[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DASSMWA3HJ04FEVV5NTH47":3,"skill-same:01M6DASSMWA3HJ04FEVV5NTH47":95},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DASSMWA3HJ04FEVV5NTH47","tooluniverse-literature-deep-research",null,"Comprehensive literature deep research across any academic domain using 120+ ToolUniverse tools. Conducts subject disambiguation, systematic literature search with citation network expansion, evidence grading (T1-T4), and structured theme extraction. Produces detailed reports with mandatory completeness checklists, integrated models, and testable hypotheses. Use when users need thorough literature reviews, target\u002Fdrug\u002Fdisease profiles, topic deep-dives, claim verification, or systematic evidence synthesis. Supports biomedical (genes, proteins, drugs, diseases), computer science, social science, and general academic topics. For single factoid questions, uses a fast verification mode with inline answer.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"tooluniverse literature deep research","deep research","deep","research","social","systematic","proteins","biomedical","grading","across","domain","claim","evidence synthesis","reports","evidence","computer","Tools","network","search","verification","2026-11-10 10:12:30",false,"---\nname: tooluniverse-literature-deep-research\ndescription: Comprehensive literature deep research across any academic domain using 120+ ToolUniverse tools. Conducts subject disambiguation, systematic literature search with citation network expansion, evidence grading (T1-T4), and structured theme extraction. Produces detailed reports with mandatory completeness checklists, integrated models, and testable hypotheses. Use when users need thorough literature reviews, target\u002Fdrug\u002Fdisease profiles, topic deep-dives, claim verification, or systematic evidence synthesis. Supports biomedical (genes, proteins, drugs, diseases), computer science, social science, and general academic topics. For single factoid questions, uses a fast verification mode with inline answer.\n---\n\n# Literature Deep Research\n\nSystematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.\n\n**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\n\n---\n\n## LOOK UP, DON'T GUESS\n\nSearch PubMed\u002FEuropePMC FIRST before reasoning. A published paper beats memory.\n\n**Factoid search strategy:**\n1. Extract KEY TERMS (most specific nouns\u002Fverbs)\n2. `EuropePMC_search_articles(query=\"term1 term2 term3\", limit=5)`\n3. No results -> BROADEN (remove most restrictive term)\n4. Too many -> NARROW (add specific terms)\n5. Answer usually in abstract of top results\n6. Failed query -> try DIFFERENT TERMS\u002Fsynonyms, don't repeat\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen 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.\n\n## Workflow\n\n```\nPhase 0: Clarify + Mode Select → Phase 1: Disambiguate + Profile → Phase 2: Literature Search → Phase 3: Report\n```\n\n---\n\n## Phase 0: Mode Selection\n\n| Mode | When | Deliverable |\n|------|------|-------------|\n| **Factoid** | Single concrete question | 1-page fact-check report + bibliography |\n| **Mini-review** | Narrow topic | 1-3 page narrative |\n| **Full Deep-Research** | Comprehensive overview | 15-section report + bibliography |\n\n### Factoid Mode (Fast Path)\n```markdown\n# [TOPIC]: Fact-check Report\n## Question \u002F ## Answer (with evidence rating) \u002F ## Source(s) \u002F ## Verification Notes \u002F ## Limitations\n```\n\n### Domain Detection\n\n| Pattern | Domain | Action |\n|---------|--------|--------|\n| Gene\u002Fprotein symbol | Biological target | Full bio disambiguation |\n| Drug name | Drug | Drug disambiguation (1.5) |\n| Disease name | Disease | Disease disambiguation (1.6) |\n| CS\u002FML topic | General academic | Skip bio tools, literature-only |\n| Cross-domain | Interdisciplinary | Resolve each entity in its domain |\n\n### Cross-Skill Delegation\n- Gene\u002Fprotein deep-dive: `tooluniverse-target-research`\n- Drug profile: `tooluniverse-drug-research`\n- Disease profile: `tooluniverse-disease-research`\n\nUse this skill for **literature synthesis**. Use specialized skills for **entity profiling**. For max depth, run both.