[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79F6EXGDPTP9T2JCVAVZ7WJ":3,"skill-same:01M79F6EXGDPTP9T2JCVAVZ7WJ":131},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M79F6EXGDPTP9T2JCVAVZ7WJ","cuopt-numerical-optimization-api-c",null,"LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C\u002FC++.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cuopt-numerical-optimization-api-c\nversion: \"26.08.00\"\ndescription: LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C\u002FC++.\nlicense: Apache-2.0\nmetadata:\n  author: NVIDIA cuOpt Team\n  tags:\n    - cuopt\n    - linear-programming\n    - milp\n    - qp\n    - c-api\n---\n\n\n# cuOpt Numerical Optimization — C API\n\nSolve LP, MILP, and QP problems via the cuOpt C API. The same library, headers, build pattern, and core calls (`cuOptCreate*Problem`, `cuOptSolve`, `cuOptGetObjectiveValue`) apply across all three; QP extends the API with quadratic-objective creation calls.\n\nConfirm problem type and formulation (variables, objective, constraints, variable types) before coding.\n\nThis skill is **C only**.\n\n## API Call Sequence\n\nFor LP\u002FMILP, the ordered C entry points are: `cuOptCreateRangedProblem` (sense `CUOPT_MINIMIZE` \u002F `CUOPT_MAXIMIZE`, CSR constraint matrix as `row_offsets` \u002F `col_indices` \u002F `values`, `var_types` char array using `CUOPT_CONTINUOUS` \u002F `CUOPT_INTEGER` macros) → `cuOptSolve(problem, settings, &solution)` → `cuOptGetObjectiveValue(solution, &obj_value)` → matching `cuOptDestroy*` calls. Include `\u003Ccuopt\u002Flinear_programming\u002Fcuopt_c.h>`. Full ordered code with build instructions in [references\u002Fexamples.md](references\u002Fexamples.md).\n\n## QP via C API (beta)\n\nQP uses the same library, include\u002Flib paths, and build pattern as LP\u002FMILP — only the problem-creation call differs (it accepts a quadratic objective). See the cuOpt C headers (`cpp\u002Finclude\u002Fcuopt\u002Flinear_programming\u002F`) for the QP-specific creation\u002Fsolve calls and the repo docs at `docs\u002Fcuopt\u002Fsource\u002Fcuopt-c\u002Flp-qp-milp\u002F` for end-to-end QP examples.\n\n**QP rules:**\n- **MINIMIZE only** (`CUOPT_MINIMIZE`). To maximize `f(x)`, negate objective coefficients and Q entries.\n- **Continuous variables only** — set `CUOPT_CONTINUOUS` for every variable; integer QP is not supported.\n- **Q should be PSD** for a convex problem.\n\n## Dual values (LP \u002F QP)\n\n`cuOptGetDualSolution` and `cuOptGetReducedCosts` return duals and reduced costs for **LP and QP**. They are not returned for a problem with quadratic constraints (the arrays are filled with `NaN`), so read them only when all constraints are linear. See [assets\u002Flp_duals](assets\u002Flp_duals\u002F) for the call sequence.\n\n## Debugging (MPS \u002F C)\n\n**MPS parsing:** Required sections in order: NAME, ROWS, COLUMNS, RHS, (optional) BOUNDS, ENDATA. Integer markers: `'MARKER'`, `'INTORG'`, `'INTEND'`.\n\n**OOM or slow:** Check problem size (variables, constraints); use sparse matrix; set time limit and gap tolerance.\n\n## Examples\n\n- [examples.md](references\u002Fexamples.md) — LP\u002FMILP with build instructions\n- [assets\u002FREADME.md](assets\u002FREADME.md) — Build commands for all reference code below\n- [lp_basic](assets\u002Flp_basic\u002F) — Simple LP: create problem, solve, get solution\n- [lp_duals](assets\u002Flp_duals\u002F) — Dual values and reduced costs\n- [lp_warmstart](assets\u002Flp_warmstart\u002F) — PDLP warmstart (see README)\n- [milp_basic](assets\u002Fmilp_basic\u002F) — Simple MILP with integer variable\n- [milp_production_planning](assets\u002Fmilp_production_planning\u002F) — Production planning with resource constraints\n- [mps_solver](assets\u002Fmps_solver\u002F) — Solve from MPS file via `cuOptReadProblem`\n\nFor **CLI** (MPS files), use `cuopt_cli` and product docs.\n\n## Escalate\n\nFor contribution or build-from-source, use product or repo documentation.