[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DE41BHQRW7QAYRZF22110P":3,"skill-same:01M6DE41BHQRW7QAYRZF22110P":70},{"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":26,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":14,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6DE41BHQRW7QAYRZF22110P","ddi-admet-research",null,"Use as the front-end\u002Frouter for biomedical research via the tooluniverse MCP server (Harvard Zitnik lab, 2206 tools) - drug-drug interactions, ADMET\u002Fphyschem prediction, CYP450 enzyme roles, target research, FDA drug labels, drug repurposing, and pharmacovigilance. Routes to the detailed tooluniverse-* skills. Use when a question needs biomedical knowledge-base lookups.","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\u002Fskills\u002Fddi-admet-research\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"research","ddi admet research","fda","tooluniverse","as","end","roles","biomedical","knowledge-base","base","MCP","router","use","question","knowledge","Tools","server","mcp server","2026-11-10 10:12:30",false,"---\nname: ddi-admet-research\ndescription: Use as the front-end\u002Frouter for biomedical research via the tooluniverse MCP server (Harvard Zitnik lab, 2206 tools) - drug-drug interactions, ADMET\u002Fphyschem prediction, CYP450 enzyme roles, target research, FDA drug labels, drug repurposing, and pharmacovigilance. Routes to the detailed tooluniverse-* skills. Use when a question needs biomedical knowledge-base lookups.\n---\n\n# DDI \u002F ADMET Research (ToolUniverse front-end)\n\n## Overview\n\nThis skill is a THIN ROUTER over the `tooluniverse` MCP server and the already-installed `tooluniverse-*` deep skills. Do NOT re-implement DDI\u002FADMET reasoning here - dispatch to the specialized skill, then call ToolUniverse tools.\n\n- Server: ToolUniverse (Apache-2.0, Harvard Zitnik lab), 2206 biomedical tools covering DDI, ADMET, CYP, targets, FDA labels, repurposing, and pharmacovigilance.\n- Registration (verified, stdio): command `uvx`, args `tooluniverse==1.2.4`, env `PYTHONIOENCODING` = `utf-8`. The stdio entry point is `tooluniverse.smcp_server:run_default_stdio_server`.\n- Cross-platform: `uvx` works on Windows and POSIX identically; no path edits needed.\n\n## Route to the Right Installed Skill\n\nDeep, ready-made skills already live at `~\u002F.agents\u002Fskills` (on Windows: `C:\\Users\\Prekzursil\\.agents\\skills`). Pick by intent:\n\n- Drug-drug interactions, polypharmacy, CYP\u002FUGT mechanisms -> `tooluniverse-drug-drug-interaction`\n- ADMET \u002F physicochemical \u002F drug-likeness prediction -> `tooluniverse-admet-prediction`\n- Hazard, GHS, handling, exposure -> `tooluniverse-chemical-safety`\n- Target identification \u002F validation -> `tooluniverse-target-research`\n- Repositioning \u002F new indications -> `tooluniverse-drug-repurposing`\n- Adverse events, signal detection, post-market safety -> `tooluniverse-pharmacovigilance`\n- Mechanism of action -> `tooluniverse-drug-mechanism-research`\n\nInvoke the matching skill first; this front-end only handles routing + the connection.\n\n## Real ToolUniverse Tools (verified in use)\n\nOnly call tools you can confirm exist. Confirmed from the installed DDI skill:\n\n- `ChEMBL_get_drug_mechanisms` - mechanism \u002F CYP substrate-inhibitor-inducer data.\n- `drugbank_get_drug_interactions_by_drug_name_or_id` - known DDI \u002F transporter interactions.\n- `DailyMed_get_spl_by_setid` - FDA label (SPL) text, highest evidence tier.\n- `PubMed_search_articles` - clinical literature.\n\nFor the full set, list the server's tools at runtime rather than guessing from the 2206 catalog.\n\n## Quick Workflow\n\n1. Identify intent and route to the matching `tooluniverse-*` skill (table above).\n2. Confirm the `tooluniverse` MCP server is connected (`claude mcp get tooluniverse`).\n3. Resolve drug\u002Ftarget names to standard identifiers (ChEMBL\u002FDrugBank) before querying.\n4. Query in the order the routed skill prescribes; grade evidence (FDA label > clinical study > theoretical).\n5. Produce the report the routed skill specifies; cite data sources.\n\n## Common Mistakes\n\n- Duplicating the deep `tooluniverse-*` skill logic here instead of routing to it.\n- Enumerating or inventing tool names from the 2206 catalog - call only verified tools or list them at runtime.\n- Skipping identifier resolution and querying by free-text drug names.\n- Using this for local structure work - that is the `schrodinger-maestro-driver` and `cheminformatics-rdkit` skills.\n\n## Related Skills\n\n- `mechanistic-ddi-pipeline` - the cross-stack orchestrator that fuses ToolUniverse CYP\u002FDDI knowledge with Schrodinger structure into a single DDI verdict.\n- `cheminformatics-rdkit` - local RDKit descriptors\u002Fsimilarity for chemistry questions.\n","# DDI \u002F ADMET Research (ToolUniverse front-end)\n\n## Overview\n\nThis skill is a THIN ROUTER over the `tooluniverse` MCP server and the already-installed `tooluniverse-*` deep skills. Do NOT re-implement DDI\u002FADMET reasoning here - dispatch to the specialized skill, then call ToolUniverse tools.