[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF79CA4BHJS66J8EZDBPWJ":3,"skill-same:01M6DF79CA4BHJS66J8EZDBPWJ":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md",null,"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.","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\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"openmm md","tool","free","molecular dynamics","local","do","use","decision","pick","analyze","MCP","stack","how","open","NVIDIA","gpu","license","windows","workflow","linux","2026-11-10 10:12:30",false,"---\nname: openmm-md\ndescription: 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.\n---\n\n# OpenMM MD (free, Windows-native GPU molecular dynamics)\n\n`openmm-md` is a FREE \u002F open-source (MIT) molecular-dynamics MCP that runs **natively on\nWindows with CUDA** on the local NVIDIA GPU (verified on an RTX 4050). It is the free lane\nfor MD work; it is **explicitly a lesser alternative** to Schrodinger Desmond, which stays\nthe preferred engine whenever a legitimate license is available.\n\n## When to use which engine (decision guide)\n\n| Situation | Use | Why |\n|---|---|---|\n| On Windows, no Schrodinger license, need MD now | **openmm-md (this)** | Only native-Windows GPU MD option; free; runs on the local RTX 4050 |\n| Quick stability \u002F RMSD \u002F Rg \u002F H-bond check of a pose | **openmm-md** | Fast, free, good enough for triage |\n| Ranking a congeneric ligand series roughly, no budget | **openmm-md** `openmm_mmgbsa` | Free relative ranking (approximate) |\n| You need validated **FEP+**, **WaterMap**, **IFD-MD**, **Prime MM-GBSA (VSGB2.1)** | **Schrodinger** (`mcp__schrodinger__*`) | OpenMM has no validated equivalent |\n| Publication-grade \u002F regulatory binding free energies | **Desmond \u002F FEP+** on a licensed host | More-validated force fields + workflows |\n| You have a **legit** Schrodinger license + a Linux box | **Desmond on Linux** | The `mcp__schrodinger__desmond_*` tools work there |\n| You want a big GPU \u002F no local install | **Desmond on a licensed Linux cloud GPU** | Scale out with a real license |\n\n**Golden rule:** if the science needs a validated commercial method, use Schrodinger. Use\nopenmm-md when free + Windows-native + \"good enough\" is the right trade. openmm-md does NOT\nreplace the 67 `mcp__schrodinger__*` tools; they stay intact and preferred.\n\n## Honest OpenMM vs Desmond trade-offs\n\nOpenMM (free) is a genuinely excellent MD **engine**, but as a **workflow** it is a lesser\nalternative to Desmond\u002FMaestro:\n\n- **Force fields**: OpenMM here uses AMBER **ff14SB** (protein) + **OpenFF Sage** or GAFF\n  (ligand). Desmond ships OPLS4, extensively validated for drug discovery.\n- **Ligand charges (Windows caveat)**: AmberTools has **no native-Windows build**, so there\n  is **no antechamber \u002F sqm AM1-BCC** and **no GAFF** here. Charges come from **NAGL** (a\n  GNN AM1-BCC surrogate, if installed) or **RDKit Gasteiger** (lower fidelity). Both are\n  clearly labelled. OpenEye\u002Fsqm AM1-BCC quality is not reproduced.\n- **Free-energy \u002F analysis**: no FEP+, no WaterMap, no IFD-MD. `openmm_mmgbsa` is an HONEST\n  OBC2\u002FGBSA single-trajectory approximation (no entropy, generic radii) -- good for ranking,\n  NOT absolute affinities, and materially weaker than Prime MM-GBSA.\n- **Polish**: no Maestro GUI, trajectory clustering, or event analysis suite. You get MDTraj\n  metrics (RMSD\u002FRMSF\u002FRg\u002FH-bonds\u002Fcontacts).\n\n## Running Desmond legitimately (the better option when licensed)\n\nThis project will **not** install, crack, or facilitate a pirated Schrodinger suite. To use\nDesmond properly:\n\n1. **Get a legitimate license.