\n","# cuOpt Numerical Optimization — C API\n\nSolve LP, MILP, and QP problems via the cuOpt C API. The same library, headers, build pattern, and core calls (`cuOptCreate*Problem`, `cuOptSolve`, `cuOptGetObjectiveValue`) apply across all three; QP extends the API with quadratic-objective creation calls.\n\nConfirm problem type and formulation (variables, objective, constraints, variable types) before coding.\n\nThis skill is **C only**.\n\n## API Call Sequence\n\nFor LP\u002FMILP, the ordered C entry points are: `cuOptCreateRangedProblem` (sense `CUOPT_MINIMIZE` \u002F `CUOPT_MAXIMIZE`, CSR constraint matrix as `row_offsets` \u002F `col_indices` \u002F `values`, `var_types` char array using `CUOPT_CONTINUOUS` \u002F `CUOPT_INTEGER` macros) → `cuOptSolve(problem, settings, &solution)` → `cuOptGetObjectiveValue(solution, &obj_value)` → matching `cuOptDestroy*` calls. Include `\u003Ccuopt\u002Flinear_programming\u002Fcuopt_c.h>`. Full ordered code with build instructions in [references\u002Fexamples.md](references\u002Fexamples.md).\n\n## QP via C API (beta)\n\nQP uses the same library, include\u002Flib paths, and build pattern as LP\u002FMILP — only the problem-creation call differs (it accepts a quadratic objective). See the cuOpt C headers (`cpp\u002Finclude\u002Fcuopt\u002Flinear_programming\u002F`) for the QP-specific creation\u002Fsolve calls and the repo docs at `docs\u002Fcuopt\u002Fsource\u002Fcuopt-c\u002Flp-qp-milp\u002F` for end-to-end QP examples.\n\n**QP rules:**\n- **MINIMIZE only** (`CUOPT_MINIMIZE`). To maximize `f(x)`, negate objective coefficients and Q entries.\n- **Continuous variables only** — set `CUOPT_CONTINUOUS` for every variable; integer QP is not supported.\n- **Q should be PSD** for a convex problem.\n\n## Dual values (LP \u002F QP)\n\n`cuOptGetDualSolution` and `cuOptGetReducedCosts` return duals and reduced costs for **LP and QP**. They are not returned for a problem with quadratic constraints (the arrays are filled with `NaN`), so read them only when all constraints are linear. See [assets\u002Flp_duals](assets\u002Flp_duals\u002F) for the call sequence.\n\n## Debugging (MPS \u002F C)\n\n**MPS parsing:** Required sections in order: NAME, ROWS, COLUMNS, RHS, (optional) BOUNDS, ENDATA. Integer markers: `'MARKER'`, `'INTORG'`, `'INTEND'`.\n\n**OOM or slow:** Check problem size (variables, constraints); use sparse matrix; set time limit and gap tolerance.\n\n## Examples\n\n- [examples.md](references\u002Fexamples.md) — LP\u002FMILP with build instructions\n- [assets\u002FREADME.md](assets\u002FREADME.md) — Build commands for all reference code below\n- [lp_basic](assets\u002Flp_basic\u002F) — Simple LP: create problem, solve, get solution\n- [lp_duals](assets\u002Flp_duals\u002F) — Dual values and reduced costs\n- [lp_warmstart](assets\u002Flp_warmstart\u002F) — PDLP warmstart (see README)\n- [milp_basic](assets\u002Fmilp_basic\u002F) — Simple MILP with integer variable\n- [milp_production_planning](assets\u002Fmilp_production_planning\u002F) — Production planning with resource constraints\n- [mps_solver](assets\u002Fmps_solver\u002F) — Solve from MPS file via `cuOptReadProblem`\n\nFor **CLI** (MPS files), use `cuopt_cli` and product docs.\n\n## Escalate\n\nFor contribution or build-from-source, use product or repo documentation.\n",{"name":5,"license":15,"version":24,"metadata":25,"description":7},"26.08.00",{"tags":26,"author":32},[27,28,29,30,31],"cuopt","linear-programming","milp","qp","c-api","NVIDIA cuOpt Team","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","skills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill cuopt-numerical-optimization-api-c",{"tool":45,"command":46},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill cuopt-numerical-optimization-api-c",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill cuopt-numerical-optimization-api-c","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002FSKILL.md",true,[53,59,63,67,71,75,79,83,87,91,95,99,103,107,113,117,121,125],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Flp_basic\u002Flp_simple.c","ASSET","资产文件",3691,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Flp_basic\u002Flp_simple.c",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"assets\u002Flp_basic\u002FREADME.md",466,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Flp_basic\u002FREADME.