wu-yc/labclaw/tooluniverse-literature-deep-research

Claude Code and agent skill by wu-yc/labclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Conduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves official IDs (Ensembl/UniProt), synonyms, naming collisions, and gathers expression/pathway context before literature search. Default deliverable is a report file; for single factoid questions, uses a fast verification mode and may include an inline answer. Use when users need thorough literature reviews, target profiles, or to verify specific claims from the literature.

Install

npx vskill@latest install wu-yc/labclaw/tooluniverse-literature-deep-research

SKILL.md

Literature Deep Research Strategy (Enhanced)

A systematic approach to comprehensive literature research that starts with target disambiguation to prevent missing details, uses evidence grading to separate signal from noise, and produces a content-focused report with mandatory completeness sections.

KEY PRINCIPLES:

  1. Target disambiguation FIRST - Resolve IDs, synonyms, naming collisions before literature search
  2. Right-size the deliverable - Use Factoid / Verification Mode for single, answerable questions; use full report mode for “deep research”
  3. Report-first output - Default deliverable is a report file; an inline answer is allowed (and recommended) for Factoid / Verification Mode
  4. Evidence grading - Grade every claim by evidence strength (mechanistic paper vs screen hit vs review vs text-mined)
  5. Mandatory completeness - All checklist sections must exist, even if "unknown/limited evidence"
  6. Source attribution - Every piece of information traceable to database/tool
  7. English-first queries - Always use English terms for literature searches and tool calls, even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language

Workflow Overview

User Query
  ↓
Phase 0: CLARIFY + MODE SELECT (factoid vs deep report)
  ↓
Phase 1: TARGET DISAMBIGUATION + PROFILE (default ON for biological targets)
  ├─ Resolve official IDs (Ensembl, UniProt, HGNC)
  ├─ Gather synonyms/aliases + known naming collisions
  ├─ Get protein length, isoforms, domain architecture
  ├─ Get subcellular location, expression, GO terms, pathways
  └─ Output: Target Profile section + Collision-aware search plan
  ↓
Phase 2: LITERATURE SEARCH (internal methodology, not shown)
  ├─ High-precision seed queries (build mechanistic core)
  ├─ Citation network expansion from seeds
  ├─ Collision-filtered broader queries
  └─ Theme clustering + evidence grading
  ↓
Phase 3: REPORT SYNTHESIS
  ├─ Progressive writing to [topic]_report.md
  ├─ Mandatory completeness checklist validation
  └─ Biological model + testable hypotheses
  ↓
Optional: methods_appendix.md (only if user requests)

Phase 0: Initial Clarification

Mandatory Questions
  1. Target type: Is this a biological target (gene/protein), a general topic, or a disease?
  2. Scope: Is this a single factoid to verify (“Which antibiotic?”, “Which strain?”, “Which year?”) or a comprehensive/deep review?
  3. Known aliases: Any specific gene symbols or protein names you use?
  4. Constraints: Open access only? Include preprints? Specific organisms?
  5. Methods appendix: Do you want methodology details in a separate file?
Mode Selection (CRITICAL)

Pick exactly one mode based on the user’s intent and the question structure:

  1. Factoid / Verification Mode (single concrete question; answer should be a short phrase/sentence)
  2. Mini-review Mode (narrow topic; 1–3 pages of synthesis)
  3. Full Deep-Research Mode (use the full template + completeness checklist)

Heuristic:

  • If the user asks “X has been evolved to be resistant to which antibiotic?” → Factoid / Verification Mode
  • If the user asks “What does the literature say about X?” → Full Deep-Research Mode
Factoid / Verification Mode (Fast Path)

Goal: Provide a correct, source-verified single answer, with minimal but explicit evidence attribution.

Deliverables (still file-backed):

  1. [topic]_factcheck_report.md (≤ 1 page)
  2. [topic]_bibliography.json (+ CSV) containing the key paper(s)

Fact-check report template:

markdown
# [TOPIC]: Fact-check Report
 
*Generated: [Date]*
*Evidence cutoff: [Date]*
 
## Question
[User question]
 
## Answer
**[One-sentence answer]** [Evidence: ★★★/★★☆/★☆☆/☆☆☆]
 
## Source(s)
-[Primary paper citation: journal/year/PMID/DOI as available]
 
## Verification Notes
-[1–3 bullets: where in the paper the statement appears (Abstract/Results/Methods), and any key constraints]
 
## Limitations
-[If full text not available, or if only review evidence exists]

Required verification behavior:

  • Prefer ToolUniverse literature tools (Europe PMC / PubMed / PMC / Semantic Scholar) over general web browsing.
  • Use full-text snippet verification when possible (Europe PMC auto-snippet tier is ideal).
  • Avoid adding extra claims (e.g., “not X”) unless the paper explicitly supports them.

