[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAWAAVCJ2WHBH6KR1P8QRH":3,"skill-same:01M6DAWAAVCJ2WHBH6KR1P8QRH":84},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6DAWAAVCJ2WHBH6KR1P8QRH","tooluniverse-protein-therapeutic-design",null,"Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design. Uses RFdiffusion for backbone generation, ProteinMPNN for sequence design, ESMFold\u002FAlphaFold2 for validation. Use when asked to design protein binders, therapeutic proteins, or engineer protein function.","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-protein-therapeutic-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],"design","tooluniverse protein therapeutic design","validation","use","engineer","enzymes","proteins","generation","2026-11-10 10:12:30",false,"---\nname: tooluniverse-protein-therapeutic-design\ndescription: Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design. Uses RFdiffusion for backbone generation, ProteinMPNN for sequence design, ESMFold\u002FAlphaFold2 for validation. Use when asked to design protein binders, therapeutic proteins, or engineer protein function.\n---\n\n# Therapeutic Protein Designer\n\nAI-guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development.\n\n**KEY PRINCIPLES**:\n1. **Structure-first** - Generate backbone geometry before sequence\n2. **Target-guided** - Design binders with target structure in mind\n3. **Iterative validation** - Predict structure to validate designs\n4. **Developability-aware** - Consider aggregation, immunogenicity, expression\n5. **Evidence-graded** - Grade designs by confidence metrics\n6. **Actionable output** - Provide sequences ready for experimental testing\n7. **English-first queries** - Always use English terms in tool calls\n\nTherapeutic protein design starts with the target interaction. What binding surface do you need to cover? A small pocket = nanobody or peptide. A large flat surface = designed protein. Stability, immunogenicity, and manufacturability constrain the design space.\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\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## When to Use\n\nApply when user asks to:\n- Design a protein binder, therapeutic protein, or scaffold\n- Optimize a protein sequence for function\n- Design a de novo enzyme\n- Generate protein variants for target binding\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Target Characterization\n  Get structure (PDB, EMDB cryo-EM, AlphaFold), identify binding epitope\n\nPhase 2: Backbone Generation (RFdiffusion)\n  Define constraints, generate >= 5 backbones, filter by geometry\n\nPhase 3: Sequence Design (ProteinMPNN)\n  Design >= 8 sequences per backbone, sample with temperature control\n\nPhase 4: Structure Validation (ESMFold\u002FAlphaFold2)\n  Predict structure, compare to backbone, assess pLDDT\u002FpTM\n\nPhase 5: Developability Assessment\n  Aggregation, pI, expression prediction\n\nPhase 6: Report Synthesis\n  Ranked candidates, FASTA, experimental recommendations\n```\n\n---\n\n## Critical Requirements\n\n### Report-First Approach (MANDATORY)\n1. Create `[TARGET]_protein_design_report.md` first with section headers\n2. Progressively update as designs are generated\n3. Output `[TARGET]_designed_sequences.fasta` and `[TARGET]_top_candidates.csv`\n\n### Design Documentation (MANDATORY)\nEvery design MUST include: Sequence, Length, Target, Method, and Quality Metrics (pLDDT, pTM, MPNN score, binding prediction).\n\n---\n\n## NVIDIA NIM Tools\n\n| Tool | Purpose | Key Parameter |\n|------|---------|---------------|\n| `NvidiaNIM_rfdiffusion` | Backbone generation | `diffusion_steps` (NOT `num_steps`) |\n| `NvidiaNIM_proteinmpnn` | Sequence design | `pdb_string` (NOT `pdb`) |\n| `ESMFold_predict_structure` | Fast validation | `sequence` (NOT `seq`) |\n| `NvidiaNIM_alphafold2` | High-accuracy validation | `sequence`, `algorithm` |\n| `NvidiaNIM_esm2_650m` | Sequence embeddings | `sequences`, `format` |\n\n### Common Parameter Mistakes\n\n| Tool | Wrong | Correct |\n|------|-------|---------|\n| `NvidiaNIM_rfdiffusion` | `num_steps=50` | `diffusion_steps=50` |\n| `NvidiaNIM_proteinmpnn` | `pdb=content` | `pdb_string=content` |\n| `ESMFold_predict_structure` | `seq=\"MVLS...\"` | `sequence=\"MVLS...\"` |\n| `NvidiaNIM_alphafold2` | `seq=\"MVLS...\"` | `sequence=\"MVLS...