** Academic\u002Fnon-commercial Desmond is **free from D. E. Shaw\n   Research** (deshawresearch.com) for non-commercial use; commercial use needs a Schrodinger\n   license. Academic Maestro\u002FSchrodinger licenses are available to universities.\n2. **Desmond on Linux.** Desmond's MD engine is Linux-only. Install the licensed suite on a\n   Linux workstation, set `$SCHRODINGER`, and the existing `mcp__schrodinger__desmond_setup`\n   \u002F `desmond_md` \u002F `desmond_trajectory_analysis` tools drive it there.\n3. **Desmond on a cloud GPU.** Put a legit-licensed Linux install on a cloud GPU instance\n   (e.g. via the cloud-hub RunPod \u002F Modal \u002F Lightning GPU tools), copy the license, and run\n   Desmond remotely. Shape only -- provision the box, install YOUR licensed suite, run.\n\n## The openmm-md workflow\n\nTools chain through a `job_dir` on disk. Typical protein-ligand run:\n\n1. **`openmm_status`** -- verify CUDA is live on the GPU (run this first).\n2. **`openmm_prepare`** -- `protein` = PDB path or 4-char RCSB id; optional `ligand_file`\n   (a **docked** SDF\u002FMOL2 pose -- preferred) or `ligand_smiles` (arbitrary conformer).\n   PDBFixer cleanup + ff14SB + OpenFF ligand params. Returns the `job_dir`.\n3. **`openmm_solvate`** -- TIP3P box (`box_shape` cube|dodecahedron|octahedron) + neutralizing\n   ions (PME). `hydrogen_mass_amu=4.0` for HMR \u002F 4 fs.\n4. **`openmm_minimize`** -- energy minimization on CUDA.\n5. **`openmm_equilibrate`** -- NVT then NPT (barostat), optional heavy-atom restraints.\n6. **`openmm_production`** -- production MD. **Non-blocking**: returns a handle; poll with\n   `openmm_production(job_dir, poll=True)` or Read `prod_status.json`. Writes `prod.dcd`.\n   Use `blocking=True` only for short runs.\n7. **`openmm_analyze`** -- MDTraj RMSD \u002F RMSF \u002F Rg \u002F H-bonds \u002F protein-ligand contacts +\n   ligand binding-site RMSD (stability).\n8. **`openmm_mmgbsa`** -- approximate free binding dG (ranking only; read `fidelity_note`).\n\n### Sensible defaults \u002F tips\n\n- **GPU memory (6 GB RTX 4050)**: keep systems modest (small-to-medium proteins, ~1.0 nm\n  padding). Large systems may OOM -- reduce padding or trim the system.\n- **Timestep**: 2 fs default (HBond constraints). 4 fs only with HMR (`hydrogen_mass_amu=4.0`).\n- **Ligand pose**: for binding studies pass a **docked** pose via `ligand_file` (e.g. from\n  Glide `mcp__schrodinger__glide_dock`); a bare SMILES has no bound pose.\n- **Long runs**: leave production non-blocking and poll; the detached worker keeps writing\n  `prod.dcd` + `prod_status.json` even across MCP calls.\n- **Honesty**: label OpenMM results as free-stack \u002F approximate; when a decision hinges on\n  absolute affinity or validated methods, escalate to Schrodinger.\n\n## Registration\n\nMCP server: `C:\\Users\\Prekzursil\\source\\repos\\openmm-md-mcp\\server.py`, run with the conda\nenv Python `D:\\micromamba\\envs\\openmm-md\\python.exe` (the server self-configures the Windows\nCUDA DLL path, so no activation wrapper is needed). See the repo README for the exact\n`~\u002F.mcp.json` block and how to install this skill into a skills directory.\n","# OpenMM MD (free, Windows-native GPU molecular dynamics)\n\n`openmm-md` is a FREE \u002F open-source (MIT) molecular-dynamics MCP that runs **natively on\nWindows with CUDA** on the local NVIDIA GPU (verified on an RTX 4050). It is the free lane\nfor MD work; it is **explicitly a lesser alternative** to Schrodinger Desmond, which stays\nthe preferred engine whenever a legitimate license is available.