[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAPHFBSY46P50EBX76QPSM":3,"skill-same:01M6DAPHFBSY46P50EBX76QPSM":85},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6DAPHFBSY46P50EBX76QPSM","tooluniverse-disease-research",null,"Generate comprehensive disease research reports using 100+ ToolUniverse tools. Creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions. All information includes source references. Use when users ask about diseases, syndromes, or need systematic disease analysis.","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-disease-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],"research","tooluniverse disease research","generate","report","file","Tools","analysis","markdown","ask","use","reports","references","dimensions","systematic","2026-11-10 10:12:30",false,"---\nname: tooluniverse-disease-research\ndescription: Generate comprehensive disease research reports using 100+ ToolUniverse tools. Creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions. All information includes source references. Use when users ask about diseases, syndromes, or need systematic disease analysis.\n---\n\n# ToolUniverse Disease Research\n\nGenerate a comprehensive disease research report with full source citations. The report is created as a markdown file and progressively updated during research.\n\n**IMPORTANT**: Always use English disease names and search terms in tool calls. Respond in the user's language.\n\n---\n\n## LOOK UP, DON'T GUESS\n\nWhen asked about a disease, query Orphanet\u002FOMIM\u002FDisGeNET FIRST. Don't rely on memory for prevalence, genetics, or treatment — these change over time. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.\n\n---\n\n## When to Use\n\n- User asks about any disease, syndrome, or medical condition\n- Needs comprehensive disease intelligence or a detailed research report\n- Asks \"what do we know about [disease]?\"\n\n---\n\n## Core Workflow: Report-First Approach\n\n**DO NOT** show the search process to the user. Instead:\n\n1. **Create report file first** - Initialize `{disease_name}_research_report.md`\n2. **Research each dimension** - Use all relevant tools\n3. **Update report progressively** - Write findings after each dimension\n4. **Include citations** - Every fact must reference its source tool\n\n---\n\n## Disease Mechanism Reasoning\n\nWhen synthesizing disease etiology, trace the full pathogenic cascade:\n1. **Genetic basis** - Which variants (rare or common) confer risk, and in which genes?\n2. **Molecular mechanism** - How do those variants alter protein function, expression, or regulation?\n3. **Cellular effect** - What downstream cellular processes are disrupted (signaling, metabolism, stress response)?\n4. **Tissue\u002Forgan manifestation** - How does cellular dysfunction present as organ-level pathology?\n\nThis chain structures the Genetic & Molecular Basis (Section 3) and Biological Pathways (Section 5) sections.\n\n---\n\n## 10 Research Dimensions\n\n| Dim | Section | Key Tools |\n|-----|---------|-----------|\n| 1 | Identity & Classification | OSL_get_efo_id_by_disease_name, ols_search_efo_terms, ols_get_efo_term, umls_search_concepts, icd_search_codes, snomed_search_concepts |\n| 2 | Clinical Presentation | OpenTargets phenotypes, HPO lookup, MedlinePlus |\n| 3 | Genetic & Molecular Basis | OpenTargets targets, ClinVar variants, GWAS associations, gnomAD |\n| 4 | Treatment Landscape | OpenTargets drugs, clinical trials, GtoPdb |\n| 5 | Biological Pathways | Reactome pathways, humanbase_ppi_analysis, GTEx expression, HPA |\n| 6 | Epidemiology & Literature | PubMed, OpenAlex, Europe PMC, Semantic Scholar |\n| 7 | Similar Diseases | OpenTargets similar entities |\n| 8 | Cancer-Specific (if applicable) | CIViC genes\u002Fvariants\u002Ftherapies |\n| 9 | Pharmacology | GtoPdb targets\u002Finteractions\u002Fligands |\n| 10 | Drug Safety | OpenTargets warnings, clinical trial AEs, FAERS |\n\nSee: tool_usage_details.md for complete tool calls per section.