[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAYQD3AJ3PRRETR5QZ18X7":3,"skill-same:01M6DAYQD3AJ3PRRETR5QZ18X7":69},{"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":28,"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},"01M6DAYQD3AJ3PRRETR5QZ18X7","tooluniverse-vaccine-design",null,"Design and evaluate vaccine candidates using computational immunology tools. Covers epitope prediction (MHC-I\u002FII binding via IEDB), population coverage analysis, antigen selection, adjuvant matching, and immunogenicity assessment. Integrates IEDB for epitope prediction, UniProt for antigen sequences, PDB\u002FAlphaFold for structural epitopes, BVBRC for pathogen proteomes, and literature for clinical precedent. Use when asked about vaccine design, epitope prediction, immunogenicity, MHC binding, T-cell epitopes, B-cell epitopes, or population coverage for vaccine candidates.","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-vaccine-design\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"design","tooluniverse vaccine design","coverage analysis","assessment","Tools","analysis","precedent","coverage","use","selection","cell","computational","matching","structural","clinical","2026-11-10 10:12:30",false,"---\nname: tooluniverse-vaccine-design\ndescription: Design and evaluate vaccine candidates using computational immunology tools. Covers epitope prediction (MHC-I\u002FII binding via IEDB), population coverage analysis, antigen selection, adjuvant matching, and immunogenicity assessment. Integrates IEDB for epitope prediction, UniProt for antigen sequences, PDB\u002FAlphaFold for structural epitopes, BVBRC for pathogen proteomes, and literature for clinical precedent. Use when asked about vaccine design, epitope prediction, immunogenicity, MHC binding, T-cell epitopes, B-cell epitopes, or population coverage for vaccine candidates.\n---\n\n# Vaccine Design\n\nComputational pipeline for designing peptide\u002Fsubunit vaccine candidates through epitope prediction, population coverage optimization, and immunogenicity assessment.\n\n## Reasoning Strategy\n\nVaccine design requires presenting the right epitopes to elicit protective immunity — not just any immune response, but one that is neutralizing, durable, and broadly applicable. For T-cell vaccines, the core tool is MHC binding prediction (IEDB tools): predict peptide-MHC affinity across multiple HLA alleles, then select epitopes with broad coverage of the target population. For antibody vaccines, prioritize surface-exposed conserved regions — a deeply buried or hypervariable region makes a poor antibody target. MHC binding does not equal immunogenicity; many good binders are not immunogenic in vivo due to tolerance, poor processing, or lack of T-cell help. A multi-epitope strategy (combining MHC-I for CD8+ CTL response, MHC-II for CD4+ helper response, and B-cell epitopes for antibody induction) is more robust than any single epitope. Conservation across pathogen strains is critical — an epitope that mutates under immune pressure (like HIV envelope hypervariable regions) is a poor vaccine target.\n\n**LOOK UP DON'T GUESS**: Do not predict MHC binding or population coverage from memory — use `IEDB_predict_mhci_binding` and `IEDB_predict_mhcii_binding` for predictions and `IEDB_search_epitopes` for validated experimental data. Do not assume what's on the pathogen surface; retrieve annotated sequences from UniProt or BVBRC.\n\n**Key principles**:\n1. **Epitope-driven** — vaccines work by presenting epitopes to T\u002FB cells; start with epitope prediction\n2. **Population coverage matters** — HLA diversity means no single epitope covers everyone; design for breadth\n3. **Multi-epitope is better** — combine CD8+ (MHC-I) and CD4+ (MHC-II) epitopes for robust immunity\n4. **Conservation = broad protection** — conserved epitopes across strains provide cross-protective immunity\n5. **Evidence grading** — T1: clinical trial data, T2: in-vivo immunogenicity, T3: in-vitro binding, T4: computational prediction only\n\n---\n\n## When to Use\n\n- \"Design a vaccine against [pathogen]\"\n- \"Predict T-cell epitopes for [protein]\"\n- \"What MHC-I epitopes does [protein] have?