\n\n---\n\n## Phase 1: Subject Disambiguation + Profile\n\n### 1.1 Biological Target Resolution\n```\nUniProt_search → UniProt_get_entry_by_accession → UniProt_id_mapping\nensembl_lookup_gene → MyGene_get_gene_annotation\n```\n\n### 1.2 Naming Collision Detection\nCheck first 20 results. If >20% off-topic, build negative filter: `NOT [collision1] NOT [collision2]`.\nGene family: `\"ADAR\" NOT \"ADAR2\" NOT \"ADARB1\"`. Cross-domain: add context terms.\n\n### 1.3 Baseline Profile (Bio Targets)\n```\nInterPro_get_protein_domains, UniProt_get_ptm_processing_by_accession, HPA_get_subcellular_location,\nGTEx_get_median_gene_expression, GO_get_annotations_for_gene, Reactome_map_uniprot_to_pathways,\nSTRING_get_protein_interactions, intact_get_interactions, OpenTargets_get_target_tractability_by_ensemblID\n```\nGPCR targets: delegate to `tooluniverse-target-research`.\n\n### 1.5 Drug Disambiguation\n**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`\n**Targets**: `ChEMBL_get_drug_mechanisms`, `OpenTargets_get_associated_targets_by_drug_chemblId`, `DGIdb_get_drug_gene_interactions`\n**Safety**: `OpenTargets_get_drug_adverse_events_by_chemblId`, `OpenTargets_get_drug_indications_by_chemblId`, `search_clinical_trials`\n\n### 1.6 Disease Disambiguation\n```\nOpenTargets disease search → EFO\u002FMONDO IDs\nDisGeNET_get_disease_genes, DisGeNET_search_disease\nCTD_get_disease_chemicals\n```\n\n### 1.7 Compound Queries (e.g., \"metformin in breast cancer\")\nResolve both entities, then cross-reference via CTD_get_chemical_gene_interactions, CTD_get_chemical_diseases, OpenTargets drug-target\u002Fdrug-disease tools. Intersect shared targets\u002Fpathways.\n\n### 1.8 General Academic \u002F 1.9 Interdisciplinary\nNon-bio: skip bio tools, use ArXiv\u002FDBLP\u002FOSF. Cross-domain: resolve bio entities with 1.1-1.3, search CS\u002Fgeneral in parallel, merge and cross-reference.\n\n---\n\n## Phase 2: Literature Search\n\n**Methodology stays internal. Report shows findings, not process.**\n\n### 2.1 Query Strategy\n**Step 1: Seeds** (15-30 core papers): domain-specific title searches with date\u002Fsort filters.\n**Step 2: Citation expansion**: `PubMed_get_cited_by`, `EuropePMC_get_citations\u002Freferences`, `PubMed_get_related`, `SemanticScholar_get_recommendations`, `OpenCitations_get_citations`\n**Step 3: Collision-filtered broader queries**: `\"[TERM]\" AND ([context]) NOT [collision]`\n\n### 2.2 Literature Tools\n\n**Biomedical**: `PubMed_search_articles`, `PMC_search_papers`, `EuropePMC_search_articles`, `PubTator3_LiteratureSearch`\n**Biology (ecology\u002Fevolution\u002Fplant)**: **EuropePMC as PRIMARY** (PubMed returns 0-1 for non-clinical biology). Also `openalex_literature_search`.\n**CS\u002FML**: `ArXiv_search_papers`, `DBLP_search_publications`, `SemanticScholar_search_papers`\n**General**: `openalex_literature_search`, `Crossref_search_works`, `CORE_search_papers`, `DOAJ_search_articles`\n**Preprints**: `BioRxiv_get_preprint`, `MedRxiv_get_preprint`, `OSF_search_preprints`, `EuropePMC_search_articles(source='PPR')`\n**Multi-source**: `advanced_literature_search_agent` (12+ DBs; needs Azure key -- fallback: query PubMed+ArXiv+SemanticScholar+OpenAlex individually)\n**Citation impact**: `iCite_search_publications` (RCR\u002FAPT), `iCite_get_publications` (by PMID), `scite_get_tallies` (support\u002Fcontradict). PubMed-only; for CS use SemanticScholar.\n\n### 2.3-2.4 Full-Text & PubMed Zero-Result Fallback\n\nFull-text: see `FULLTEXT_STRATEGY.md` for three-tier strategy.\n\n**CRITICAL**: PubMed returns 0 for ~30% of valid queries. **Always retry with EuropePMC** when PubMed returns empty. This is not optional.\n\n### 2.5 Tool Failure \u002F OA Handling\nRetry once -> fallback tool. Key fallbacks: PubMed_get_cited_by -> EuropePMC_get_citations -> OpenCitations. OA: Unpaywall if configured, else Europe PMC\u002FPMC\u002FOpenAlex flags.