[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DDHSTDV7AT1SHMWAZNG8EE":3,"skill-same:01M6DDHSTDV7AT1SHMWAZNG8EE":117},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6DDHSTDV7AT1SHMWAZNG8EE","phenibut-compchem",null,"Use when planning or running phenibut computational pharmacology with Schrodinger and PyMOL, including GABA-B docking, SAR, ADMET, MD, FEP+, QM pKa, or publication figures.","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\u002Freconcile-flags\u002Fimport-2026-08-28\u002Fskills\u002Fphenibut-compchem\u002FSKILL.md",[],[19,20,21,22,23,24],"phenibut compchem","planning","use","project","docking","computational","2026-11-10 10:12:30",false,"---\nname: phenibut-compchem\ndescription: \"Use when planning or running phenibut computational pharmacology with Schrodinger and PyMOL, including GABA-B docking, SAR, ADMET, MD, FEP+, QM pKa, or publication figures.\"\nmetadata:\n  type: project\n---\n\n# Phenibut Computational Pharmacology — Tool Routing & Pipeline\n\nCompanion to `proof_empty\u002FRESEARCH_PLAN.md` and `proof_empty\u002FSCHRODINGER_TOOLKIT.md`\n(the authoritative capability map + gap analysis). Read those for the full module\u002Ffeature detail.\n\n## Ground truth\n\n- **You own the full Schrodinger Drug Discovery Suite** (2026-2, licensed to 2050): Glide, IFD\u002FIFD-MD,\n  FEP+, Desmond, Jaguar\u002FQSite (QM), Prime+STA_GPCR, QikProp, Phase, SiteMap, WaterMap, Epik,\n  MacroModel, Canvas, AutoQSAR, AutoDesigner. **Buy nothing for the structural\u002Fchemistry layer.**\n- **PyMOL 3.1.7** (Incentive) is the only figure tool. Headless: `Scripts\\pymol.exe -cq script.pml`.\n  License lives at `%USERPROFILE%\\.pymol\\license.lic` (must be the real entitlement, not the\n  auto-generated eval token — else figures get a watermark).\n- **The mechanistic \"why\" questions (dopamine puzzle, withdrawal, prosocial effect) are\n  neurobiology\u002Fsystems pharmacology, not docking.** Corpus synthesis + free tools (PK-Sim,\n  STRING\u002FCytoscape, NEURON\u002FBrian2) are the main engine; computation tests falsifiable sub-hypotheses.\n\n## MCP: `schrodinger` (server at `C:\\Users\\Prekzursil\\source\\repos\\schrodinger-mcp\\server.py`)\n\nAfter editing the server, **reconnect the MCP \u002F restart Claude Code** to reload it.\n\nTested, ready: `schrodinger_version`, `backend_info`, `smiles_to_3d`, `molecule_properties`,\n`convert_structure`, `ligprep`, `qikprop_admet`, `glide_grid`, `glide_dock`, `prepwizard`,\n`prime_mmgbsa`, `run_schrodinger_python`, **`pdb_fetch`**, **`qikprop_parse_results`**, **`pymol_render`**.\nImplemented-untested (verify first live run): **`sitemap`**, **`jaguar_pka`**, **`epik_enumerate`**.\nRoadmap (Phase 2, async\u002FGPU — spec in `schrod_cards\u002F_mcp_expansion.md`): job-queue +\n`ifd_dock`, `fep_plus_rbfe`, `desmond_md_*`, `watermap_run`, `phase_pharmacophore`,\n`autoqsar_*`, `prime_homology`, glide XP\u002Fconstrained variants.\n\n## Standard structure-based pipeline (GABA-B + analogs)\n\n1. `pdb_fetch('7eb2'|'7c7q'|'6uo8', out_dir)` — GABA-B cryo-EM structure.\n2. `prepwizard(pdb, prepped.mae, ph=7.0)` — clean receptor → QC with `pymol_render`.\n3. `sitemap(prepped.mae, ...)` — locate orthosteric + cryptic pockets (verify first run).\n4. `smiles_to_3d` \u002F `ligprep` (+ `epik_enumerate` for the zwitterion at pH 7.4) — prep ligands.\n5. `jaguar_pka(ligand.mae, ...)` — confirm protonation state (load-bearing for binding mode).\n6. `glide_grid(prepped.mae, grid.zip, center=...)` → `glide_dock(grid.zip, ligands.mae, 'SP'|'XP')`.\n7. `prime_mmgbsa(pv.maegz)` — rescore dG_bind; `qikprop_admet` + `qikprop_parse_results` — ADMET\u002FBBB.\n8. `pymol_render([prepped.mae, pv.maegz], fig.png, highlight_selection='polymer within 5 of hetatm')`\n   — publication pose figure.\n9. (Phase 2) IFD-MD for the flexible VFT; FEP+ for \u003C2 kcal\u002Fmol analog ranking; Desmond for dynamics.