[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBPRR5KBC0407GS26K2GPY":3,"skill-same:01M6DBPRR5KBC0407GS26K2GPY":97},{"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":18,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6DBPRR5KBC0407GS26K2GPY","protein-interaction-network-analysis",null,"Use when analyzing protein interaction networks, confidence scores, functional enrichment, or structural context with STRING, BioGRID, and SASBDB.","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\u002Fskills\u002Fprotein-interaction-network-analysis\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"network","analysis","protein interaction network analysis","analyzing","enrichment","networks","context","use","structural","2026-11-10 10:12:30",false,"---\nname: protein-interaction-network-analysis\ndescription: \"Use when analyzing protein interaction networks, confidence scores, functional enrichment, or structural context with STRING, BioGRID, and SASBDB.\"\n---\n\n# Protein Interaction Network Analysis\n\nComprehensive protein interaction network analysis using ToolUniverse tools. Analyzes protein networks through a 4-phase workflow: identifier mapping, network retrieval, enrichment analysis, and optional structural data.\n\n## Domain Reasoning: Interaction Type Clarification\n\nWhen asked about protein interactions, ask: physical interaction (do they bind?) or functional interaction (do they affect the same pathway)? STRING combines both — a high combined_score does not mean physical binding. For physical binding evidence, check the experimental score (`escore`) specifically. A high `tscore` (text mining) or `dscore` (database) with a low `escore` suggests co-annotation or co-citation, not direct binding.\n\nLOOK UP DON'T GUESS: protein interaction scores, experimental evidence types, and whether two specific proteins have known co-crystal structures. Use STRING `escore` and BioGRID experimental data — do not infer binding from pathway co-membership alone.\n\n## Databases Used\n\n| Database | Coverage | API Key | Purpose |\n|----------|----------|---------|---------|\n| **STRING** | 14M+ proteins, 5,000+ organisms | Not required | Primary interaction source |\n| **BioGRID** | 2.3M+ interactions, 80+ organisms | Required | Fallback, curated data |\n| **SASBDB** | 2,000+ SAXS\u002FSANS entries | Not required | Solution structures |\n\n## 4-Phase Workflow\n\n1. **Identifier Mapping** — `STRING_map_identifiers()`: validate protein names, get STRING IDs\n2. **Network Retrieval** — `STRING_get_network()` (primary); `BioGRID_get_interactions()` (fallback, requires API key)\n3. **Enrichment Analysis** — `STRING_functional_enrichment()` for GO\u002FKEGG\u002FReactome; `STRING_ppi_enrichment()` to test functional coherence\n4. **Structural Data (optional)** — `SASBDB_search_entries()` for SAXS\u002FSANS solution structures\n\nSee `python_implementation.py` for runnable examples (`example_tp53_analysis()`, `analyze_protein_network()`).\n\n## Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `proteins` | Required | Gene symbols or UniProt IDs |\n| `species` | 9606 | NCBI taxonomy ID |\n| `confidence_score` | 0.7 | Min interaction confidence (0–1) |\n| `include_biogrid` | False | BioGRID fallback (requires API key) |\n| `include_structure` | False | SASBDB structural data (slower) |\n\n### Confidence Score Guidelines\n\n| Score | Use Case |\n|-------|----------|\n| 0.4 | Exploratory analysis (default STRING threshold) |\n| 0.7 | Recommended — reliable interactions |\n| 0.9 | Core interactions only |\n\n## Network Edge Fields (STRING)\n\nKey fields returned per interaction edge:\n- `score` — combined confidence (0–1)\n- `escore` — experimental score (use for physical binding evidence)\n- `dscore` — database score\n- `tscore` — text mining score\n- `ascore` — coexpression score\n- `preferredName_A`, `preferredName_B` — gene names\n\n## Extended Analysis Tools\n\n**Signaling Pathways:**\n- `OmniPath_get_signaling_interactions` — directed, signed PPI (stimulation\u002Finhibition)\n- `Reactome_map_uniprot_to_pathways` — map proteins to Reactome pathways (param: `uniprot_id`)\n- `ReactomeAnalysis_pathway_enrichment` — pathway