\"\n- \"Assess population coverage of these epitopes\"\n- \"Find conserved epitopes across [pathogen] strains\"\n\n**Not this skill**: For HLA typing or allele frequency only, use `tooluniverse-hla-immunogenomics`. For antibody engineering, use `tooluniverse-antibody-engineering`.\n\n---\n\n## Core Tools\n\n| Tool | Use For |\n|------|---------|\n| `IEDB_search_epitopes` | Search experimentally validated epitopes |\n| `IEDB_get_epitope` | Get detailed epitope data (assay results, MHC restriction) |\n| `iedb_search_mhc` | Search validated MHC binding assay data |\n| `IEDB_predict_mhci_binding` | **Predict MHC-I binding** (NetMHCpan EL; rank \u003C 0.5% = strong binder) |\n| `IEDB_predict_mhcii_binding` | **Predict MHC-II binding** (NetMHCIIpan EL; CD4+ helper epitopes) |\n| `UniProt_get_entry_by_accession` | Get antigen protein sequence |\n| `UniProt_search` | Find pathogen protein sequences |\n| `BVBRC_search_genome_features` | Search pathogen proteomes |\n| `alphafold_get_prediction` | Get\u002Fpredict antigen 3D structure |\n| `EnsemblVEP_annotate_hgvs` | Check epitope conservation across variants |\n| `PubMed_search_articles` | Find published vaccine studies |\n| `search_clinical_trials` | Find ongoing vaccine clinical trials |\n\n---\n\n## Workflow\n\n```\nPhase 0: Antigen Selection\n  Pathogen → essential surface proteins → sequence retrieval\n    |\nPhase 1: T-Cell Epitope Prediction\n  MHC-I (CD8+ CTL) and MHC-II (CD4+ helper) binding prediction\n    |\nPhase 2: B-Cell Epitope Prediction\n  Linear and conformational B-cell epitopes for antibody response\n    |\nPhase 3: Population Coverage\n  HLA allele frequencies → design for target population\n    |\nPhase 4: Conservation Analysis\n  Cross-strain epitope conservation → broad protection\n    |\nPhase 5: Candidate Assembly & Report\n  Multi-epitope construct design → immunogenicity assessment\n```\n\n### Phase 0: Antigen Selection\n\n**Best antigens for vaccines**: Surface-exposed, essential for pathogen function, conserved across strains.\n\n```python\n# Find pathogen surface proteins\nUniProt_search(query=\"[organism] AND locations:(location:cell surface) AND reviewed:true\")\n# Or search BVBRC for annotated pathogen proteomes\nBVBRC_search_genome_features(keyword=\"surface protein\", genome_id=\"[taxon_id]\")\n```\n\n**Antigen prioritization**: prefer surface-exposed (secreted\u002Fouter membrane) over cytoplasmic; >95% conserved across strains; essential for pathogen viability; known immunogen in natural infection. Use UniProt subcellular location annotations and PubMed to verify these properties.\n\n### Phase 1: T-Cell Epitope Prediction\n\n**MHC-I epitopes** (CD8+ cytotoxic T cells — kill infected cells):\n\n```python\n# Option A: Search for KNOWN validated epitopes from IEDB\niedb_search_mhc(\n    mhc_class=\"I\",\n    qualitative_measure=\"Positive\",\n    filters={\"source_organism_iri\": \"eq.NCBITaxon:2697049\"},  # SARS-CoV-2\n    select=[\"linear_sequence\", \"mhc_restriction\", \"qualitative_measure\"],\n    limit=50\n)\n\n# Option B: PREDICT novel peptide binding (recommended for new proteins)\nIEDB_predict_mhci_binding(\n    sequence=\"YOUR_PROTEIN_SEQUENCE\",  # full protein or peptide\n    allele=\"HLA-A*02:01\",             # or H-2-Kd for mouse\n    method=\"netmhcpan_el\",            # EL = eluted ligand (recommended)\n    length=9                           # 8-11 for MHC-I\n)\n# Returns peptides ranked by percentile_rank:\n# \u003C 0.5% = strong binder (include in vaccine)\n# 0.5-2% = moderate binder (consider)\n# > 2% = weak\u002Fnon-binder (exclude)\n```\n\n**MHC-II epitopes** (CD4+ helper T cells — activate B cells and CD8+ T cells):\n\n```python\niedb_search_mhc(\n    mhc_class=\"II\",\n    qualitative_measure=\"Positive\",\n    filters={\"source_organism_iri\": \"eq.NCBITaxon:2697049\"},\n    limit=50\n)\n```\n\n**Binding affinity interpretation**:\n\n| IC50 (nM) | Classification | Vaccine Relevance |\n|-----------|---------------|-------------------|\n| \u003C 50 | Strong binder | Include — high presentation probability |\n| 50-500 | Moderate binder | Consider — may contribute to response |\n| 500-5000 | Weak binder | Exclude — unlikely to be presented |\n| > 5000 | Non-binder | Exclude |\n\n**HLA supertype strategy**: For broad coverage, predict against HLA supertypes:\n- **A2 supertype** (A*02:01, A*02:06, A*68:02) — covers ~40% globally\n- **A3 supertype** (A*03:01, A*11:01, A*31:01) — covers ~25%\n- **B7 supertype** (B*07:02, B*35:01, B*51:01) — covers ~25%\n- **A2 + A3 + B7 + B44** combined — covers >90% of most populations\n\n### Phase 2: B-Cell Epitope Prediction\n\nB-cell epitopes trigger antibody production. Look for:\n- **Linear epitopes**: Continuous peptide sequences (easier to synthesize)\n- **Conformational epitopes**: 3D surface patches (requires structural data)\n\n```python\n# Check for known B-cell epitopes\nIEDB_search_epitopes(query=\"[protein_name]\", epitope_type=\"B cell\")\n# Get structure for conformational epitope prediction\nalphafold_get_prediction(uniprot_id=\"[accession]\")\n```\n\n**B-cell epitope criteria**: Surface-exposed loops, hydrophilic regions, flexible regions (high B-factor). Combine computational prediction with structural analysis.\n\n### Phase 3: Population Coverage\n\n```python\n# Search for epitopes restricted to common HLA alleles in target population\n# NOTE: No HLA frequency tool exists in ToolUniverse. For population coverage:\n# 1. Use IEDB Analysis Resource (tools.iedb.org\u002Fpopulation) for population coverage calculation\n# 2. Use the HLA supertype strategy (see above) to ensure broad coverage\n# 3. Search PubMed for published HLA frequency data: PubMed_search_articles(query=\"HLA allele frequency [population]\")\n```\n\n**Population coverage targets**:\n\n| Coverage Level | Interpretation | Action |\n|---------------|---------------|--------|\n| >90% | Excellent — vaccine will work in most individuals | Proceed to development |\n| 70-90% | Good — most people covered; some populations underserved | Add more epitopes for uncovered HLA types |\n| 50-70% | Moderate — significant gaps | Redesign with broader HLA coverage |\n| \u003C50% | Poor — vaccine will miss too many people | Fundamental redesign needed |\n\n### Phase 4: Conservation Analysis\n\nCheck if epitopes are conserved across pathogen strains\u002Fvariants:\n\n```python\n# Search for protein variants across strains\nPubMed_search_articles(query=\"[pathogen] [protein] sequence variation strains\")\n# Check specific mutations in epitope regions\nEnsemblVEP_annotate_hgvs(hgvs_notation=\"[variant_in_epitope]\")\n```\n\n**Conservation interpretation**:\n- **100% conserved** across all known strains → ideal vaccine target\n- **>95% conserved** → good target; monitor emerging variants\n- **80-95% conserved** → may need strain-specific variants in construct\n- **\u003C80% conserved** → avoid; pathogen evolves to escape this epitope\n\n### Phase 5: Candidate Assembly & Report\n\n**Multi-epitope construct design principles**:\n1. Include 3-5 MHC-I epitopes (CD8+ response)\n2. Include 2-3 MHC-II epitopes (CD4+ helper response)\n3. Include 1-2 B-cell epitopes (antibody response)\n4. Connect with appropriate linkers (AAY for MHC-I, GPGPG for MHC-II)\n5. Add adjuvant sequence if needed (e.g., flagellin domain for TLR5)\n\n**Report structure**:\n1. **Antigen Selection** — rationale, conservation, essentiality\n2. **Epitope Map** — all predicted epitopes with binding affinities and HLA restrictions\n3. **Top Epitopes** — ranked by binding strength × conservation × population coverage\n4. **Population Coverage** — % coverage per major world population\n5. **Conservation Analysis** — strain coverage, escape risk assessment\n6. **Construct Design** — multi-epitope sequence with linkers\n7. **Clinical Precedent** — existing vaccines\u002Ftrials for related antigens\n8. **Limitations** — predicted only (T4 evidence); needs experimental validation\n\n---\n\n## Limitations\n\n- **All predictions are computational** (T4 evidence) — experimental validation (binding assays, immunogenicity studies) is required before any clinical development\n- **No immunogenicity guarantee** — MHC binding ≠ immunogenicity; many good binders are not immunogenic in vivo\n- **B-cell epitope prediction is less reliable** than T-cell; conformational epitopes require accurate structures\n- **No adjuvant optimization** — adjuvant selection requires empirical testing\n- **Pathogen evasion** — rapidly evolving pathogens (HIV, influenza) may escape epitope-based vaccines\n","# Vaccine Design\n\nComputational pipeline for designing peptide\u002Fsubunit vaccine candidates through epitope prediction, population coverage optimization, and immunogenicity assessment.