\n\n---\n\n## Report Template\n\nCreate this file structure at the start:\n\n```markdown\n# Disease Research Report: {Disease Name}\n\n**Report Generated**: {date}\n**Disease Identifiers**: (to be filled)\n\n---\n\n## Executive Summary\n(Brief 3-5 sentence overview - fill after all research complete)\n\n---\n\n## 1. Disease Identity & Classification\n### Ontology Identifiers\n| System | ID | Source |\n\n### Synonyms & Alternative Names\n### Disease Hierarchy\n\n---\n\n## 2. Clinical Presentation\n### Phenotypes (HPO)\n| HPO ID | Phenotype | Description | Source |\n\n### Symptoms & Signs\n### Diagnostic Criteria\n\n---\n\n## 3. Genetic & Molecular Basis\n### Associated Genes\n| Gene | Score | Ensembl ID | Evidence | Source |\n\n### GWAS Associations\n| SNP | P-value | Odds Ratio | Study | Source |\n\n### Pathogenic Variants (ClinVar)\n\n---\n\n## 4. Treatment Landscape\n### Approved Drugs\n| Drug | ChEMBL ID | Mechanism | Phase | Target | Source |\n\n### Clinical Trials\n| NCT ID | Title | Phase | Status | Source |\n\n---\n\n## 5. Biological Pathways & Mechanisms\n\n## 6. Epidemiology & Risk Factors\n\n## 7. Literature & Research Activity\n\n## 8. Similar Diseases & Comorbidities\n\n## 9. Cancer-Specific Information (if applicable)\n\n## 10. Drug Safety & Adverse Events\n\n---\n\n## References\n### Tools Used\n| # | Tool | Parameters | Section | Items Retrieved |\n```\n\n---\n\n## Citation Format\n\nEvery piece of data MUST include its source:\n\n**In tables**: Add a `Source` column with tool name\n**In lists**: `- Finding [Source: tool_name]`\n**In prose**: `(Source: tool_name, query: \"...\")`\n**References section**: Complete tool usage log with parameters\n\n---\n\n## Progressive Update Pattern\n\n```python\n# After each dimension's research:\n# 1. Read current report\n# 2. Replace placeholder with formatted content\n# 3. Write back immediately\n# 4. Continue to next dimension\n```\n\n---\n\n## Evidence Grading & Interpretation\n\nEvery finding in the report should be graded:\n\n| Grade | Criteria | Example |\n|-------|---------|---------|\n| **T1 (Strong)** | Replicated genetic evidence (GWAS, rare variants), FDA-approved therapy | BRCA1 → breast cancer; trastuzumab for HER2+ |\n| **T2 (Moderate)** | Single genetic study, phase II+ trial data, strong biological evidence | FOXO3 → longevity (centenarian studies) |\n| **T3 (Association)** | Observational data, gene expression changes, pathway membership | IL-6 elevated in Alzheimer's CSF |\n| **T4 (Computational)** | Network proximity, text mining, predicted associations | DisGeNET text-mined gene-disease link |\n\n### Synthesis Questions (answer in Executive Summary)\n\nAfter collecting data from all 10 dimensions, the report MUST answer:\n\n1. **What causes this disease?** Summarize the genetic architecture (monogenic vs polygenic, key loci, penetrance)\n2. **What are the therapeutic options?** Ranked by evidence level and approval status\n3. **What biomarkers exist?** For diagnosis, prognosis, and treatment selection\n4. **What's the unmet need?** What aspects lack effective treatment or understanding?\n5. **What are the active research frontiers?** Based on clinical trials and recent publications\n\n### Interpreting Cross-Database Concordance\n\nWhen multiple databases provide different data for the same disease:\n- **OpenTargets + DisGeNET + OMIM agree on a gene**: T1 evidence — high confidence\n- **Only OpenTargets reports an association**: Check the datasource scores — genetic_association > literature > animal_model\n- **DisGeNET score > 0.5 but not in OpenTargets**: May be text-mined; verify with PubMed\n- **Gene in GWAS but not OMIM**: Likely a complex disease susceptibility locus, not Mendelian\n\n### Handling Conflicting Data\n\n| Conflict | Resolution |\n|----------|-----------|\n| Different prevalence estimates across sources | Report range; note the most recent\u002Flargest study |\n| Drug approved in one country but not another | Note regulatory status per region |\n| Gene-disease association in one DB but absent in another | Grade by evidence type; text-mining alone is T4 |\n| Clinical trial results contradict label indications | The trial result is newer evidence; note both |\n\n---\n\n## Final Report Quality Checklist\n\n- [ ] All 10 sections have content (or marked \"No data available\")\n- [ ] Every data point has a source citation\n- [ ] Executive summary reflects key findings\n- [ ] References section lists all tools used\n- [ ] Tables properly formatted\n- [ ] No placeholder text remains\n\n---\n\n## Expected Output Scale\n\nFor a well-studied disease (e.g., Alzheimer's), the final report should include:\n- 5+ ontology IDs, 10+ synonyms, disease hierarchy\n- 20+ phenotypes with HPO IDs\n- 50+ genes, 30+ GWAS associations, 100+ ClinVar variants\n- 20+ drugs, 50+ clinical trials\n- 10+ pathways, PPI network, expression data\n- 100+ publications\n- 15+ similar diseases\n- Drug warnings and adverse events\n\nTotal: 500+ individual data points, each with source citation.