enrichment for gene sets\n\n**Druggability & Clinical Context:**\n- `DGIdb_get_drug_gene_interactions` — drug interactions for hub proteins (param: `genes` as array)\n- `DGIdb_get_gene_druggability` — druggability categories\n- `gnomad_get_gene_constraints` — gene essentiality metrics (pLI, oe_lof)\n- `civic_search_evidence_items` — clinical evidence for mutations in network proteins\n- `UniProt_get_function_by_accession` — protein function annotation\n\n## Tool-Specific Notes\n\n### IntAct Interaction Data\n\n`interaction_ids` are in the `metadata` field of the response, NOT at the top level:\n```python\ninteraction_ids = result.get(\"metadata\", {}).get(\"interaction_ids\", [])\n```\n\n### BioGRID Chemical Interactions\n\n`BioGRID_get_chemical_interactions` always includes a limitation note — chemical interaction coverage may be incomplete. Defaults to `taxId=9606` (human) when no organism is provided.\n\n### IntAct `protein_name` Alias\n\nIntAct tools accept `protein_name` as an alias parameter in addition to the original identifier parameter.\n\n## Domain Reasoning: Multimeric Assemblies & Binding Valency\n\nLOOK UP DON'T GUESS: oligomeric state, subunit stoichiometry, and binding valency. Use RCSB PDB (`RCSB_search_structures`, `RCSB_get_entry_info`) or UniProt (`UniProt_get_function_by_accession`) to confirm whether a protein is a monomer, dimer, trimer, etc. Do not assume from gene name alone.\n\n### Calculating Multimer Valency from Binding Data\n\n**Valency** = number of independent binding sites on a multimeric complex. A homodimer with one binding site per subunit has valency 2. A pentamer (e.g., IgM) with 2 Fab arms each has valency 10.\n\nKey reasoning steps:\n1. **Determine oligomeric state**: Look up quaternary structure in PDB\u002FUniProt. A \"dimer\" in solution may be a dimer-of-dimers (tetramer) crystallographically.\n2. **Count binding sites per subunit**: Each subunit contributes independently unless the binding site spans the interface (then the complex itself is the functional unit).\n3. **Valency = subunits x sites_per_subunit** (only if sites are independent). If binding at one site affects another, you have cooperativity, not simple valency.\n4. **Avidity vs affinity**: A multivalent complex binds more tightly than a single site (avidity effect). Apparent Kd_multivalent \u003C\u003C Kd_monovalent. The enhancement depends on linker flexibility and target geometry.\n\n### Statistical Factors in Multimeric Binding\n\nWhen a symmetric multimer binds a ligand, **statistical factors** affect the apparent rate constants:\n- **First ligand binding**: kon_apparent = n x kon_intrinsic (n equivalent sites available)\n- **First ligand dissociation**: koff_apparent = koff_intrinsic (only one ligand to dissociate)\n- **General rule**: For a multimer with n identical sites, binding to the i-th site has forward statistical factor (n - i + 1) and reverse statistical factor i.\n- **Macroscopic vs microscopic Kd**: Kd_macro(1st site) = Kd_micro \u002F n. Kd_macro(last site) = n x Kd_micro. The ratio Kd_last \u002F Kd_first = n^2 for non-cooperative binding.\n\nIf measured Kd values deviate from these statistical predictions, the protein shows **positive cooperativity** (Kd decreases more than expected) or **negative cooperativity** (Kd increases more than expected).\n\n### When to Use Binding Curve Analysis vs Stoichiometry\n\n| Approach | Use when | What it tells you |\n|----------|----------|-------------------|\n| **Stoichiometry** (ITC, AUC, SEC-MALS) | You need the number of binding partners per complex | n (sites), not affinity |\n| **Binding curves** (SPR, FP, ELISA) | You need Kd and kinetics | Affinity, but apparent Kd conflates valency and cooperativity |\n| **Hill plot** (log-log binding curve) | You suspect cooperativity | Hill coefficient nH: nH=1 non-cooperative, nH>1 positive, nH\u003C1 negative |\n| **Scatchard plot** (bound\u002Ffree vs bound) | Classic approach, now less common | Curved = multiple site classes or cooperativity; linear = single Kd |\n\n**Obligate vs facultative multimers**: An obligate dimer (e.g., many kinases) has NO monomeric activity. If your \"purified protein\" shows no activity, check if dimer formation is required. Use SEC or native PAGE to confirm oligomeric state. Low protein concentration, high salt, or wrong pH can dissociate obligate multimers.