\n\n## When to use which engine (decision guide)\n\n| Situation | Use | Why |\n|---|---|---|\n| On Windows, no Schrodinger license, need MD now | **openmm-md (this)** | Only native-Windows GPU MD option; free; runs on the local RTX 4050 |\n| Quick stability \u002F RMSD \u002F Rg \u002F H-bond check of a pose | **openmm-md** | Fast, free, good enough for triage |\n| Ranking a congeneric ligand series roughly, no budget | **openmm-md** `openmm_mmgbsa` | Free relative ranking (approximate) |\n| You need validated **FEP+**, **WaterMap**, **IFD-MD**, **Prime MM-GBSA (VSGB2.1)** | **Schrodinger** (`mcp__schrodinger__*`) | OpenMM has no validated equivalent |\n| Publication-grade \u002F regulatory binding free energies | **Desmond \u002F FEP+** on a licensed host | More-validated force fields + workflows |\n| You have a **legit** Schrodinger license + a Linux box | **Desmond on Linux** | The `mcp__schrodinger__desmond_*` tools work there |\n| You want a big GPU \u002F no local install | **Desmond on a licensed Linux cloud GPU** | Scale out with a real license |\n\n**Golden rule:** if the science needs a validated commercial method, use Schrodinger. Use\nopenmm-md when free + Windows-native + \"good enough\" is the right trade. openmm-md does NOT\nreplace the 67 `mcp__schrodinger__*` tools; they stay intact and preferred.\n\n## Honest OpenMM vs Desmond trade-offs\n\nOpenMM (free) is a genuinely excellent MD **engine**, but as a **workflow** it is a lesser\nalternative to Desmond\u002FMaestro:\n\n- **Force fields**: OpenMM here uses AMBER **ff14SB** (protein) + **OpenFF Sage** or GAFF\n  (ligand). Desmond ships OPLS4, extensively validated for drug discovery.\n- **Ligand charges (Windows caveat)**: AmberTools has **no native-Windows build**, so there\n  is **no antechamber \u002F sqm AM1-BCC** and **no GAFF** here. Charges come from **NAGL** (a\n  GNN AM1-BCC surrogate, if installed) or **RDKit Gasteiger** (lower fidelity). Both are\n  clearly labelled. OpenEye\u002Fsqm AM1-BCC quality is not reproduced.\n- **Free-energy \u002F analysis**: no FEP+, no WaterMap, no IFD-MD. `openmm_mmgbsa` is an HONEST\n  OBC2\u002FGBSA single-trajectory approximation (no entropy, generic radii) -- good for ranking,\n  NOT absolute affinities, and materially weaker than Prime MM-GBSA.\n- **Polish**: no Maestro GUI, trajectory clustering, or event analysis suite. You get MDTraj\n  metrics (RMSD\u002FRMSF\u002FRg\u002FH-bonds\u002Fcontacts).\n\n## Running Desmond legitimately (the better option when licensed)\n\nThis project will **not** install, crack, or facilitate a pirated Schrodinger suite. To use\nDesmond properly:\n\n1. **Get a legitimate license.** Academic\u002Fnon-commercial Desmond is **free from D. E. Shaw\n   Research** (deshawresearch.com) for non-commercial use; commercial use needs a Schrodinger\n   license. Academic Maestro\u002FSchrodinger licenses are available to universities.\n2. **Desmond on Linux.** Desmond's MD engine is Linux-only. Install the licensed suite on a\n   Linux workstation, set `$SCHRODINGER`, and the existing `mcp__schrodinger__desmond_setup`\n   \u002F `desmond_md` \u002F `desmond_trajectory_analysis` tools drive it there.\n3. **Desmond on a cloud GPU.** Put a legit-licensed Linux install on a cloud GPU instance\n   (e.g. via the cloud-hub RunPod \u002F Modal \u002F Lightning GPU tools), copy the license, and run\n   Desmond remotely. Shape only -- provision the box, install YOUR licensed suite, run.\n\n## The openmm-md workflow\n\nTools chain through a `job_dir` on disk. Typical protein-ligand run:\n\n1. **`openmm_status`** -- verify CUDA is live on the GPU (run this first).\n2. **`openmm_prepare`** -- `protein` = PDB path or 4-char RCSB id; optional `ligand_file`\n   (a **docked** SDF\u002FMOL2 pose -- preferred) or `ligand_smiles` (arbitrary conformer).\n   PDBFixer cleanup + ff14SB + OpenFF ligand params. Returns the `job_dir`.\n3. **`openmm_solvate`** -- TIP3P box (`box_shape` cube|dodecahedron|octahedron) + neutralizing\n   ions (PME). `hydrogen_mass_amu=4.0` for HMR \u002F 4 fs.\n4. **`openmm_minimize`** -- energy minimization on CUDA.\n5. **`openmm_equilibrate`** -- NVT then NPT (barostat), optional heavy-atom restraints.