\n\n## Biomedical & literature MCP layer — ToolUniverse + direct MCPs (PREFER over external installs)\n\nMost \"gap\" capabilities are already callable **in-session** — no desktop install. Reach for an\nexternal tool only when no MCP can do it (the short list below).\n\n**ToolUniverse** (`mcp__tooluniverse__*`, 2,206 tools\u002F511 categories, globally registered; 5 compact\ntools). Workflow: `find_tools`\u002F`grep_tools` → `get_tool_info(detail_level='full')` → `execute_tool`.\nMap each phenibut question to its tools:\n\n| Need | Q | ToolUniverse tools |\n|---|---|---|\n| Bioactivity \u002F Ki \u002F IC50 \u002F targets (SAR table) | A,B,D | `ChEMBL` (29), `bindingdb`, `gtopdb` (IUPHAR — has GABA-B), `drugcentral`, `pubchem_bioassay` |\n| GPCR target data (GABA-B = class-C GPCR) | A,B | `gpcrdb`, `gtopdb`, `uniprot` |\n| ADMET \u002F BBB \u002F CNS | D | `ADMETAI_predict_BBB_penetrance`, `SwissADME_calculate_adme` (49 props), `admetai` (9) — ADMET-AI v1 vs v2 predictions differ (v2 = Chemprop-v2, retrained): re-run or version-label any existing phenibut ADMET number; pin the exact version in every receipt |\n| Off-target panel (dopamine puzzle) | B | `swiss_target` (SwissTargetPrediction), `stitch`, `dgidb`, `pharos` |\n| Pathway \u002F network (GABA-B→VTA, neuroadaptation) | B,E | `reactome`, `kegg`, `wikipathways`, `string_network`, `omnipath` (ligand-receptor) |\n| Drug-drug interactions (phenibut + amphetamine\u002Falcohol\u002Fbenzo) | C | `DailyMed_parse_drug_interactions` (CYP\u002FP-gp), `sider`, `DrugSynergy_calculate_loewe`, `synergxdb`, `dose_response` |\n| Structures (no install) | all | `rcsb_pdb` (39), `pdbe`, `alphafold`, `swissmodel`, `esmfold` |\n| Literature beyond the corpus | all | `EuropePMC`, `pubmed`, `semantic_scholar`, `OpenAlex`, `unpaywall`, `biorxiv`\u002F`medrxiv` |\n| Free docking cross-check | B | `swissdock` |\n| Enzyme\u002Finhibition kinetics math | C,D | `EnzymeKinetics_calculate`, `DrugSynergy_calculate_loewe` |\n\n**Direct MCPs in-session** (often richer than ToolUniverse's wrapper):\n`mcp__claude_ai_ChEMBL__*`, `mcp__claude_ai_PubMed__*`, `mcp__claude_ai_bioRxiv__*`,\n`mcp__claude_ai_Clinical_Trials__*`, `mcp__rdkit__*` (74 descriptor tools),\n`mcp__scholarly-access__*` (OA PDF resolve\u002Ffetch — corpus expansion). See the `tooluniverse` and\n`consensus-tooluniverse-research` skills; the `bionlp` workspace (`Downloads\u002Fbionlp\u002F`) has the full setup.\n\n## Still needs an external install (no MCP covers it)\n\n- **PBPK brain kinetics** (phenibut vs baclofen CNS exposure) → **PK-Sim + MoBi** (free, OSP Suite).\n- **VTA disinhibition circuit** model (the dopamine puzzle's *circuit* answer) → **NEURON\u002FBrian2** + ModelDB (free).\n- **All-atom MD** as a free Desmond backup \u002F cross-validation → **GROMACS \u002F OpenMM**.\n- **Protein-ligand co-folding** for novel analogs (no PDB template) → **Boltz-2** (`pip install boltz`); structure-only is covered by ToolUniverse `alphafold`\u002F`esmfold`.\n- **SAR-cliff \u002F MMP visual analysis** → **DataWarrior** (free).\n\n## Gotchas\n\n- The MCP never imports `schrodinger` in-process; everything goes through `$SCHRODINGER\u002Frun.exe`.\n  The `.mcp.json` env block pins `SCHRODINGER=D:\\Program Files\\Schrodinger 2026-2` (authoritative).\n- IFD-MD, FEP+, Desmond, WaterMap-MD, DeepAutoQSAR are **GPU \u002F Linux-host**; don't expect them to run\n  synchronously on the Windows box — they need the job-queue (async) pattern.\n- Run PyMOL as a **separate subprocess** from the Schrodinger Python runtime (interpreter conflict).\n","# Phenibut Computational Pharmacology — Tool Routing & Pipeline\n\nCompanion to `proof_empty\u002FRESEARCH_PLAN.md` and `proof_empty\u002FSCHRODINGER_TOOLKIT.md`\n(the authoritative capability map + gap analysis). Read those for the full module\u002Ffeature detail.