\"` |\n\n### NVIDIA NIM Requirements\n- **API Key**: `NVIDIA_API_KEY` environment variable required\n- **Rate limits**: 40 RPM (1.5 second minimum between calls)\n- AlphaFold2 may return 202 (polling required); RFdiffusion and ESMFold are synchronous\n\n---\n\n## Supporting Tools\n\n| Tool | Purpose | Key Parameters |\n|------|---------|----------------|\n| `PDBe_get_uniprot_mappings` | Find PDB structures | `uniprot_id` |\n| `RCSBData_get_entry` | Download PDB file | `pdb_id` |\n| `alphafold_get_prediction` | Get AlphaFold DB structure | `accession` |\n| `emdb_search` | Search cryo-EM maps | `query` |\n| `emdb_get_entry` | Get entry details | `entry_id` |\n| `UniProt_get_entry_by_accession` | Get target sequence | `accession` |\n| `InterPro_get_protein_domains` | Get domains | `accession` |\n\n---\n\n## Evidence Grading\n\n| Tier | Criteria |\n|------|----------|\n| T1 (best) | pLDDT >85, pTM >0.8, low aggregation, neutral pI |\n| T2 | pLDDT >75, pTM >0.7, acceptable developability |\n| T3 | pLDDT >70, pTM >0.65, developability concerns |\n| T4 | Failed validation or major developability issues |\n\n---\n\n## Completeness Checklist\n\n- [ ] Target structure obtained (PDB or predicted)\n- [ ] Binding epitope identified\n- [ ] >= 5 backbones generated, top 3-5 selected\n- [ ] >= 8 sequences per backbone, MPNN scores reported\n- [ ] All sequences validated (ESMFold), pLDDT\u002FpTM reported, >= 3 passing\n- [ ] Developability assessed (aggregation, pI, expression)\n- [ ] Ranked candidate list, FASTA file, experimental recommendations\n\n---\n\n## Reference Files\n\n- **DESIGN_PROCEDURES.md** - Phase-by-phase code examples, sampling parameters, fallback chains\n- **TOOLS_REFERENCE.md** - Complete tool documentation with code examples\n- **EXAMPLES.md** - Sample design workflows and outputs\n- **CHECKLIST.md** - Detailed phase checklists and quality metrics\n- **design_templates.md** - Report templates and output format examples\n","# Therapeutic Protein Designer\n\nAI-guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development.\n\n**KEY PRINCIPLES**:\n1. **Structure-first** - Generate backbone geometry before sequence\n2. **Target-guided** - Design binders with target structure in mind\n3. **Iterative validation** - Predict structure to validate designs\n4. **Developability-aware** - Consider aggregation, immunogenicity, expression\n5. **Evidence-graded** - Grade designs by confidence metrics\n6. **Actionable output** - Provide sequences ready for experimental testing\n7. **English-first queries** - Always use English terms in tool calls\n\nTherapeutic protein design starts with the target interaction. What binding surface do you need to cover? A small pocket = nanobody or peptide. A large flat surface = designed protein. Stability, immunogenicity, and manufacturability constrain the design space.\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\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## When to Use\n\nApply when user asks to:\n- Design a protein binder, therapeutic protein, or scaffold\n- Optimize a protein sequence for function\n- Design a de novo enzyme\n- Generate protein variants for target binding\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Target Characterization\n  Get structure (PDB, EMDB cryo-EM, AlphaFold), identify binding epitope\n\nPhase 2: Backbone Generation (RFdiffusion)\n  Define constraints, generate >= 5 backbones, filter by geometry\n\nPhase 3: Sequence Design (ProteinMPNN)\n  Design >= 8 sequences per backbone, sample with temperature control\n\nPhase 4: Structure Validation (ESMFold\u002FAlphaFold2)\n  Predict structure, compare to backbone, assess pLDDT\u002FpTM\n\nPhase 5: Developability Assessment\n  Aggregation, pI, expression prediction\n\nPhase 6: Report Synthesis\n  Ranked candidates, FASTA, experimental recommendations\n```\n\n---\n\n## Critical Requirements\n\n### Report-First Approach (MANDATORY)\n1. Create `[TARGET]_protein_design_report.md` first with section headers\n2. Progressively update as designs are generated\n3. Output `[TARGET]_designed_sequences.fasta` and `[TARGET]_top_candidates.csv`\n\n### Design Documentation (MANDATORY)\nEvery design MUST include: Sequence, Length, Target, Method, and Quality Metrics (pLDDT, pTM, MPNN score, binding prediction).\n\n---\n\n## NVIDIA NIM Tools\n\n| Tool | Purpose | Key Parameter |\n|------|---------|---------------|\n| `NvidiaNIM_rfdiffusion` | Backbone generation | `diffusion_steps` (NOT `num_steps`) |\n| `NvidiaNIM_proteinmpnn` | Sequence design | `pdb_string` (NOT `pdb`) |\n| `ESMFold_predict_structure` | Fast validation | `sequence` (NOT `seq`) |\n| `NvidiaNIM_alphafold2` | High-accuracy validation | `sequence`, `algorithm` |\n| `NvidiaNIM_esm2_650m` | Sequence embeddings | `sequences`, `format` |\n\n### Common Parameter Mistakes\n\n| Tool | Wrong | Correct |\n|------|-------|---------|\n| `NvidiaNIM_rfdiffusion` | `num_steps=50` | `diffusion_steps=50` |\n| `NvidiaNIM_proteinmpnn` | `pdb=content` | `pdb_string=content` |\n| `ESMFold_predict_structure` | `seq=\"MVLS...