\n\n---\n\n## Cross-Skill References\n\nFor rare disease differential diagnosis, run: `python3 skills\u002Ftooluniverse-rare-disease-diagnosis\u002Fscripts\u002Fclinical_patterns.py --type differential --symptoms 'symptom1,symptom2'`\n\n---\n\n## Reference Files\n\n- **[REPORT_TEMPLATE.md](REPORT_TEMPLATE.md)** - Full report markdown template and citation format guide\n- **[RESEARCH_PROTOCOL.md](RESEARCH_PROTOCOL.md)** - Step-by-step code procedures, progressive update pattern, quality checklist\n- **[tool_usage_details.md](tool_usage_details.md)** - Complete tool calls for each research dimension\n- **[TOOLS_REFERENCE.md](TOOLS_REFERENCE.md)** - Complete tool documentation\n- **[EXAMPLES.md](EXAMPLES.md)** - Sample disease research reports\n","# ToolUniverse Disease Research\n\nGenerate a comprehensive disease research report with full source citations. The report is created as a markdown file and progressively updated during research.\n\n**IMPORTANT**: Always use English disease names and search terms in tool calls. Respond in the user's language.\n\n---\n\n## LOOK UP, DON'T GUESS\n\nWhen asked about a disease, query Orphanet\u002FOMIM\u002FDisGeNET FIRST. Don't rely on memory for prevalence, genetics, or treatment — these change over time. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.\n\n---\n\n## When to Use\n\n- User asks about any disease, syndrome, or medical condition\n- Needs comprehensive disease intelligence or a detailed research report\n- Asks \"what do we know about [disease]?\"\n\n---\n\n## Core Workflow: Report-First Approach\n\n**DO NOT** show the search process to the user. Instead:\n\n1. **Create report file first** - Initialize `{disease_name}_research_report.md`\n2. **Research each dimension** - Use all relevant tools\n3. **Update report progressively** - Write findings after each dimension\n4. **Include citations** - Every fact must reference its source tool\n\n---\n\n## Disease Mechanism Reasoning\n\nWhen synthesizing disease etiology, trace the full pathogenic cascade:\n1. **Genetic basis** - Which variants (rare or common) confer risk, and in which genes?\n2. **Molecular mechanism** - How do those variants alter protein function, expression, or regulation?\n3. **Cellular effect** - What downstream cellular processes are disrupted (signaling, metabolism, stress response)?\n4. **Tissue\u002Forgan manifestation** - How does cellular dysfunction present as organ-level pathology?\n\nThis chain structures the Genetic & Molecular Basis (Section 3) and Biological Pathways (Section 5) sections.\n\n---\n\n## 10 Research Dimensions\n\n| Dim | Section | Key Tools |\n|-----|---------|-----------|\n| 1 | Identity & Classification | OSL_get_efo_id_by_disease_name, ols_search_efo_terms, ols_get_efo_term, umls_search_concepts, icd_search_codes, snomed_search_concepts |\n| 2 | Clinical Presentation | OpenTargets phenotypes, HPO lookup, MedlinePlus |\n| 3 | Genetic & Molecular Basis | OpenTargets targets, ClinVar variants, GWAS associations, gnomAD |\n| 4 | Treatment Landscape | OpenTargets drugs, clinical trials, GtoPdb |\n| 5 | Biological Pathways | Reactome pathways, humanbase_ppi_analysis, GTEx expression, HPA |\n| 6 | Epidemiology & Literature | PubMed, OpenAlex, Europe PMC, Semantic Scholar |\n| 7 | Similar Diseases | OpenTargets similar entities |\n| 8 | Cancer-Specific (if applicable) | CIViC genes\u002Fvariants\u002Ftherapies |\n| 9 | Pharmacology | GtoPdb targets\u002Finteractions\u002Fligands |\n| 10 | Drug Safety | OpenTargets warnings, clinical trial AEs, FAERS |\n\nSee: tool_usage_details.md for complete tool calls per section.