Suggested tool pattern:

  • EuropePMC_search_articles(query=..., extract_terms_from_fulltext=[...]) to pull OA full-text snippets for the key terms.
  • If OA snippets unavailable: fall back to PMC_search_papers (if in PMC) or SemanticScholar_search_papers → SemanticScholar_get_pdf_snippets.

Evidence grading (factoid):

  • If the statement is explicitly made in a primary experimental paper (Results/Methods/Abstract): label T1 (★★★).
  • If it’s only in a review: label T4 (☆☆☆) and try to locate the primary source.
Detect Target Type
Query PatternTypeAction
Gene symbol (EGFR, TP53, ATP6V1A)Biological targetPhase 1 required
Protein name ("V-ATPase", "kinase")Biological targetPhase 1 required
UniProt ID (P00533, Q93050)Biological targetPhase 1 required
Disease, pathway, methodGeneral topicPhase 1 optional
"Literature on X"Depends on XAssess X

Phase 1: Target Disambiguation + Profile (Default ON)

CRITICAL: This phase prevents "missing target details" when literature is sparse or noisy.

1.1 Resolve Official Identifiers

Use these tools to establish canonical identity:

UniProt_search → Get UniProt accession for human protein
UniProt_get_entry_by_accession → Full entry with cross-references
UniProt_id_mapping → Map between ID types
ensembl_lookup_gene → Ensembl gene ID, biotype
MyGene_get_gene_annotation → NCBI Gene ID, aliases, summary

Output for report:

markdown
## Target Identity
 
| Identifier | Value | Source |
|------------|-------|--------|
| Official Symbol | ATP6V1A | HGNC |
| UniProt | P38606 | UniProt |
| Ensembl Gene | ENSG00000114573 | Ensembl |
| NCBI Gene ID | 523 | NCBI |
| ChEMBL Target | CHEMBL2364682 | ChEMBL |
 
**Full Name**: V-type proton ATPase catalytic subunit A
**Synonyms/Aliases**: ATP6A1, VPP2, Vma1, VA68
1.2 Identify Naming Collisions

CRITICAL: Many gene names have collisions. Examples:

  • TRAG: T-cell regulatory gene vs bacterial TraG conjugation protein
  • WDR7-7: Could match gene WDR7 vs lncRNA
  • JAK: Janus kinase vs Just Another Kinase
  • CAT: Catalase vs chloramphenicol acetyltransferase

Detection strategy:

  1. Search PubMed for "[SYMBOL]"[Title] - review first 20 titles
  2. If >20% off-topic, identify collision terms
  3. Build negative filter: NOT [collision_term1] NOT [collision_term2]

Output for report:

markdown
### Known Naming Collisions
 
-Symbol "ATP6V1A" is unambiguous (no major collisions detected)
-Related but distinct: ATP6V0A1-4 (V0 subunits vs V1 subunits)
-Search filter applied: Include "vacuolar" OR "V-ATPase", exclude "V0 domain" when V1-specific
1.3 Protein Architecture & Domains

Use annotation tools (not literature):

InterPro_get_protein_domains → Domain architecture
UniProt_get_ptm_processing_by_accession → PTMs, active sites
proteins_api_get_protein → Additional protein features

Output for report:

markdown
### Protein Architecture
 
| Domain | Position | InterPro ID | Function |
|--------|----------|-------------|----------|
| V-ATPase A subunit, N-terminal | 1-90 | IPR022879 | ATP binding |
| V-ATPase A subunit, catalytic | 91-490 | IPR005725 | Catalysis |
| V-ATPase A subunit, C-terminal | 491-617 | IPR022878 | Complex assembly |
 
**Length**: 617 aa | **Isoforms**: 2 (canonical P38606-1, variant P38606-2 missing aa 1-45)
**Active sites**: Lys-168 (ATP binding), Glu-261 (catalytic)
 
*Sources: InterPro, UniProt*
1.4 Subcellular Location
HPA_get_subcellular_location → Human Protein Atlas localization
UniProt_get_subcellular_location_by_accession → UniProt annotation