\n\n## Reasoning Strategy\n\nVaccine design requires presenting the right epitopes to elicit protective immunity — not just any immune response, but one that is neutralizing, durable, and broadly applicable. For T-cell vaccines, the core tool is MHC binding prediction (IEDB tools): predict peptide-MHC affinity across multiple HLA alleles, then select epitopes with broad coverage of the target population. For antibody vaccines, prioritize surface-exposed conserved regions — a deeply buried or hypervariable region makes a poor antibody target. MHC binding does not equal immunogenicity; many good binders are not immunogenic in vivo due to tolerance, poor processing, or lack of T-cell help. A multi-epitope strategy (combining MHC-I for CD8+ CTL response, MHC-II for CD4+ helper response, and B-cell epitopes for antibody induction) is more robust than any single epitope. Conservation across pathogen strains is critical — an epitope that mutates under immune pressure (like HIV envelope hypervariable regions) is a poor vaccine target.\n\n**LOOK UP DON'T GUESS**: Do not predict MHC binding or population coverage from memory — use `IEDB_predict_mhci_binding` and `IEDB_predict_mhcii_binding` for predictions and `IEDB_search_epitopes` for validated experimental data. Do not assume what's on the pathogen surface; retrieve annotated sequences from UniProt or BVBRC.\n\n**Key principles**:\n1. **Epitope-driven** — vaccines work by presenting epitopes to T\u002FB cells; start with epitope prediction\n2. **Population coverage matters** — HLA diversity means no single epitope covers everyone; design for breadth\n3. **Multi-epitope is better** — combine CD8+ (MHC-I) and CD4+ (MHC-II) epitopes for robust immunity\n4. **Conservation = broad protection** — conserved epitopes across strains provide cross-protective immunity\n5. **Evidence grading** — T1: clinical trial data, T2: in-vivo immunogenicity, T3: in-vitro binding, T4: computational prediction only\n\n---\n\n## When to Use\n\n- \"Design a vaccine against [pathogen]\"\n- \"Predict T-cell epitopes for [protein]\"\n- \"What MHC-I epitopes does [protein] have?\"\n- \"Assess population coverage of these epitopes\"\n- \"Find conserved epitopes across [pathogen] strains\"\n\n**Not this skill**: For HLA typing or allele frequency only, use `tooluniverse-hla-immunogenomics`. For antibody engineering, use `tooluniverse-antibody-engineering`.\n\n---\n\n## Core Tools\n\n| Tool | Use For |\n|------|---------|\n| `IEDB_search_epitopes` | Search experimentally validated epitopes |\n| `IEDB_get_epitope` | Get detailed epitope data (assay results, MHC restriction) |\n| `iedb_search_mhc` | Search validated MHC binding assay data |\n| `IEDB_predict_mhci_binding` | **Predict MHC-I binding** (NetMHCpan EL; rank \u003C 0.5% = strong binder) |\n| `IEDB_predict_mhcii_binding` | **Predict MHC-II binding** (NetMHCIIpan EL; CD4+ helper epitopes) |\n| `UniProt_get_entry_by_accession` | Get antigen protein sequence |\n| `UniProt_search` | Find pathogen protein sequences |\n| `BVBRC_search_genome_features` | Search pathogen proteomes |\n| `alphafold_get_prediction` | Get\u002Fpredict antigen 3D structure |\n| `EnsemblVEP_annotate_hgvs` | Check epitope conservation across variants |\n| `PubMed_search_articles` | Find published vaccine studies |\n| `search_clinical_trials` | Find ongoing vaccine clinical trials |\n\n---\n\n## Workflow\n\n```\nPhase 0: Antigen Selection\n  Pathogen → essential surface proteins → sequence retrieval\n    |\nPhase 1: T-Cell Epitope Prediction\n  MHC-I (CD8+ CTL) and MHC-II (CD4+ helper) binding prediction\n    |\nPhase 2: B-Cell Epitope Prediction\n  Linear and conformational B-cell epitopes for antibody response\n    |\nPhase 3: Population Coverage\n  HLA allele frequencies → design for target population\n    |\nPhase 4: Conservation Analysis\n  Cross-strain epitope conservation → broad protection\n    |\nPhase 5: Candidate Assembly & Report\n  Multi-epitope construct design → immunogenicity assessment\n```\n\n### Phase 0: Antigen Selection\n\n**Best antigens for vaccines**: Surface-exposed, essential for pathogen function, conserved across strains.