[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXYGFWM3SWVAVK0M1SFRSD":3,"skill-same:01M6BXYGFWM3SWVAVK0M1SFRSD":78},{"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":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6BXYGFWM3SWVAVK0M1SFRSD","debug",null,"Run commands inside a remote Docker container via the file-based command relay (tools\u002Fdebugger). Use when the user says \"run in Docker\", \"run on GPU\", \"debug remotely\", \"run test in container\", \"check nvidia-smi\", \"run pytest in Docker\", or needs to execute any command inside a Docker container that shares the repo filesystem. Requires the user to have started server.sh inside the container first.","NVIDIA\u002FModel-Optimizer","NVIDIA","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1728152?v=4","01M6BXXZYTRNBXSTRXNNBB356H","NVIDIA Corporation","01M6BXY02X3PRVHNNATDHA2D0W",5584,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Fdebug\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,9,44,45,46,47,48,49],"debugger","when","smi","remote","relay","via","container","use","command","check","repo","filesystem","docker","first","Tools","server","file","run test","gpu","run","test","2026-11-10 10:12:30",false,"---\nname: debug\ndescription: Run commands inside a remote Docker container via the file-based command relay (tools\u002Fdebugger). Use when the user says \"run in Docker\", \"run on GPU\", \"debug remotely\", \"run test in container\", \"check nvidia-smi\", \"run pytest in Docker\", or needs to execute any command inside a Docker container that shares the repo filesystem. Requires the user to have started server.sh inside the container first.\n---\n\n# Remote Docker Debugger\n\nExecute commands inside a Docker container from the host using the file-based command relay.\n\n**Read `tools\u002Fdebugger\u002FCLAUDE.md` for full usage details** — it has the protocol and examples.\n\n## Quick Reference\n\n```bash\n# Check connection\nbash tools\u002Fdebugger\u002Fclient.sh status\n\n# Connect to server (user must start server.sh in Docker first)\nbash tools\u002Fdebugger\u002Fclient.sh handshake\n\n# Run a command\nbash tools\u002Fdebugger\u002Fclient.sh run \"\u003Ccommand>\"\n\n# Long-running command (default timeout is 600s)\nbash tools\u002Fdebugger\u002Fclient.sh --timeout 1800 run \"\u003Ccommand>\"\n\n# Cancel the currently running command\nbash tools\u002Fdebugger\u002Fclient.sh cancel\n\n# Reconnect after server restart\nbash tools\u002Fdebugger\u002Fclient.sh flush\nbash tools\u002Fdebugger\u002Fclient.sh handshake\n```\n","# Remote Docker Debugger\n\nExecute commands inside a Docker container from the host using the file-based command relay.\n\n**Read `tools\u002Fdebugger\u002FCLAUDE.md` for full usage details** — it has the protocol and examples.\n\n## Quick Reference\n\n```bash\n# Check connection\nbash tools\u002Fdebugger\u002Fclient.sh status\n\n# Connect to server (user must start server.sh in Docker first)\nbash tools\u002Fdebugger\u002Fclient.sh handshake\n\n# Run a command\nbash tools\u002Fdebugger\u002Fclient.sh run \"\u003Ccommand>\"\n\n# Long-running command (default timeout is 600s)\nbash tools\u002Fdebugger\u002Fclient.sh --timeout 1800 run \"\u003Ccommand>\"\n\n# Cancel the currently running command\nbash tools\u002Fdebugger\u002Fclient.sh cancel\n\n# Reconnect after server restart\nbash tools\u002Fdebugger\u002Fclient.sh flush\nbash tools\u002Fdebugger\u002Fclient.sh handshake\n```\n",{"name":5,"description":7},"main","cf38ec30ca4d8d81fde0322e8d3d3003d5d5827b","plugins\u002Fmodelopt\u002Fskills\u002Fdebug",806,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer","https:\u002F\u002Fnvidia.github.io\u002FModel-Optimizer\u002F","https:\u002F\u002Fgithub.com\u002FNVIDIA","https:\u002F\u002Fnvidia.com","2026-11-11 09:05:50",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add NVIDIA\u002FModel-Optimizer --skill debug",{"tool":70,"command":71},"bunx","bunx skills add NVIDIA\u002FModel-Optimizer --skill debug",{"tool":73,"command":74},"pnpm","pnpm dlx skills add NVIDIA\u002FModel-Optimizer --skill debug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Fdebug\u002FSKILL.md",true,[],[79,105,125,147,176,196],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":50},"01M6BXZCWMVSWF5ZJG07J8PYTR","speculative-decoding","Train, debug, and validate a speculative decoding draft model (EAGLE3, DFlash, DSpark, Domino) through the ModelOpt launcher pipeline. Use when the user wants to add a new model to a draft-training pipeline, asks why a pipeline run failed, wants experiment logs reviewed, or wants to check whether a run's acceptance rate meets threshold. Triggers on \"EAGLE3\", \"DFlash\", \"DSpark\", \"Domino\", \"draft