Output for report:

markdown
### Subcellular Localization
 
| Location | Confidence | Source |
|----------|------------|--------|
| Lysosome membrane | High | HPA + UniProt |
| Endosome membrane | High | UniProt |
| Golgi apparatus | Medium | HPA |
| Plasma membrane (subset) | Low | Literature |
 
**Primary location**: Lysosomal/endosomal membranes (vacuolar ATPase complex)
*Sources: Human Protein Atlas, UniProt*
1.5 Baseline Expression
GTEx_get_median_gene_expression → Tissue expression (TPM)
HPA_get_rna_expression_by_source → HPA expression data

Output for report:

markdown
### Baseline Tissue Expression
 
| Tissue | Expression (TPM) | Specificity |
|--------|------------------|-------------|
| Kidney cortex | 145.3 | Elevated |
| Liver | 98.7 | Medium |
| Brain - Cerebellum | 87.2 | Medium |
| Lung | 76.4 | Medium |
| Ubiquitous baseline | ~50 | Broad |
 
**Tissue Specificity**: Low (τ = 0.28) - broadly expressed housekeeping gene
*Source: GTEx v8*
1.6 GO Terms & Pathway Placement
GO_get_annotations_for_gene → GO annotations
Reactome_map_uniprot_to_pathways → Reactome pathways
kegg_get_gene_info → KEGG pathways
OpenTargets_get_target_gene_ontology_by_ensemblID → Open Targets GO

Output for report:

markdown
### Functional Annotations (GO)
 
**Molecular Function**:
-ATP hydrolysis activity (GO:0016887) [Evidence: IDA]
-Proton-transporting ATPase activity (GO:0046961) [Evidence: IDA]
 
**Biological Process**:
-Lysosomal acidification (GO:0007041) [Evidence: IMP]
-Autophagy (GO:0006914) [Evidence: IMP]
-Bone resorption (GO:0045453) [Evidence: IMP]
 
**Cellular Component**:
-Vacuolar proton-transporting V-type ATPase, V1 domain (GO:0000221) [Evidence: IDA]
 
### Pathway Involvement
 
| Pathway | Database | Significance |
|---------|----------|--------------|
| Lysosome | KEGG hsa04142 | Core component |
| Phagosome | KEGG hsa04145 | Acidification |
| Autophagy - animal | Reactome R-HSA-9612973 | mTORC1 regulation |
 
*Sources: GO Consortium, Reactome, KEGG*

Phase 2: Literature Search (Internal Methodology)

NOTE: This methodology is kept internal. The report shows findings, not process.

2.1 Query Strategy: Collision-Aware Synonym Plan
Step 1: High-Precision Seed Queries (Build Mechanistic Core)
Query 1: "[GENE_SYMBOL]"[Title] AND (mechanism OR function OR structure)
Query 2: "[FULL_PROTEIN_NAME]"[Title] 
Query 3: "[UNIPROT_ID]" (catches supplementary materials)

Purpose: Get 15-30 high-confidence, mechanistic papers that are definitely on-target.

Step 2: Citation Network Expansion (Especially for Sparse Targets)

Once you have 5-15 core PMIDs:

PubMed_get_cited_by → Papers citing each seed
PubMed_get_related → Computationally related papers  
EuropePMC_get_citations → Alternative citation source
EuropePMC_get_references → Backward citations from seeds

Citation-network first option: For older targets with deprecated terminology, citation expansion often outperforms keyword searching.

Step 3: Collision-Filtered Broader Queries
Broader query: "[GENE_SYMBOL]" AND ([pathway1] OR [pathway2] OR [function])
Apply collision filter: NOT [collision_term1] NOT [collision_term2]

Example for bacterial TraG collision:

"TRAG" AND (T-cell OR immune OR cancer) NOT plasmid NOT conjugation NOT bacterial
2.2 Database Tools

Literature Search (use all relevant):

  • PubMed_search_articles - Primary biomedical
  • PMC_search_papers - Full-text
  • EuropePMC_search_articles - European coverage
  • openalex_literature_search - Broad academic
  • Crossref_search_works - DOI registry
  • SemanticScholar_search_papers - AI-ranked
  • BioRxiv_search_preprints / MedRxiv_search_preprints - Preprints

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
880
Repository forks
123
7-day trend score
34

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 26 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/wu-yc/labclaw/tooluniverse-literature-deep-research/badge)](https://verified-skill.com/skills/wu-yc/labclaw/tooluniverse-literature-deep-research)

Something wrong with this skill or its page? Tell us.