\n\n```python\n# Find pathogen surface proteins\nUniProt_search(query=\"[organism] AND locations:(location:cell surface) AND reviewed:true\")\n# Or search BVBRC for annotated pathogen proteomes\nBVBRC_search_genome_features(keyword=\"surface protein\", genome_id=\"[taxon_id]\")\n```\n\n**Antigen prioritization**: prefer surface-exposed (secreted\u002Fouter membrane) over cytoplasmic; >95% conserved across strains; essential for pathogen viability; known immunogen in natural infection. Use UniProt subcellular location annotations and PubMed to verify these properties.\n\n### Phase 1: T-Cell Epitope Prediction\n\n**MHC-I epitopes** (CD8+ cytotoxic T cells — kill infected cells):\n\n```python\n# Option A: Search for KNOWN validated epitopes from IEDB\niedb_search_mhc(\n    mhc_class=\"I\",\n    qualitative_measure=\"Positive\",\n    filters={\"source_organism_iri\": \"eq.NCBITaxon:2697049\"},  # SARS-CoV-2\n    select=[\"linear_sequence\", \"mhc_restriction\", \"qualitative_measure\"],\n    limit=50\n)\n\n# Option B: PREDICT novel peptide binding (recommended for new proteins)\nIEDB_predict_mhci_binding(\n    sequence=\"YOUR_PROTEIN_SEQUENCE\",  # full protein or peptide\n    allele=\"HLA-A*02:01\",             # or H-2-Kd for mouse\n    method=\"netmhcpan_el\",            # EL = eluted ligand (recommended)\n    length=9                           # 8-11 for MHC-I\n)\n# Returns peptides ranked by percentile_rank:\n# \u003C 0.5% = strong binder (include in vaccine)\n# 0.5-2% = moderate binder (consider)\n# > 2% = weak\u002Fnon-binder (exclude)\n```\n\n**MHC-II epitopes** (CD4+ helper T cells — activate B cells and CD8+ T cells):\n\n```python\niedb_search_mhc(\n    mhc_class=\"II\",\n    qualitative_measure=\"Positive\",\n    filters={\"source_organism_iri\": \"eq.NCBITaxon:2697049\"},\n    limit=50\n)\n```\n\n**Binding affinity interpretation**:\n\n| IC50 (nM) | Classification | Vaccine Relevance |\n|-----------|---------------|-------------------|\n| \u003C 50 | Strong binder | Include — high presentation probability |\n| 50-500 | Moderate binder | Consider — may contribute to response |\n| 500-5000 | Weak binder | Exclude — unlikely to be presented |\n| > 5000 | Non-binder | Exclude |\n\n**HLA supertype strategy**: For broad coverage, predict against HLA supertypes:\n- **A2 supertype** (A*02:01, A*02:06, A*68:02) — covers ~40% globally\n- **A3 supertype** (A*03:01, A*11:01, A*31:01) — covers ~25%\n- **B7 supertype** (B*07:02, B*35:01, B*51:01) — covers ~25%\n- **A2 + A3 + B7 + B44** combined — covers >90% of most populations\n\n### Phase 2: B-Cell Epitope Prediction\n\nB-cell epitopes trigger antibody production. Look for:\n- **Linear epitopes**: Continuous peptide sequences (easier to synthesize)\n- **Conformational epitopes**: 3D surface patches (requires structural data)\n\n```python\n# Check for known B-cell epitopes\nIEDB_search_epitopes(query=\"[protein_name]\", epitope_type=\"B cell\")\n# Get structure for conformational epitope prediction\nalphafold_get_prediction(uniprot_id=\"[accession]\")\n```\n\n**B-cell epitope criteria**: Surface-exposed loops, hydrophilic regions, flexible regions (high B-factor). Combine computational prediction with structural analysis.\n\n### Phase 3: Population Coverage\n\n```python\n# Search for epitopes restricted to common HLA alleles in target population\n# NOTE: No HLA frequency tool exists in ToolUniverse. For population coverage:\n# 1. Use IEDB Analysis Resource (tools.iedb.org\u002Fpopulation) for population coverage calculation\n# 2. Use the HLA supertype strategy (see above) to ensure broad coverage\n# 3. Search PubMed for published HLA frequency data: PubMed_search_articles(query=\"HLA allele frequency [population]\")\n```\n\n**Population coverage targets**:\n\n| Coverage Level | Interpretation | Action |\n|---------------|---------------|--------|\n| >90% | Excellent — vaccine will work in most individuals | Proceed to development |\n| 70-90% | Good — most people covered; some populations underserved | Add more epitopes for uncovered HLA types |\n| 50-70% | Moderate — significant gaps | Redesign with broader HLA coverage |\n| \u003C50% | Poor — vaccine will miss too many people | Fundamental redesign needed |\n\n### Phase 4: Conservation Analysis\n\nCheck if epitopes are conserved across pathogen strains\u002Fvariants:\n\n```python\n# Search for protein variants across strains\nPubMed_search_articles(query=\"[pathogen] [protein] sequence variation strains\")\n# Check specific mutations in epitope regions\nEnsemblVEP_annotate_hgvs(hgvs_notation=\"[variant_in_epitope]\")\n```\n\n**Conservation interpretation**:\n- **100% conserved** across all known strains → ideal vaccine target\n- **>95% conserved** → good target; monitor emerging variants\n- **80-95% conserved** → may need strain-specific variants in construct\n- **\u003C80% conserved** → avoid; pathogen evolves to escape this epitope\n\n### Phase 5: Candidate Assembly & Report\n\n**Multi-epitope construct design principles**:\n1. Include 3-5 MHC-I epitopes (CD8+ response)\n2. Include 2-3 MHC-II epitopes (CD4+ helper response)\n3. Include 1-2 B-cell epitopes (antibody response)\n4. Connect with appropriate linkers (AAY for MHC-I, GPGPG for MHC-II)\n5. Add adjuvant sequence if needed (e.g., flagellin domain for TLR5)\n\n**Report structure**:\n1. **Antigen Selection** — rationale, conservation, essentiality\n2. **Epitope Map** — all predicted epitopes with binding affinities and HLA restrictions\n3. **Top Epitopes** — ranked by binding strength × conservation × population coverage\n4. **Population Coverage** — % coverage per major world population\n5. **Conservation Analysis** — strain coverage, escape risk assessment\n6. **Construct Design** — multi-epitope sequence with linkers\n7. **Clinical Precedent** — existing vaccines\u002Ftrials for related antigens\n8. **Limitations** — predicted only (T4 evidence); needs experimental validation\n\n---\n\n## Limitations\n\n- **All predictions are computational** (T4 evidence) — experimental validation (binding assays, immunogenicity studies) is required before any clinical development\n- **No immunogenicity guarantee** — MHC binding ≠ immunogenicity; many good binders are not immunogenic in vivo\n- **B-cell epitope prediction is less reliable** than T-cell; conformational epitopes require accurate structures\n- **No adjuvant optimization** — adjuvant selection requires empirical testing\n- **Pathogen evasion** — rapidly evolving pathogens (HIV, influenza) may escape epitope-based vaccines\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-vaccine-design","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-vaccine-design",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-vaccine-design",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-vaccine-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-vaccine-design\u002FSKILL.md",true,[],[70,91,120,147,161,177],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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",[],[77,78,79,80,81,82,83,84,85,37,86,87,88,89,90],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":100,"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",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[101,102,103,104,105,106,107,108,109,110,111,112,113,114,37,115,116,117,118,119],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":132,"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",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[133,134,135,136,137,138,139,140,141,142,102,143,144,145,146],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"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":153,"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",[],[149,154,155,156,157,158,159,160],"setup","report","project","installation","project setup","issues","state",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"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",[167],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},[163,169,82,170,171,172,37,173,174,175,176],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":178,"name":154,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"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",[],[154,156,117,183,158,184],"files","interactive"]