\"` | `sequence=\"MVLS...\"` |\n| `NvidiaNIM_alphafold2` | `seq=\"MVLS...\"` | `sequence=\"MVLS...\"` |\n\n### NVIDIA NIM Requirements\n- **API Key**: `NVIDIA_API_KEY` environment variable required\n- **Rate limits**: 40 RPM (1.5 second minimum between calls)\n- AlphaFold2 may return 202 (polling required); RFdiffusion and ESMFold are synchronous\n\n---\n\n## Supporting Tools\n\n| Tool | Purpose | Key Parameters |\n|------|---------|----------------|\n| `PDBe_get_uniprot_mappings` | Find PDB structures | `uniprot_id` |\n| `RCSBData_get_entry` | Download PDB file | `pdb_id` |\n| `alphafold_get_prediction` | Get AlphaFold DB structure | `accession` |\n| `emdb_search` | Search cryo-EM maps | `query` |\n| `emdb_get_entry` | Get entry details | `entry_id` |\n| `UniProt_get_entry_by_accession` | Get target sequence | `accession` |\n| `InterPro_get_protein_domains` | Get domains | `accession` |\n\n---\n\n## Evidence Grading\n\n| Tier | Criteria |\n|------|----------|\n| T1 (best) | pLDDT >85, pTM >0.8, low aggregation, neutral pI |\n| T2 | pLDDT >75, pTM >0.7, acceptable developability |\n| T3 | pLDDT >70, pTM >0.65, developability concerns |\n| T4 | Failed validation or major developability issues |\n\n---\n\n## Completeness Checklist\n\n- [ ] Target structure obtained (PDB or predicted)\n- [ ] Binding epitope identified\n- [ ] >= 5 backbones generated, top 3-5 selected\n- [ ] >= 8 sequences per backbone, MPNN scores reported\n- [ ] All sequences validated (ESMFold), pLDDT\u002FpTM reported, >= 3 passing\n- [ ] Developability assessed (aggregation, pI, expression)\n- [ ] Ranked candidate list, FASTA file, experimental recommendations\n\n---\n\n## Reference Files\n\n- **DESIGN_PROCEDURES.md** - Phase-by-phase code examples, sampling parameters, fallback chains\n- **TOOLS_REFERENCE.md** - Complete tool documentation with code examples\n- **EXAMPLES.md** - Sample design workflows and outputs\n- **CHECKLIST.md** - Detailed phase checklists and quality metrics\n- **design_templates.md** - Report templates and output format examples\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-protein-therapeutic-design",{"tool":54,"command":55},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-protein-therapeutic-design",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-protein-therapeutic-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-design\u002FSKILL.md",true,[62,68,72,76,80],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"CHECKLIST.md","REFERENCE","参考文档",6775,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-design\u002FCHECKLIST.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"DESIGN_PROCEDURES.md",3331,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-design\u002FDESIGN_PROCEDURES.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"design_templates.md",2906,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-design\u002Fdesign_templates.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"EXAMPLES.md",10976,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-design\u002FEXAMPLES.md",{"path":81,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":82,"sourceHtmlUrl":83},"TOOLS_REFERENCE.md",13253,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-protein-therapeutic-design\u002FTOOLS_REFERENCE.md",[85,106,135,162,176,192],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":37},"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",[],[92,93,94,95,96,97,98,99,100,32,101,102,103,104,105],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"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":37},"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",[116,117,118,119,120,121,122,123,124,125,126,127,128,129,32,130,131,132,133,134],"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":37},"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":37},"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",[],[164,169,170,171,172,173,174,175],"setup","report","project","installation","project setup","issues","state",{"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":183,"publishedAt":37},"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",[182],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},[178,184,97,185,186,187,32,188,189,190,191],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":193,"name":169,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":37},"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",[],[169,171,132,198,173,199],"files","interactive"]