\n\n---\n\n## Phase 3: Evidence Grading\n\n| Tier | Label | Bio Example | CS\u002FML Example |\n|------|-------|-------------|---------------|\n| **T1** | Mechanistic | CRISPR KO + rescue, RCT | Formal proof, controlled ablation |\n| **T2** | Functional | siRNA knockdown phenotype | Benchmark with baselines |\n| **T3** | Association | GWAS, screen hit | Observational, case study |\n| **T4** | Mention | Review article | Survey, workshop abstract |\n\nInline: `Target X regulates Y [T1: PMID:12345678]`. Per theme: summarize evidence distribution.\n\n---\n\n## Report Output\n\n| File | Mode |\n|------|------|\n| `[topic]_report.md` | Full |\n| `[topic]_factcheck_report.md` | Factoid |\n| `[topic]_bibliography.json` + `.csv` | All |\n\n**Progressive update**: create report with all section headers immediately. Fill after each phase. Write Executive Summary LAST.\n\nUse 15-section template from `REPORT_TEMPLATE.md`. Domain adaptations: bio (architecture\u002Fexpression\u002FGO\u002Fdisease), drug (properties\u002FMOA\u002FPK\u002Fsafety), disease (epi\u002Fpatho\u002Fgenes\u002Ftreatments), general (history\u002Ftheories\u002Fevidence\u002Fapplications).\n\n---\n\n## Communication\n\nBrief progress updates only: \"Resolving identifiers...\", \"Building paper set...\", \"Grading evidence...\"\nDo NOT expose: raw tool outputs, dedup counts, search round details.\n\n---\n\n## References\n\n- `TOOL_NAMES_REFERENCE.md` -- 123 tools with parameters\n- `REPORT_TEMPLATE.md` -- template, domain adaptations, bibliography, completeness checklist\n- `FULLTEXT_STRATEGY.md` -- three-tier full-text verification\n- `WORKFLOW.md` -- compact cheat-sheet\n- `EXAMPLES.md` -- worked examples\n","# Literature Deep Research\n\nSystematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.\n\n**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\n\n---\n\n## LOOK UP, DON'T GUESS\n\nSearch PubMed\u002FEuropePMC FIRST before reasoning. A published paper beats memory.\n\n**Factoid search strategy:**\n1. Extract KEY TERMS (most specific nouns\u002Fverbs)\n2. `EuropePMC_search_articles(query=\"term1 term2 term3\", limit=5)`\n3. No results -> BROADEN (remove most restrictive term)\n4. Too many -> NARROW (add specific terms)\n5. Answer usually in abstract of top results\n6. Failed query -> try DIFFERENT TERMS\u002Fsynonyms, don't repeat\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen 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.\n\n## Workflow\n\n```\nPhase 0: Clarify + Mode Select → Phase 1: Disambiguate + Profile → Phase 2: Literature Search → Phase 3: Report\n```\n\n---\n\n## Phase 0: Mode Selection\n\n| Mode | When | Deliverable |\n|------|------|-------------|\n| **Factoid** | Single concrete question | 1-page fact-check report + bibliography |\n| **Mini-review** | Narrow topic | 1-3 page narrative |\n| **Full Deep-Research** | Comprehensive overview | 15-section report + bibliography |\n\n### Factoid Mode (Fast Path)\n```markdown\n# [TOPIC]: Fact-check Report\n## Question \u002F ## Answer (with evidence rating) \u002F ## Source(s) \u002F ## Verification Notes \u002F ## Limitations\n```\n\n### Domain Detection\n\n| Pattern | Domain | Action |\n|---------|--------|--------|\n| Gene\u002Fprotein symbol | Biological target | Full bio disambiguation |\n| Drug name | Drug | Drug disambiguation (1.5) |\n| Disease name | Disease | Disease disambiguation (1.6) |\n| CS\u002FML topic | General academic | Skip bio tools, literature-only |\n| Cross-domain | Interdisciplinary | Resolve each entity in its domain |\n\n### Cross-Skill Delegation\n- Gene\u002Fprotein deep-dive: `tooluniverse-target-research`\n- Drug profile: `tooluniverse-drug-research`\n- Disease profile: `tooluniverse-disease-research`\n\nUse this skill for **literature synthesis**. Use specialized skills for **entity profiling**. For max depth, run both.