\n\n- Server: ToolUniverse (Apache-2.0, Harvard Zitnik lab), 2206 biomedical tools covering DDI, ADMET, CYP, targets, FDA labels, repurposing, and pharmacovigilance.\n- Registration (verified, stdio): command `uvx`, args `tooluniverse==1.2.4`, env `PYTHONIOENCODING` = `utf-8`. The stdio entry point is `tooluniverse.smcp_server:run_default_stdio_server`.\n- Cross-platform: `uvx` works on Windows and POSIX identically; no path edits needed.\n\n## Route to the Right Installed Skill\n\nDeep, ready-made skills already live at `~\u002F.agents\u002Fskills` (on Windows: `C:\\Users\\Prekzursil\\.agents\\skills`). Pick by intent:\n\n- Drug-drug interactions, polypharmacy, CYP\u002FUGT mechanisms -> `tooluniverse-drug-drug-interaction`\n- ADMET \u002F physicochemical \u002F drug-likeness prediction -> `tooluniverse-admet-prediction`\n- Hazard, GHS, handling, exposure -> `tooluniverse-chemical-safety`\n- Target identification \u002F validation -> `tooluniverse-target-research`\n- Repositioning \u002F new indications -> `tooluniverse-drug-repurposing`\n- Adverse events, signal detection, post-market safety -> `tooluniverse-pharmacovigilance`\n- Mechanism of action -> `tooluniverse-drug-mechanism-research`\n\nInvoke the matching skill first; this front-end only handles routing + the connection.\n\n## Real ToolUniverse Tools (verified in use)\n\nOnly call tools you can confirm exist. Confirmed from the installed DDI skill:\n\n- `ChEMBL_get_drug_mechanisms` - mechanism \u002F CYP substrate-inhibitor-inducer data.\n- `drugbank_get_drug_interactions_by_drug_name_or_id` - known DDI \u002F transporter interactions.\n- `DailyMed_get_spl_by_setid` - FDA label (SPL) text, highest evidence tier.\n- `PubMed_search_articles` - clinical literature.\n\nFor the full set, list the server's tools at runtime rather than guessing from the 2206 catalog.\n\n## Quick Workflow\n\n1. Identify intent and route to the matching `tooluniverse-*` skill (table above).\n2. Confirm the `tooluniverse` MCP server is connected (`claude mcp get tooluniverse`).\n3. Resolve drug\u002Ftarget names to standard identifiers (ChEMBL\u002FDrugBank) before querying.\n4. Query in the order the routed skill prescribes; grade evidence (FDA label > clinical study > theoretical).\n5. Produce the report the routed skill specifies; cite data sources.\n\n## Common Mistakes\n\n- Duplicating the deep `tooluniverse-*` skill logic here instead of routing to it.\n- Enumerating or inventing tool names from the 2206 catalog - call only verified tools or list them at runtime.\n- Skipping identifier resolution and querying by free-text drug names.\n- Using this for local structure work - that is the `schrodinger-maestro-driver` and `cheminformatics-rdkit` skills.\n\n## Related Skills\n\n- `mechanistic-ddi-pipeline` - the cross-stack orchestrator that fuses ToolUniverse CYP\u002FDDI knowledge with Schrodinger structure into a single DDI verdict.\n- `cheminformatics-rdkit` - local RDKit descriptors\u002Fsimilarity for chemistry questions.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fddi-admet-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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill ddi-admet-research",{"tool":62,"command":63},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill ddi-admet-research",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill ddi-admet-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fddi-admet-research\u002FSKILL.md",true,[],[71,92,118,145,159,175],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":45},"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",[],[78,79,80,81,82,83,84,85,86,39,87,88,89,90,91],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":99,"publishedAt":45},"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",[98],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[100,101,102,103,104,105,106,107,108,109,110,111,112,113,39,114,115,116,117,37],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do",{"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":130,"publishedAt":45},"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",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[131,132,133,134,135,136,137,138,139,140,101,141,142,143,144],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":45},"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",[],[147,152,153,154,155,156,157,158],"setup","report","project","installation","project setup","issues","state",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":45},"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",[165],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[161,167,83,168,169,170,39,171,172,173,174],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":176,"name":152,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":45},"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",[],[152,154,116,181,156,182],"files","interactive"]