\n6. **`openmm_production`** -- production MD. **Non-blocking**: returns a handle; poll with\n   `openmm_production(job_dir, poll=True)` or Read `prod_status.json`. Writes `prod.dcd`.\n   Use `blocking=True` only for short runs.\n7. **`openmm_analyze`** -- MDTraj RMSD \u002F RMSF \u002F Rg \u002F H-bonds \u002F protein-ligand contacts +\n   ligand binding-site RMSD (stability).\n8. **`openmm_mmgbsa`** -- approximate free binding dG (ranking only; read `fidelity_note`).\n\n### Sensible defaults \u002F tips\n\n- **GPU memory (6 GB RTX 4050)**: keep systems modest (small-to-medium proteins, ~1.0 nm\n  padding). Large systems may OOM -- reduce padding or trim the system.\n- **Timestep**: 2 fs default (HBond constraints). 4 fs only with HMR (`hydrogen_mass_amu=4.0`).\n- **Ligand pose**: for binding studies pass a **docked** pose via `ligand_file` (e.g. from\n  Glide `mcp__schrodinger__glide_dock`); a bare SMILES has no bound pose.\n- **Long runs**: leave production non-blocking and poll; the detached worker keeps writing\n  `prod.dcd` + `prod_status.json` even across MCP calls.\n- **Honesty**: label OpenMM results as free-stack \u002F approximate; when a decision hinges on\n  absolute affinity or validated methods, escalate to Schrodinger.\n\n## Registration\n\nMCP server: `C:\\Users\\Prekzursil\\source\\repos\\openmm-md-mcp\\server.py`, run with the conda\nenv Python `D:\\micromamba\\envs\\openmm-md\\python.exe` (the server self-configures the Windows\nCUDA DLL path, so no activation wrapper is needed). See the repo README for the exact\n`~\u002F.mcp.json` block and how to install this skill into a skills directory.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","tools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill openmm-md",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill openmm-md",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill openmm-md","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",true,[],[70,91,118,132,148,156],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":44},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[77,78,79,80,81,82,83,84,85,86,87,30,88,89,90],"clarify requirements","clarify","requirements","options","task","file","execution","injection","risk","repo","context","scanning","goal","prompts",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":103,"publishedAt":44},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[97,100],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[104,105,106,107,108,109,36,110,111,112,113,114,115,116,117],"review","visual","visual review","web","screenshot","ui","slides","check","take","iteration","pages","false","playwright","screenshots",{"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":44},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[120,125,126,127,128,129,130,131],"installation","setup","report","state","issues","project setup","project",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":44},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[138],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[134,140,141,142,143,144,30,145,146,147,81],"user","development","work on","start issue","work","work on issue","ready","issue",{"skillNo":149,"name":126,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":44},"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",[],[126,154,130,155,28,131],"interactive","files",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":44},"01M6DF6M1P5KAJ13YQJ28T7XDE","pr-shepherd","Monitor a PR through to merge — handle CI failures, review comments, and thread resolution automatically until all checks pass","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fpr-shepherd\u002FSKILL.md",[],[163,164,165,166,167,168,169,104],"shepherd","pr shepherd","pr","merge","monitor","ci","resolution"]