\n\n---\n\n## Phase 1: Subject Disambiguation + Profile\n\n### 1.1 Biological Target Resolution\n```\nUniProt_search → UniProt_get_entry_by_accession → UniProt_id_mapping\nensembl_lookup_gene → MyGene_get_gene_annotation\n```\n\n### 1.2 Naming Collision Detection\nCheck first 20 results. If >20% off-topic, build negative filter: `NOT [collision1] NOT [collision2]`.\nGene family: `\"ADAR\" NOT \"ADAR2\" NOT \"ADARB1\"`. Cross-domain: add context terms.\n\n### 1.3 Baseline Profile (Bio Targets)\n```\nInterPro_get_protein_domains, UniProt_get_ptm_processing_by_accession, HPA_get_subcellular_location,\nGTEx_get_median_gene_expression, GO_get_annotations_for_gene, Reactome_map_uniprot_to_pathways,\nSTRING_get_protein_interactions, intact_get_interactions, OpenTargets_get_target_tractability_by_ensemblID\n```\nGPCR targets: delegate to `tooluniverse-target-research`.\n\n### 1.5 Drug Disambiguation\n**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`\n**Targets**: `ChEMBL_get_drug_mechanisms`, `OpenTargets_get_associated_targets_by_drug_chemblId`, `DGIdb_get_drug_gene_interactions`\n**Safety**: `OpenTargets_get_drug_adverse_events_by_chemblId`, `OpenTargets_get_drug_indications_by_chemblId`, `search_clinical_trials`\n\n### 1.6 Disease Disambiguation\n```\nOpenTargets disease search → EFO\u002FMONDO IDs\nDisGeNET_get_disease_genes, DisGeNET_search_disease\nCTD_get_disease_chemicals\n```\n\n### 1.7 Compound Queries (e.g., \"metformin in breast cancer\")\nResolve both entities, then cross-reference via CTD_get_chemical_gene_interactions, CTD_get_chemical_diseases, OpenTargets drug-target\u002Fdrug-disease tools. Intersect shared targets\u002Fpathways.\n\n### 1.8 General Academic \u002F 1.9 Interdisciplinary\nNon-bio: skip bio tools, use ArXiv\u002FDBLP\u002FOSF. Cross-domain: resolve bio entities with 1.1-1.3, search CS\u002Fgeneral in parallel, merge and cross-reference.\n\n---\n\n## Phase 2: Literature Search\n\n**Methodology stays internal. Report shows findings, not process.**\n\n### 2.1 Query Strategy\n**Step 1: Seeds** (15-30 core papers): domain-specific title searches with date\u002Fsort filters.\n**Step 2: Citation expansion**: `PubMed_get_cited_by`, `EuropePMC_get_citations\u002Freferences`, `PubMed_get_related`, `SemanticScholar_get_recommendations`, `OpenCitations_get_citations`\n**Step 3: Collision-filtered broader queries**: `\"[TERM]\" AND ([context]) NOT [collision]`\n\n### 2.2 Literature Tools\n\n**Biomedical**: `PubMed_search_articles`, `PMC_search_papers`, `EuropePMC_search_articles`, `PubTator3_LiteratureSearch`\n**Biology (ecology\u002Fevolution\u002Fplant)**: **EuropePMC as PRIMARY** (PubMed returns 0-1 for non-clinical biology). Also `openalex_literature_search`.\n**CS\u002FML**: `ArXiv_search_papers`, `DBLP_search_publications`, `SemanticScholar_search_papers`\n**General**: `openalex_literature_search`, `Crossref_search_works`, `CORE_search_papers`, `DOAJ_search_articles`\n**Preprints**: `BioRxiv_get_preprint`, `MedRxiv_get_preprint`, `OSF_search_preprints`, `EuropePMC_search_articles(source='PPR')`\n**Multi-source**: `advanced_literature_search_agent` (12+ DBs; needs Azure key -- fallback: query PubMed+ArXiv+SemanticScholar+OpenAlex individually)\n**Citation impact**: `iCite_search_publications` (RCR\u002FAPT), `iCite_get_publications` (by PMID), `scite_get_tallies` (support\u002Fcontradict). PubMed-only; for CS use SemanticScholar.\n\n### 2.3-2.4 Full-Text & PubMed Zero-Result Fallback\n\nFull-text: see `FULLTEXT_STRATEGY.md` for three-tier strategy.\n\n**CRITICAL**: PubMed returns 0 for ~30% of valid queries. **Always retry with EuropePMC** when PubMed returns empty. This is not optional.\n\n### 2.5 Tool Failure \u002F OA Handling\nRetry once -> fallback tool. Key fallbacks: PubMed_get_cited_by -> EuropePMC_get_citations -> OpenCitations. OA: Unpaywall if configured, else Europe PMC\u002FPMC\u002FOpenAlex flags.\n\n---\n\n## Phase 3: Evidence Grading\n\n| Tier | Label | Bio Example | CS\u002FML Example |\n|------|-------|-------------|---------------|\n| **T1** | Mechanistic | CRISPR KO + rescue, RCT | Formal proof, controlled ablation |\n| **T2** | Functional | siRNA knockdown phenotype | Benchmark with baselines |\n| **T3** | Association | GWAS, screen hit | Observational, case study |\n| **T4** | Mention | Review article | Survey, workshop abstract |\n\nInline: `Target X regulates Y [T1: PMID:12345678]`. Per theme: summarize evidence distribution.