\n\n## Ground truth\n\n- **You own the full Schrodinger Drug Discovery Suite** (2026-2, licensed to 2050): Glide, IFD\u002FIFD-MD,\n  FEP+, Desmond, Jaguar\u002FQSite (QM), Prime+STA_GPCR, QikProp, Phase, SiteMap, WaterMap, Epik,\n  MacroModel, Canvas, AutoQSAR, AutoDesigner. **Buy nothing for the structural\u002Fchemistry layer.**\n- **PyMOL 3.1.7** (Incentive) is the only figure tool. Headless: `Scripts\\pymol.exe -cq script.pml`.\n  License lives at `%USERPROFILE%\\.pymol\\license.lic` (must be the real entitlement, not the\n  auto-generated eval token — else figures get a watermark).\n- **The mechanistic \"why\" questions (dopamine puzzle, withdrawal, prosocial effect) are\n  neurobiology\u002Fsystems pharmacology, not docking.** Corpus synthesis + free tools (PK-Sim,\n  STRING\u002FCytoscape, NEURON\u002FBrian2) are the main engine; computation tests falsifiable sub-hypotheses.\n\n## MCP: `schrodinger` (server at `C:\\Users\\Prekzursil\\source\\repos\\schrodinger-mcp\\server.py`)\n\nAfter editing the server, **reconnect the MCP \u002F restart Claude Code** to reload it.\n\nTested, ready: `schrodinger_version`, `backend_info`, `smiles_to_3d`, `molecule_properties`,\n`convert_structure`, `ligprep`, `qikprop_admet`, `glide_grid`, `glide_dock`, `prepwizard`,\n`prime_mmgbsa`, `run_schrodinger_python`, **`pdb_fetch`**, **`qikprop_parse_results`**, **`pymol_render`**.\nImplemented-untested (verify first live run): **`sitemap`**, **`jaguar_pka`**, **`epik_enumerate`**.\nRoadmap (Phase 2, async\u002FGPU — spec in `schrod_cards\u002F_mcp_expansion.md`): job-queue +\n`ifd_dock`, `fep_plus_rbfe`, `desmond_md_*`, `watermap_run`, `phase_pharmacophore`,\n`autoqsar_*`, `prime_homology`, glide XP\u002Fconstrained variants.\n\n## Standard structure-based pipeline (GABA-B + analogs)\n\n1. `pdb_fetch('7eb2'|'7c7q'|'6uo8', out_dir)` — GABA-B cryo-EM structure.\n2. `prepwizard(pdb, prepped.mae, ph=7.0)` — clean receptor → QC with `pymol_render`.\n3. `sitemap(prepped.mae, ...)` — locate orthosteric + cryptic pockets (verify first run).\n4. `smiles_to_3d` \u002F `ligprep` (+ `epik_enumerate` for the zwitterion at pH 7.4) — prep ligands.\n5. `jaguar_pka(ligand.mae, ...)` — confirm protonation state (load-bearing for binding mode).\n6. `glide_grid(prepped.mae, grid.zip, center=...)` → `glide_dock(grid.zip, ligands.mae, 'SP'|'XP')`.\n7. `prime_mmgbsa(pv.maegz)` — rescore dG_bind; `qikprop_admet` + `qikprop_parse_results` — ADMET\u002FBBB.\n8. `pymol_render([prepped.mae, pv.maegz], fig.png, highlight_selection='polymer within 5 of hetatm')`\n   — publication pose figure.\n9. (Phase 2) IFD-MD for the flexible VFT; FEP+ for \u003C2 kcal\u002Fmol analog ranking; Desmond for dynamics.\n\n## Biomedical & literature MCP layer — ToolUniverse + direct MCPs (PREFER over external installs)\n\nMost \"gap\" capabilities are already callable **in-session** — no desktop install. Reach for an\nexternal tool only when no MCP can do it (the short list below).\n\n**ToolUniverse** (`mcp__tooluniverse__*`, 2,206 tools\u002F511 categories, globally registered; 5 compact\ntools). Workflow: `find_tools`\u002F`grep_tools` → `get_tool_info(detail_level='full')` → `execute_tool`.\nMap each phenibut question to its tools:\n\n| Need | Q | ToolUniverse tools |\n|---|---|---|\n| Bioactivity \u002F Ki \u002F IC50 \u002F targets (SAR table) | A,B,D | `ChEMBL` (29), `bindingdb`, `gtopdb` (IUPHAR — has GABA-B), `drugcentral`, `pubchem_bioassay` |\n| GPCR target data (GABA-B = class-C GPCR) | A,B | `gpcrdb`, `gtopdb`, `uniprot` |\n| ADMET \u002F BBB \u002F CNS | D | `ADMETAI_predict_BBB_penetrance`, `SwissADME_calculate_adme` (49 props), `admetai` (9) — ADMET-AI v1 vs v2 predictions differ (v2 = Chemprop-v2, retrained): re-run or version-label any existing phenibut ADMET number; pin the