CTD_get_chemical_gene_interactions, CTD_get_chemical_diseases, OpenTargets drug-target/drug-disease tools. Intersect shared targets/pathways.
Non-bio: skip bio tools, use ArXiv/DBLP/OSF. Cross-domain: resolve bio entities with 1.1-1.3, search CS/general in parallel, merge and cross-reference.
Methodology stays internal. Report shows findings, not process.
Step 1: Seeds (15-30 core papers): domain-specific title searches with date/sort filters.
Step 2: Citation expansion: PubMed_get_cited_by, EuropePMC_get_citations/references, PubMed_get_related, SemanticScholar_get_recommendations, OpenCitations_get_citations
Step 3: Collision-filtered broader queries: "[TERM]" AND ([context]) NOT [collision]
Run the core multi-field set on every review (catches what any single index misses), then add the domain rows that match the subject. Don't fire every source blindly — 6–10 well-chosen indexes beat 20 noisy ones.
ALWAYS run (core, all disciplines): PubMed_search_articles, EuropePMC_search_articles, openalex_search_works (query param search/query) or openalex_literature_search (query param search_keywords) — pick one and match its param; mixing them silently returns off-topic results — and SemanticScholar_search_papers
Then add by domain:
| Domain | Add these | Notes |
|---|---|---|
| Biomedical / clinical | PMC_search_papers (full text), PubTator3_LiteratureSearch (entity & relations: queries), PubMed_Guidelines_Search (clinical guidelines) | PubTator normalizes gene/drug/disease entities |
| Biology (ecology/evolution/plant) | EuropePMC as PRIMARY + OpenAlex | PubMed returns 0–1 for non-clinical biology |
| CS / ML / AI | ArXiv_search_papers, DBLP_search_publications | arXiv + CS bibliography |
| Physics / HEP / astro | InspireHEP_search_papers | 1.6M+ particle/astro records |
| Broad / hard-to-find / OA | Crossref_search_works, CORE_search_papers, DOAJ_search_articles, Fatcat_search_scholar | DOI registry + OA aggregators + Internet Archive Scholar |
| Regional / EU-funded | OpenAIRE_search_publications, HAL_search_archive | EU open science + French national archive |
| Datasets / software / outputs | Figshare_search_articles, Zenodo_search_records | Citable DOIs for data & code |
| Preprints (latest) | EuropePMC_search_articles(source='PPR'), OSF_search_preprints, BioRxiv_get_preprint/MedRxiv_get_preprint (DOI lookup) | bioRxiv/medRxiv/PsyArXiv etc. |
Multi-source: advanced_literature_search_agent (12+ DBs; needs Azure key -- fallback: query the core set individually).
Citation impact: iCite_search_publications (RCR/APT), iCite_get_publications (by PMID), scite_get_tallies (support/contradict). PubMed-only; for CS use SemanticScholar.
A domain-specific index returning 0 (e.g. ArXiv on a pure-clinical topic) is normal — only worry if the whole core set is empty.
Full-text: see FULLTEXT_STRATEGY.md for three-tier strategy.
CRITICAL: PubMed returns 0 for ~30% of valid queries. Always retry with EuropePMC when PubMed returns empty. This is not optional.
Retry once -> fallback tool. Key fallbacks: PubMed_get_cited_by -> EuropePMC_get_citations -> OpenCitations. OA: Unpaywall if configured, else Europe PMC/PMC/OpenAlex flags.
| Tier | Label | Bio Example | CS/ML Example |
|---|---|---|---|
| T1 | Mechanistic | CRISPR KO + rescue, RCT | Formal proof, controlled ablation |
| T2 | Functional | siRNA knockdown phenotype | Benchmark with baselines |
| T3 | Association | GWAS, screen hit | Observational, case study |
| T4 | Mention | Review article | Survey, workshop abstract |
Inline: Target X regulates Y [T1: PMID:12345678]. Per theme: summarize evidence distribution.
| File | Mode |
|---|---|
[topic]_report.md | Full |
[topic]_factcheck_report.md | Factoid |
[topic]_bibliography.json + .csv | All |
Progressive update: create report with all section headers immediately. Fill after each phase. Write Executive Summary LAST.
Use 15-section template from REPORT_TEMPLATE.md. Domain adaptations: bio (architecture/expression/GO/disease), drug (properties/MOA/PK/safety), disease (epi/patho/genes/treatments), general (history/theories/evidence/applications).
Brief progress updates only: "Resolving identifiers...", "Building paper set...", "Grading evidence..." Do NOT expose: raw tool outputs, dedup counts, search round details.
TOOL_NAMES_REFERENCE.md -- 123 tools with parametersREPORT_TEMPLATE.md -- template, domain adaptations, bibliography, completeness checklistFULLTEXT_STRATEGY.md -- three-tier full-text verificationWORKFLOW.md -- compact cheat-sheetEXAMPLES.md -- worked examplesまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
日本語の概要は準備中です。原文の説明を表示しています。
ADMET property prediction for drug candidates. Full pharmacokinetic panel (Caco-2, PPB, clearance, CYP), toxicity (hERG, AMES, DILI), drug-likeness (Lipinski, QED), using RDKit descriptors and TDC models.
日本語の概要は準備中です。原文の説明を表示しています。
Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
日本語の概要は準備中です。原文の説明を表示しています。
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
日本語の概要は準備中です。原文の説明を表示しています。
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
日本語の概要は準備中です。原文の説明を表示しています。