\n\n---\n\n## Report Template\n\nCreate this file structure at the start:\n\n```markdown\n# Disease Research Report: {Disease Name}\n\n**Report Generated**: {date}\n**Disease Identifiers**: (to be filled)\n\n---\n\n## Executive Summary\n(Brief 3-5 sentence overview - fill after all research complete)\n\n---\n\n## 1. Disease Identity & Classification\n### Ontology Identifiers\n| System | ID | Source |\n\n### Synonyms & Alternative Names\n### Disease Hierarchy\n\n---\n\n## 2. Clinical Presentation\n### Phenotypes (HPO)\n| HPO ID | Phenotype | Description | Source |\n\n### Symptoms & Signs\n### Diagnostic Criteria\n\n---\n\n## 3. Genetic & Molecular Basis\n### Associated Genes\n| Gene | Score | Ensembl ID | Evidence | Source |\n\n### GWAS Associations\n| SNP | P-value | Odds Ratio | Study | Source |\n\n### Pathogenic Variants (ClinVar)\n\n---\n\n## 4. Treatment Landscape\n### Approved Drugs\n| Drug | ChEMBL ID | Mechanism | Phase | Target | Source |\n\n### Clinical Trials\n| NCT ID | Title | Phase | Status | Source |\n\n---\n\n## 5. Biological Pathways & Mechanisms\n\n## 6. Epidemiology & Risk Factors\n\n## 7. Literature & Research Activity\n\n## 8. Similar Diseases & Comorbidities\n\n## 9. Cancer-Specific Information (if applicable)\n\n## 10. Drug Safety & Adverse Events\n\n---\n\n## References\n### Tools Used\n| # | Tool | Parameters | Section | Items Retrieved |\n```\n\n---\n\n## Citation Format\n\nEvery piece of data MUST include its source:\n\n**In tables**: Add a `Source` column with tool name\n**In lists**: `- Finding [Source: tool_name]`\n**In prose**: `(Source: tool_name, query: \"...\")`\n**References section**: Complete tool usage log with parameters\n\n---\n\n## Progressive Update Pattern\n\n```python\n# After each dimension's research:\n# 1. Read current report\n# 2. Replace placeholder with formatted content\n# 3. Write back immediately\n# 4. Continue to next dimension\n```\n\n---\n\n## Evidence Grading & Interpretation\n\nEvery finding in the report should be graded:\n\n| Grade | Criteria | Example |\n|-------|---------|---------|\n| **T1 (Strong)** | Replicated genetic evidence (GWAS, rare variants), FDA-approved therapy | BRCA1 → breast cancer; trastuzumab for HER2+ |\n| **T2 (Moderate)** | Single genetic study, phase II+ trial data, strong biological evidence | FOXO3 → longevity (centenarian studies) |\n| **T3 (Association)** | Observational data, gene expression changes, pathway membership | IL-6 elevated in Alzheimer's CSF |\n| **T4 (Computational)** | Network proximity, text mining, predicted associations | DisGeNET text-mined gene-disease link |\n\n### Synthesis Questions (answer in Executive Summary)\n\nAfter collecting data from all 10 dimensions, the report MUST answer:\n\n1. **What causes this disease?** Summarize the genetic architecture (monogenic vs polygenic, key loci, penetrance)\n2. **What are the therapeutic options?** Ranked by evidence level and approval status\n3. **What biomarkers exist?** For diagnosis, prognosis, and treatment selection\n4. **What's the unmet need?** What aspects lack effective treatment or understanding?\n5. **What are the active research frontiers?** Based on clinical trials and recent publications\n\n### Interpreting Cross-Database Concordance\n\nWhen multiple databases provide different data for the same disease:\n- **OpenTargets + DisGeNET + OMIM agree on a gene**: T1 evidence — high confidence\n- **Only OpenTargets reports an association**: Check the datasource scores — genetic_association > literature > animal_model\n- **DisGeNET score > 0.5 but not in OpenTargets**: May be text-mined; verify with PubMed\n- **Gene in GWAS but not OMIM**: Likely a complex disease susceptibility locus, not Mendelian\n\n### Handling Conflicting Data\n\n| Conflict | Resolution |\n|----------|-----------|\n| Different prevalence estimates across sources | Report range; note the most recent\u002Flargest study |\n| Drug approved in one country but not another | Note regulatory status per region |\n| Gene-disease association in one DB but absent in another | Grade by evidence type; text-mining alone is T4 |\n| Clinical trial results contradict label indications | The trial result is newer evidence; note both |\n\n---\n\n## Final Report Quality Checklist\n\n- [ ] All 