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"assets\u002Flp_duals\u002Flp_duals.c",4046,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Flp_duals\u002Flp_duals.c",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"assets\u002Flp_duals\u002FREADME.md",500,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Flp_duals\u002FREADME.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"assets\u002Flp_warmstart\u002FREADME.md",289,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Flp_warmstart\u002FREADME.md",{"path":76,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":77,"sourceHtmlUrl":78},"assets\u002Fmilp_basic\u002Fmilp_simple.c",3449,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmilp_basic\u002Fmilp_simple.c",{"path":80,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":81,"sourceHtmlUrl":82},"assets\u002Fmilp_basic\u002FREADME.md",405,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmilp_basic\u002FREADME.md",{"path":84,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":85,"sourceHtmlUrl":86},"assets\u002Fmilp_production_planning\u002Fmilp_production.c",3532,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmilp_production_planning\u002Fmilp_production.c",{"path":88,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":89,"sourceHtmlUrl":90},"assets\u002Fmilp_production_planning\u002FREADME.md",459,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmilp_production_planning\u002FREADME.md",{"path":92,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":93,"sourceHtmlUrl":94},"assets\u002Fmps_solver\u002Fdata\u002Fsample.mps",490,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmps_solver\u002Fdata\u002Fsample.mps",{"path":96,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":97,"sourceHtmlUrl":98},"assets\u002Fmps_solver\u002Fmps_solver.c",3479,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmps_solver\u002Fmps_solver.c",{"path":100,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":101,"sourceHtmlUrl":102},"assets\u002Fmps_solver\u002FREADME.md",590,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002Fmps_solver\u002FREADME.md",{"path":104,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":105,"sourceHtmlUrl":106},"assets\u002FREADME.md",1712,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fassets\u002FREADME.md",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"BENCHMARK.md","REFERENCE","参考文档",4308,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002FBENCHMARK.md",{"path":114,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":115,"sourceHtmlUrl":116},"evals\u002Fevals.json",5373,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fevals\u002Fevals.json",{"path":118,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Fexamples.md",9865,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Freferences\u002Fexamples.md",{"path":122,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":123,"sourceHtmlUrl":124},"skill-card.md",3710,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fskill-card.md",{"path":126,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":129,"sourceHtmlUrl":130},"skill.oms.sig","OTHER","其他",8009,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fcuopt-numerical-optimization-api-c\u002Fskill.oms.sig",[132,139,146,153,160,167],{"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":138,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"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":145,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]