\n\n## Domain Reasoning: Coiled-Coil Oligomeric State Prediction\n\n- **Heptad repeat**: (abcdefg)n where positions a and d are hydrophobic core residues.\n- **Oligomeric state from packing**: dimer (leucine zipper, Leu at d), trimer (Ile\u002FVal at a, Leu at d), tetramer (Leu at both a+d), pentamer (complex mixed packing, e.g., Trp or polar residues at a).\n- **Heptad net diagram**: map residues onto helical wheel; a+d form the hydrophobic core interface. The identity of a\u002Fd residues determines packing geometry and thus oligomeric state.\n- **Polar residues at a\u002Fd** (Asn, Gln) specify parallel vs antiparallel orientation and can select for specific oligomeric states.\n- LOOK UP: search PubMed for \"[sequence motif] coiled coil oligomeric state\" and check CC+ or SOCKET databases before predicting oligomeric state from sequence alone.\n\n## Domain Reasoning: Detergent Effects on Membrane Proteins\n\n- **Mild detergents** (DDM, LMNG, CHAPS, digitonin) preserve native oligomeric state and lipid interactions; preferred for structural studies.\n- **Harsh detergents** (SDS, OG at high concentration above CMC) can dissociate native complexes and strip stabilizing lipids.\n- **Native MS in different detergents** reveals whether specific lipids stabilize oligomeric assemblies; comparing CHAPS vs OG results distinguishes detergent-stable from lipid-dependent oligomers.\n\n## Protein Identification Questions\n\nFor \"what protein does X\" questions: ALWAYS search UniProt and PubMed first — do not guess from memory. Key pathways to know:\n- **Amyloid clearance**: collagen degradation by matrix metalloproteinases is required to expose amyloid deposits, allowing macrophage engulfment. The answer is collagen, not serum amyloid P (SAP) or other amyloid-binding proteins.\n- When a question asks \"what protein\", give JUST the protein name — no abbreviations, descriptions, or qualifications.\n\n## Troubleshooting\n\n- **No interactions found**: verify protein names (case-sensitive), try `confidence_score=0.4`\n- **BioGRID not working**: set `BIOGRID_API_KEY` in environment; STRING works without a key\n- **Verbose output**: filter with `2>&1 | grep -v \"Error loading tools\"` (see KNOWN_ISSUES.md)\n\n## References\n\n- STRING: https:\u002F\u002Fstring-db.org\u002F\n- BioGRID: https:\u002F\u002Fthebiogrid.org\u002F (register for free API key)\n- SASBDB: https:\u002F\u002Fwww.sasbdb.org\u002F\n- ToolUniverse: https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FToolUniverse\n","# Protein Interaction Network Analysis\n\nComprehensive protein interaction network analysis using ToolUniverse tools. Analyzes protein networks through a 4-phase workflow: identifier mapping, network retrieval, enrichment analysis, and optional structural data.\n\n## Domain Reasoning: Interaction Type Clarification\n\nWhen asked about protein interactions, ask: physical interaction (do they bind?) or functional interaction (do they affect the same pathway)? STRING combines both — a high combined_score does not mean physical binding. For physical binding evidence, check the experimental score (`escore`) specifically. A high `tscore` (text mining) or `dscore` (database) with a low `escore` suggests co-annotation or co-citation, not direct binding.\n\nLOOK UP DON'T GUESS: protein interaction scores, experimental evidence types, and whether two specific proteins have known co-crystal structures. Use STRING `escore` and BioGRID experimental data — do not infer binding from pathway co-membership alone.