10 sections have content (or marked \"No data available\")\n- [ ] Every data point has a source citation\n- [ ] Executive summary reflects key findings\n- [ ] References section lists all tools used\n- [ ] Tables properly formatted\n- [ ] No placeholder text remains\n\n---\n\n## Expected Output Scale\n\nFor a well-studied disease (e.g., Alzheimer's), the final report should include:\n- 5+ ontology IDs, 10+ synonyms, disease hierarchy\n- 20+ phenotypes with HPO IDs\n- 50+ genes, 30+ GWAS associations, 100+ ClinVar variants\n- 20+ drugs, 50+ clinical trials\n- 10+ pathways, PPI network, expression data\n- 100+ publications\n- 15+ similar diseases\n- Drug warnings and adverse events\n\nTotal: 500+ individual data points, each with source citation.\n\n---\n\n## Cross-Skill References\n\nFor rare disease differential diagnosis, run: `python3 skills\u002Ftooluniverse-rare-disease-diagnosis\u002Fscripts\u002Fclinical_patterns.py --type differential --symptoms 'symptom1,symptom2'`\n\n---\n\n## Reference Files\n\n- **[REPORT_TEMPLATE.md](REPORT_TEMPLATE.md)** - Full report markdown template and citation format guide\n- **[RESEARCH_PROTOCOL.md](RESEARCH_PROTOCOL.md)** - Step-by-step code procedures, progressive update pattern, quality checklist\n- **[tool_usage_details.md](tool_usage_details.md)** - Complete tool calls for each research dimension\n- **[TOOLS_REFERENCE.md](TOOLS_REFERENCE.md)** - Complete tool documentation\n- **[EXAMPLES.md](EXAMPLES.md)** - Sample disease research reports\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-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":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-disease-research",{"tool":55,"command":56},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-disease-research",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-disease-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-research\u002FSKILL.md",true,[63,69,73,77,81],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"EXAMPLES.md","REFERENCE","参考文档",20162,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-research\u002FEXAMPLES.md",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"REPORT_TEMPLATE.md",5291,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-research\u002FREPORT_TEMPLATE.md",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"RESEARCH_PROTOCOL.md",5298,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-research\u002FRESEARCH_PROTOCOL.md",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"tool_usage_details.md",6033,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-research\u002Ftool_usage_details.md",{"path":82,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":83,"sourceHtmlUrl":84},"TOOLS_REFERENCE.md",23201,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-disease-research\u002FTOOLS_REFERENCE.md",[86,106,135,162,175,191],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":38},"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",[],[93,94,95,96,97,98,99,100,101,33,102,103,104,105,28],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":115,"publishedAt":38},"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",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[116,117,118,119,120,121,122,123,124,125,126,127,128,129,33,130,131,132,133,134],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":147,"publishedAt":38},"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",[141,144],{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[148,149,150,151,152,153,154,155,156,157,117,158,159,160,161],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":38},"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",[],[164,169,27,170,171,172,173,174],"setup","project","installation","project setup","issues","state",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":38},"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",[181],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},[177,183,98,184,185,186,33,187,188,189,190],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":192,"name":169,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":38},"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",[],[169,170,132,197,172,198],"files","interactive"]