model\", \"acceptance rate\", \"speculative decoding pipeline\". Do NOT use for quantizing a model (use ptq) or serving a checkpoint (use deployment).","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Fspeculative-decoding\u002FSKILL.md",[],[86,87,88,48,89,90,91,92,93,94,95,5,96,97,98,99,100,101,102,103,36,30,38,104],"speculative decoding","model","pipeline","why","deployment","checkpoint","training","validate","ptq","acceptance","logs","do","dspark","for","launcher","triggers","true","new","draft",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":50},"01M6BXZAV5KW803GEZBTGWGXCG","run-agentx","Run the AgentX agentic serving benchmark with the SemiAnalysis harness. Use for AgentX setup, dataset downloads, concurrency sweeps, or serving latency and throughput comparisons.","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Frun-agentx\u002FSKILL.md",[],[48,112,113,114,115,116,117,118,119,120,121,99,122,36,123,124],"run agentx","agentx","harness","downloads","concurrency","agentic","setup","benchmark","with","latency","serving","dataset","throughput",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":50},"01M6BXZ8QSX51J73Q17W8D7HFW","release-cherry-pick","Audit merged bug-fix PRs and release NVBugs for missing cherry-pick labels, then cherry-pick labeled PRs into a release branch and open a PR. Use when asked to \"cherry-pick PRs for release\u002FX.Y.Z\", \"pick PRs to release branch\", \"verify cherry-pick labels\", or \"cherry-pick labeled PRs\".","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Frelease-cherry-pick\u002FSKILL.md",[],[132,133,134,135,136,137,138,139,140,99,141,142,143,144,36,30,145,146],"release cherry pick","cherry pick","release","pick","open","pr","verify","audit","branch","fix","labels","missing","prs","bug","bug-fix",{"skillNo":148,"name":149,"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":156,"publishedAt":50},"01M6BXZ5WQYP885CTNKGH5GQFY","quant-recipe-search","Use when the user asks to find, search for, or optimize the best quantization recipe for a model, including direct requests like \"find the best quantization recipe and generate a PTQ checkpoint.\" Guides the multi-candidate loop: choose compute-vs-memory success metrics, select ModelOpt recipe baselines, design AutoQuant\u002Fmanual recipe deltas, interpret sensitivity, and decide next candidates. Do NOT use for a single known PTQ recipe run (use ptq), serving (use deployment), creating\u002Frunning evals (use evaluation or launching-evals), monitoring jobs (use monitor), MLflow browsing (use accessing-mlflow), or comparing completed baseline-vs-candidate scores only (use compare-results).","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Fquant-recipe-search\u002FSKILL.md",[153],{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[157,158,159,160,161,87,162,163,164,165,166,167,168,169,170,171,172,173,174,175,30],"search","quant recipe search","recipe","quant","generate","memory","select","choose","design","loop","monitoring","deltas","decide","only","browsing","candidate","guides","optimize","next",{"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":182,"publishedAt":50},"01M6BXZ3AG8ER5HWGNK6CGT6MT","qad","Run explicitly requested ModelOpt Quantization-Aware Distillation (QAD) through Megatron Bridge (recommended) or Hugging Face Transformers to recover a measured BF16-to-PTQ accuracy gap. Use only when the user explicitly asks for QAD, including its topology, data preparation, launch, resume, checkpoint export, or recovery decisions.","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Fqad\u002FSKILL.md",[],[178,183,184,185,48,91,186,94,187,188,99,189,170,36,190,191,192,193,194,195,30],"data preparation","recovery","Transformers","launch","megatron","bridge","accuracy","decisions","resume","gap","Quantization","preparation","export",{"skillNo":197,"name":94,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":50},"01M6BXZ06YTSZFT9PZA2P2RGWD","Use when the user asks to \"quantize a model\", \"run PTQ\", \"post-training quantization\", \"NVFP4 quantization\", \"FP8 quantization\", \"INT8 quantization\", \"INT4 AWQ\", \"quantize LLM\", \"quantize MoE\", \"quantize VLM\", or needs to produce a quantized HuggingFace checkpoint from a pretrained model using ModelOpt. Do NOT use for multi-candidate recipe exploration or optimization (use quant-recipe-search).","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FModel-Optimizer\u002Fblob\u002Fmain\u002Fplugins\u002Fmodelopt\u002Fskills\u002Fptq\u002FSKILL.md",[],[94,202,87,48,203,91,157,92,204,205,206,207,159,30,172,208,209,97,99,210,36],"HuggingFace","Optimization","FP8","Post-Training","produce","exploration","quantize","AWQ","INT8"]