\n\n## Databases Used\n\n| Database | Coverage | API Key | Purpose |\n|----------|----------|---------|---------|\n| **STRING** | 14M+ proteins, 5,000+ organisms | Not required | Primary interaction source |\n| **BioGRID** | 2.3M+ interactions, 80+ organisms | Required | Fallback, curated data |\n| **SASBDB** | 2,000+ SAXS\u002FSANS entries | Not required | Solution structures |\n\n## 4-Phase Workflow\n\n1. **Identifier Mapping** — `STRING_map_identifiers()`: validate protein names, get STRING IDs\n2. **Network Retrieval** — `STRING_get_network()` (primary); `BioGRID_get_interactions()` (fallback, requires API key)\n3. **Enrichment Analysis** — `STRING_functional_enrichment()` for GO\u002FKEGG\u002FReactome; `STRING_ppi_enrichment()` to test functional coherence\n4. **Structural Data (optional)** — `SASBDB_search_entries()` for SAXS\u002FSANS solution structures\n\nSee `python_implementation.py` for runnable examples (`example_tp53_analysis()`, `analyze_protein_network()`).\n\n## Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `proteins` | Required | Gene symbols or UniProt IDs |\n| `species` | 9606 | NCBI taxonomy ID |\n| `confidence_score` | 0.7 | Min interaction confidence (0–1) |\n| `include_biogrid` | False | BioGRID fallback (requires API key) |\n| `include_structure` | False | SASBDB structural data (slower) |\n\n### Confidence Score Guidelines\n\n| Score | Use Case |\n|-------|----------|\n| 0.4 | Exploratory analysis (default STRING threshold) |\n| 0.7 | Recommended — reliable interactions |\n| 0.9 | Core interactions only |\n\n## Network Edge Fields (STRING)\n\nKey fields returned per interaction edge:\n- `score` — combined confidence (0–1)\n- `escore` — experimental score (use for physical binding evidence)\n- `dscore` — database score\n- `tscore` — text mining score\n- `ascore` — coexpression score\n- `preferredName_A`, `preferredName_B` — gene names\n\n## Extended Analysis Tools\n\n**Signaling Pathways:**\n- `OmniPath_get_signaling_interactions` — directed, signed PPI (stimulation\u002Finhibition)\n- `Reactome_map_uniprot_to_pathways` — map proteins to Reactome pathways (param: `uniprot_id`)\n- `ReactomeAnalysis_pathway_enrichment` — pathway enrichment for gene sets\n\n**Druggability & Clinical Context:**\n- `DGIdb_get_drug_gene_interactions` — drug interactions for hub proteins (param: `genes` as array)\n- `DGIdb_get_gene_druggability` — druggability categories\n- `gnomad_get_gene_constraints` — gene essentiality metrics (pLI, oe_lof)\n- `civic_search_evidence_items` — clinical evidence for mutations in network proteins\n- `UniProt_get_function_by_accession` — protein function annotation\n\n## Tool-Specific Notes\n\n### IntAct Interaction Data\n\n`interaction_ids` are in the `metadata` field of the response, NOT at the top level:\n```python\ninteraction_ids = result.get(\"metadata\", {}).get(\"interaction_ids\", [])\n```\n\n### BioGRID Chemical Interactions\n\n`BioGRID_get_chemical_interactions` always includes a limitation note — chemical interaction coverage may be incomplete. Defaults to `taxId=9606` (human) when no organism is provided.\n\n### IntAct `protein_name` Alias\n\nIntAct tools accept `protein_name` as an alias parameter in addition to the original identifier parameter.\n\n## Domain Reasoning: Multimeric Assemblies & Binding Valency\n\nLOOK UP DON'T GUESS: oligomeric state, subunit stoichiometry, and binding valency. Use RCSB PDB (`RCSB_search_structures`, `RCSB_get_entry_info`) or UniProt (`UniProt_get_function_by_accession`) to confirm whether a protein is a monomer, dimer, trimer, etc. Do not assume from gene name alone.\n\n### Calculating Multimer Valency from Binding Data\n\n**Valency** = number of independent binding sites on a multimeric complex. A homodimer with one binding site per subunit has valency 2. A pentamer (e.g., IgM) with 2 Fab arms each has valency 10.\n\nKey reasoning steps:\n1. **Determine oligomeric state**: Look up quaternary structure in PDB\u002FUniProt. A \"dimer\" in solution may be a dimer-of-dimers (tetramer) crystallographically.\n2. **Count binding sites per subunit**: Each subunit contributes independently unless the binding site spans the interface (then the complex itself is the functional unit).\n3. **Valency = subunits x sites_per_subunit** (only if sites are independent). If binding at one site affects another, you have cooperativity, not simple valency.\n4. **Avidity vs affinity**: A multivalent complex binds more tightly than a single site (avidity effect). Apparent Kd_multivalent \u003C\u003C Kd_monovalent. The enhancement depends on linker flexibility and target geometry.