exact version in every receipt |\n| Off-target panel (dopamine puzzle) | B | `swiss_target` (SwissTargetPrediction), `stitch`, `dgidb`, `pharos` |\n| Pathway \u002F network (GABA-B→VTA, neuroadaptation) | B,E | `reactome`, `kegg`, `wikipathways`, `string_network`, `omnipath` (ligand-receptor) |\n| Drug-drug interactions (phenibut + amphetamine\u002Falcohol\u002Fbenzo) | C | `DailyMed_parse_drug_interactions` (CYP\u002FP-gp), `sider`, `DrugSynergy_calculate_loewe`, `synergxdb`, `dose_response` |\n| Structures (no install) | all | `rcsb_pdb` (39), `pdbe`, `alphafold`, `swissmodel`, `esmfold` |\n| Literature beyond the corpus | all | `EuropePMC`, `pubmed`, `semantic_scholar`, `OpenAlex`, `unpaywall`, `biorxiv`\u002F`medrxiv` |\n| Free docking cross-check | B | `swissdock` |\n| Enzyme\u002Finhibition kinetics math | C,D | `EnzymeKinetics_calculate`, `DrugSynergy_calculate_loewe` |\n\n**Direct MCPs in-session** (often richer than ToolUniverse's wrapper):\n`mcp__claude_ai_ChEMBL__*`, `mcp__claude_ai_PubMed__*`, `mcp__claude_ai_bioRxiv__*`,\n`mcp__claude_ai_Clinical_Trials__*`, `mcp__rdkit__*` (74 descriptor tools),\n`mcp__scholarly-access__*` (OA PDF resolve\u002Ffetch — corpus expansion). See the `tooluniverse` and\n`consensus-tooluniverse-research` skills; the `bionlp` workspace (`Downloads\u002Fbionlp\u002F`) has the full setup.\n\n## Still needs an external install (no MCP covers it)\n\n- **PBPK brain kinetics** (phenibut vs baclofen CNS exposure) → **PK-Sim + MoBi** (free, OSP Suite).\n- **VTA disinhibition circuit** model (the dopamine puzzle's *circuit* answer) → **NEURON\u002FBrian2** + ModelDB (free).\n- **All-atom MD** as a free Desmond backup \u002F cross-validation → **GROMACS \u002F OpenMM**.\n- **Protein-ligand co-folding** for novel analogs (no PDB template) → **Boltz-2** (`pip install boltz`); structure-only is covered by ToolUniverse `alphafold`\u002F`esmfold`.\n- **SAR-cliff \u002F MMP visual analysis** → **DataWarrior** (free).\n\n## Gotchas\n\n- The MCP never imports `schrodinger` in-process; everything goes through `$SCHRODINGER\u002Frun.exe`.\n  The `.mcp.json` env block pins `SCHRODINGER=D:\\Program Files\\Schrodinger 2026-2` (authoritative).\n- IFD-MD, FEP+, Desmond, WaterMap-MD, DeepAutoQSAR are **GPU \u002F Linux-host**; don't expect them to run\n  synchronously on the Windows box — they need the job-queue (async) pattern.\n- Run PyMOL as a **separate subprocess** from the Schrodinger Python runtime (interpreter conflict).\n",{"name":5,"metadata":30,"description":7},{"type":22},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","reconcile-flags\u002Fimport-2026-08-28\u002Fskills\u002Fphenibut-compchem","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill phenibut-compchem",{"tool":43,"command":44},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill phenibut-compchem",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill phenibut-compchem","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Freconcile-flags\u002Fimport-2026-08-28\u002Fskills\u002Fphenibut-compchem\u002FSKILL.md",true,[51,57,63,67,71,75,79,83,87,91,95,99,103,107,111],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},".gitignore","OTHER","其他",239,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002F.gitignore",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"docs\u002Fbest-practices.md","REFERENCE","参考文档",12095,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fdocs\u002Fbest-practices.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"docs\u002Ftasks-reference.md",14331,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fdocs\u002Ftasks-reference.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"docs\u002Ftemplates-guide.md",14597,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fdocs\u002Ftemplates-guide.