\n\n---\n\n## Report Output\n\n| File | Mode |\n|------|------|\n| `[topic]_report.md` | Full |\n| `[topic]_factcheck_report.md` | Factoid |\n| `[topic]_bibliography.json` + `.csv` | All |\n\n**Progressive update**: create report with all section headers immediately. Fill after each phase. Write Executive Summary LAST.\n\nUse 15-section template from `REPORT_TEMPLATE.md`. Domain adaptations: bio (architecture\u002Fexpression\u002FGO\u002Fdisease), drug (properties\u002FMOA\u002FPK\u002Fsafety), disease (epi\u002Fpatho\u002Fgenes\u002Ftreatments), general (history\u002Ftheories\u002Fevidence\u002Fapplications).\n\n---\n\n## Communication\n\nBrief progress updates only: \"Resolving identifiers...\", \"Building paper set...\", \"Grading evidence...\"\nDo NOT expose: raw tool outputs, dedup counts, search round details.\n\n---\n\n## References\n\n- `TOOL_NAMES_REFERENCE.md` -- 123 tools with parameters\n- `REPORT_TEMPLATE.md` -- template, domain adaptations, bibliography, completeness checklist\n- `FULLTEXT_STRATEGY.md` -- three-tier full-text verification\n- `WORKFLOW.md` -- compact cheat-sheet\n- `EXAMPLES.md` -- worked examples\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-literature-deep-research",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-literature-deep-research",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-literature-deep-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FSKILL.md",true,[69,75,79,83,87,91],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"EXAMPLES.md","REFERENCE","参考文档",26860,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FEXAMPLES.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"FULLTEXT_STRATEGY.md",3807,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FFULLTEXT_STRATEGY.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"QUICK_REFERENCE.md",6208,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FQUICK_REFERENCE.md",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"REPORT_TEMPLATE.md",12892,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FREPORT_TEMPLATE.md",{"path":88,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":89,"sourceHtmlUrl":90},"TOOL_NAMES_REFERENCE.md",19153,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FTOOL_NAMES_REFERENCE.md",{"path":92,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":93,"sourceHtmlUrl":94},"WORKFLOW.md",7827,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-literature-deep-research\u002FWORKFLOW.md",[96,118,147,174,188,204],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":44},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[103,104,105,106,107,108,109,110,111,112,113,114,115,116,117],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":127,"publishedAt":44},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[128,129,130,131,132,133,134,135,136,137,138,139,140,141,112,142,143,144,145,146],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":159,"publishedAt":44},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[153,156],{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[160,161,162,163,164,165,166,167,168,169,129,170,171,172,173],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":44},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[176,181,182,183,184,185,186,187],"setup","report","project","installation","project setup","issues","state",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":44},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[194],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},[190,196,108,197,198,199,112,200,201,202,203],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":205,"name":181,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":209,"publishedAt":44},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[181,183,144,210,185,211],"files","interactive"]