\n\n### Statistical Factors in Multimeric Binding\n\nWhen a symmetric multimer binds a ligand, **statistical factors** affect the apparent rate constants:\n- **First ligand binding**: kon_apparent = n x kon_intrinsic (n equivalent sites available)\n- **First ligand dissociation**: koff_apparent = koff_intrinsic (only one ligand to dissociate)\n- **General rule**: For a multimer with n identical sites, binding to the i-th site has forward statistical factor (n - i + 1) and reverse statistical factor i.\n- **Macroscopic vs microscopic Kd**: Kd_macro(1st site) = Kd_micro \u002F n. Kd_macro(last site) = n x Kd_micro. The ratio Kd_last \u002F Kd_first = n^2 for non-cooperative binding.\n\nIf measured Kd values deviate from these statistical predictions, the protein shows **positive cooperativity** (Kd decreases more than expected) or **negative cooperativity** (Kd increases more than expected).\n\n### When to Use Binding Curve Analysis vs Stoichiometry\n\n| Approach | Use when | What it tells you |\n|----------|----------|-------------------|\n| **Stoichiometry** (ITC, AUC, SEC-MALS) | You need the number of binding partners per complex | n (sites), not affinity |\n| **Binding curves** (SPR, FP, ELISA) | You need Kd and kinetics | Affinity, but apparent Kd conflates valency and cooperativity |\n| **Hill plot** (log-log binding curve) | You suspect cooperativity | Hill coefficient nH: nH=1 non-cooperative, nH>1 positive, nH\u003C1 negative |\n| **Scatchard plot** (bound\u002Ffree vs bound) | Classic approach, now less common | Curved = multiple site classes or cooperativity; linear = single Kd |\n\n**Obligate vs facultative multimers**: An obligate dimer (e.g., many kinases) has NO monomeric activity. If your \"purified protein\" shows no activity, check if dimer formation is required. Use SEC or native PAGE to confirm oligomeric state. Low protein concentration, high salt, or wrong pH can dissociate obligate multimers.\n\n## Domain Reasoning: Coiled-Coil Oligomeric State Prediction\n\n- **Heptad repeat**: (abcdefg)n where positions a and d are hydrophobic core residues.\n- **Oligomeric state from packing**: dimer (leucine zipper, Leu at d), trimer (Ile\u002FVal at a, Leu at d), tetramer (Leu at both a+d), pentamer (complex mixed packing, e.g., Trp or polar residues at a).\n- **Heptad net diagram**: map residues onto helical wheel; a+d form the hydrophobic core interface. The identity of a\u002Fd residues determines packing geometry and thus oligomeric state.\n- **Polar residues at a\u002Fd** (Asn, Gln) specify parallel vs antiparallel orientation and can select for specific oligomeric states.\n- LOOK UP: search PubMed for \"[sequence motif] coiled coil oligomeric state\" and check CC+ or SOCKET databases before predicting oligomeric state from sequence alone.\n\n## Domain Reasoning: Detergent Effects on Membrane Proteins\n\n- **Mild detergents** (DDM, LMNG, CHAPS, digitonin) preserve native oligomeric state and lipid interactions; preferred for structural studies.\n- **Harsh detergents** (SDS, OG at high concentration above CMC) can dissociate native complexes and strip stabilizing lipids.\n- **Native MS in different detergents** reveals whether specific lipids stabilize oligomeric assemblies; comparing CHAPS vs OG results distinguishes detergent-stable from lipid-dependent oligomers.\n\n## Protein Identification Questions\n\nFor \"what protein does X\" questions: ALWAYS search UniProt and PubMed first — do not guess from memory. Key pathways to know:\n- **Amyloid clearance**: collagen degradation by matrix metalloproteinases is required to expose amyloid deposits, allowing macrophage engulfment. The answer is collagen, not serum amyloid P (SAP) or other amyloid-binding proteins.\n- When a question asks \"what protein\", give JUST the protein name — no abbreviations, descriptions, or qualifications.