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"docs\u002Fyaml-schema.md",13980,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fdocs\u002Fyaml-schema.md",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"examples\u002Fbasic-ci.yml",1683,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Fbasic-ci.yml",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"examples\u002Fdotnet-cicd.yml",4697,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Fdotnet-cicd.yml",{"path":84,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":85,"sourceHtmlUrl":86},"examples\u002Fgo-cicd.yml",11740,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Fgo-cicd.yml",{"path":88,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":89,"sourceHtmlUrl":90},"examples\u002Fkubernetes-deploy.yml",3879,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Fkubernetes-deploy.yml",{"path":92,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":93,"sourceHtmlUrl":94},"examples\u002Fmulti-stage-cicd.yml",5498,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Fmulti-stage-cicd.yml",{"path":96,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":97,"sourceHtmlUrl":98},"examples\u002Fpython-cicd.yml",4675,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Fpython-cicd.yml",{"path":100,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":101,"sourceHtmlUrl":102},"examples\u002Ftemplate-usage.yml",1508,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Ftemplate-usage.yml",{"path":104,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":105,"sourceHtmlUrl":106},"examples\u002Ftemplates\u002Fbuild-template.yml",2028,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Ftemplates\u002Fbuild-template.yml",{"path":108,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":109,"sourceHtmlUrl":110},"examples\u002Ftemplates\u002Fdeploy-template.yml",3354,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Fexamples\u002Ftemplates\u002Fdeploy-template.yml",{"path":112,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":115,"sourceHtmlUrl":116},"tests\u002Ftest_template_regressions.py","SCRIPT","脚本",2978,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcloud-azure-microsoft-sdks\u002Flatest-release-devops\u002Fazure-pipelines-generator\u002Ftests\u002Ftest_template_regressions.py",[118,139,170,197,210,226],{"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":124,"publishedAt":25},"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",[],[125,126,127,128,129,130,131,132,133,21,134,135,136,137,138],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":150,"publishedAt":25},"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",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[151,152,153,154,155,156,157,158,159,160,161,162,163,164,21,165,166,167,168,169],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":182,"publishedAt":25},"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",[176,179],{"categoryNo":177,"categoryName":178,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":180,"categoryName":181,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000008","测试与质量",[183,184,185,186,187,188,189,190,191,192,152,193,194,195,196],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"publishedAt":25},"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",[],[199,204,205,22,206,207,208,209],"setup","report","installation","project setup","issues","state",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":25},"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",[216],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},[212,218,130,219,220,221,21,222,223,224,225],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":227,"name":204,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":231,"publishedAt":25},"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",[],[204,22,167,232,207,233],"files","interactive"]