\n\n## Troubleshooting\n\n- **No interactions found**: verify protein names (case-sensitive), try `confidence_score=0.4`\n- **BioGRID not working**: set `BIOGRID_API_KEY` in environment; STRING works without a key\n- **Verbose output**: filter with `2>&1 | grep -v \"Error loading tools\"` (see KNOWN_ISSUES.md)\n\n## References\n\n- STRING: https:\u002F\u002Fstring-db.org\u002F\n- BioGRID: https:\u002F\u002Fthebiogrid.org\u002F (register for free API key)\n- SASBDB: https:\u002F\u002Fwww.sasbdb.org\u002F\n- ToolUniverse: https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FToolUniverse\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fprotein-interaction-network-analysis","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill protein-interaction-network-analysis",{"tool":45,"command":46},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill protein-interaction-network-analysis",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill protein-interaction-network-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FSKILL.md",true,[53,59,63,67,71,75,81,85,89,93],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"DESCRIPTION_UPDATE_COMPLETE.md","REFERENCE","参考文档",1945,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FDESCRIPTION_UPDATE_COMPLETE.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"DESCRIPTION_UPDATE_PROGRESS.md",5104,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FDESCRIPTION_UPDATE_PROGRESS.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"DOMAIN_ANALYSIS.md",13066,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FDOMAIN_ANALYSIS.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"KNOWN_ISSUES.md",3505,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FKNOWN_ISSUES.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"PHASE2_DISCOVERIES.md",7377,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FPHASE2_DISCOVERIES.md",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"python_implementation.py","SCRIPT","脚本",15004,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002Fpython_implementation.py",{"path":82,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":83,"sourceHtmlUrl":84},"QUICK_START.md",4101,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FQUICK_START.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"test_protein_tools.py",14520,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002Ftest_protein_tools.py",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"test_skill_comprehensive.py",20143,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002Ftest_skill_comprehensive.py",{"path":94,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":95,"sourceHtmlUrl":96},"TOOL_DESCRIPTION_OPTIMIZATION.md",22106,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprotein-interaction-network-analysis\u002FTOOL_DESCRIPTION_OPTIMIZATION.md",[98,118,149,176,190,206],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":28},"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",[],[105,106,107,108,109,110,111,112,113,26,25,114,115,116,117],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","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":129,"publishedAt":28},"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":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[130,131,132,133,134,135,136,137,138,139,140,141,142,143,26,144,145,146,147,148],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":161,"publishedAt":28},"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",[155,158],{"categoryNo":156,"categoryName":157,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":159,"categoryName":160,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000008","测试与质量",[162,163,164,165,166,167,168,169,170,171,131,172,173,174,175],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":177,"name":178,"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":28},"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",[],[178,183,184,185,186,187,188,189],"setup","report","project","installation","project setup","issues","state",{"skillNo":191,"name":192,"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":197,"publishedAt":28},"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",[196],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},[192,198,110,199,200,201,26,202,203,204,205],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":207,"name":183,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":28},"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",[],[183,185,146,212,187,213],"files","interactive"]