[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FENK2VM5GGGJHH1JB6S166":3,"skill-same:01M7FENK2VM5GGGJHH1JB6S166":133},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7FENK2VM5GGGJHH1JB6S166","tracelens-analysis-orchestrator",null,"Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md). Use when the user asks to follow the analysis orchestrator, run the agentic analysis workflow, analyze a trace, compare two traces, or mentions standalone or comparative TraceLens analysis.","vvvdwbvvv\u002Fpi-setup","vvvdwbvvv","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F56776714?v=4","01M7FEKVND77XV7GKPW1KE2NYW","Eddie A. Tsai","01M7FEKVP4EXMGZ0DC8H0J58P8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: tracelens-analysis-orchestrator\ndescription: >-\n  Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf\n  reports, prepares category data, runs system-level and compute-kernel subagents in\n  parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md).\n  Use when the user asks to follow the analysis orchestrator, run the agentic analysis\n  workflow, analyze a trace, compare two traces, or mentions standalone or comparative\n  TraceLens analysis.\nlicense: MIT\n---\n\n\u003C!--\nCopyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.\n\nSee LICENSE for license information.\n-->\n\n# Analysis orchestrator\n\nCoordinate **system-level** analysis (CPU\u002Fidle, kernel fusion, multi-kernel \u002F comm \u002F memcpy) and **compute-kernel** analysis (GEMM, SDPA, elementwise, etc.): one trace load, shared prep, parallel subagents, then aggregation into `analysis.md`.\n\n## Full procedure\n\nFollow **[reference.md](reference.md)** for every step (user prompts, `\u003Cprefix>` \u002F `{CMD}` usage, CLI commands, subagent launch text, validation, report `tee` order, plot embedding, and trace diagnostics).\n\n## Workflow index\n\n```\n0. Query User Inputs (Platform, Trace Path(s), Analysis Mode, Environment Setup)\n1. Generate Performance Report (branches on analysis mode: training vs inference then, comparison scope)\n2-5. Prepare Category Data (GPU Util, Top Ops, Tree Data, Multi-Kernel Data, Category Filtering)\n6. System-Level Analysis (PARALLEL) → system_findings\u002F\n7. Compute Kernel Subagents (PARALLEL) → category_findings\u002F\n   7.5. Aggregate → priority_data.json::findings[]\n8. Validate Subagent Outputs\n9. load_findings + Model Identification (subagent) → metadata\u002Fmodel_info.json\n10. Render performance PNG if agent_extension.py is absent\n11. Generate analysis.md (orchestrator writes via \u003Cprefix> tee), optional extension, embed PNG\n```\n\n## Rules\n\n- **Subagents:** Use the Task tool **only** where reference.md says “subagent” (Steps **6**, **7**, **9**). The orchestrator runs everything else, including Step 7.5, using the command prefix from `\u003Coutput_dir>\u002Fcache\u002Fcmd_prefix.txt` (`{CMD}` substitution).\n- **Language:** Prefer vendor-agnostic terms (GPU kernels, collective communication, vendor GEMM library, DNN primitives, GPU graph). When quoting trace data, real kernel names are fine.\n- **Subagent prompts:** Point each subagent at the checked-in agent file under `TraceLens\u002FAgent\u002FAnalysis\u002Fskills\u002Fanalysis-orchestrator\u002Fagents\u002F\u003Cname>.md` (see reference.md for exact paths and prompt shells).\n\n## Primary outputs\n\n- **Deliverable:** `\u003Coutput_dir>\u002Fanalysis.md`\n- **Internals:** `system_findings\u002F`, `category_findings\u002F`, `category_data\u002F`, `metadata\u002F`, `perf_report*.xlsx`, CSV folders — see package README for layout.\n\n## Agent layout\n\nProject subagents ship with this skill: `TraceLens\u002FAgent\u002FAnalysis\u002Fskills\u002Fanalysis-orchestrator\u002Fagents\u002F*.md`.\n","\u003C!--\nCopyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.\n\nSee LICENSE for license information.\n-->\n\n# Analysis orchestrator\n\nCoordinate **system-level** analysis (CPU\u002Fidle, kernel fusion, multi-kernel \u002F comm \u002F memcpy) and **compute-kernel** analysis (GEMM, SDPA, elementwise, etc.): one trace load, shared prep, parallel subagents, then aggregation into `analysis.md`.\n\n## Full procedure\n\nFollow **[reference.md](reference.md)** for every step (user prompts, `\u003Cprefix>` \u002F `{CMD}` usage, CLI commands, subagent launch text, validation, report `tee` order, plot embedding, and trace diagnostics).\n\n## Workflow index\n\n```\n0. Query User Inputs (Platform, Trace Path(s), Analysis Mode, Environment Setup)\n1. Generate Performance Report (branches on analysis mode: training vs inference then, comparison scope)\n2-5. Prepare Category Data (GPU Util, Top Ops, Tree Data, Multi-Kernel Data, Category Filtering)\n6. System-Level Analysis (PARALLEL) → system_findings\u002F\n7. Compute Kernel Subagents (PARALLEL) → category_findings\u002F\n   7.5. Aggregate → priority_data.json::findings[]\n8. Validate Subagent Outputs\n9. load_findings + Model Identification (subagent) → metadata\u002Fmodel_info.json\n10. Render performance PNG if agent_extension.py is absent\n11. Generate analysis.md (orchestrator writes via \u003Cprefix> tee), optional extension, embed PNG\n```\n\n## Rules\n\n- **Subagents:** Use the Task tool **only** where reference.md says “subagent” (Steps **6**, **7**, **9**). The orchestrator runs everything else, including Step 7.5, using the command prefix from `\u003Coutput_dir>\u002Fcache\u002Fcmd_prefix.txt` (`{CMD}` substitution).\n- **Language:** Prefer vendor-agnostic terms (GPU kernels, collective communication, vendor GEMM library, DNN primitives, GPU graph). When quoting trace data, real kernel names are fine.\n- **Subagent prompts:** Point each subagent at the checked-in agent file under `TraceLens\u002FAgent\u002FAnalysis\u002Fskills\u002Fanalysis-orchestrator\u002Fagents\u002F\u003Cname>.md` (see reference.md for exact paths and prompt shells).\n\n## Primary outputs\n\n- **Deliverable:** `\u003Coutput_dir>\u002Fanalysis.md`\n- **Internals:** `system_findings\u002F`, `category_findings\u002F`, `category_data\u002F`, `metadata\u002F`, `perf_report*.xlsx`, CSV folders — see package README for layout.\n\n## Agent layout\n\nProject subagents ship with this skill: `TraceLens\u002FAgent\u002FAnalysis\u002Fskills\u002Fanalysis-orchestrator\u002Fagents\u002F*.md`.\n",{"name":5,"license":15,"description":7},"main","a8aae05a5f530dbf920e93757774f4f89d52228e","payload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator","https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup","https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv","Machine Learning and Storage","2026-10-24 00:19:11",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add vvvdwbvvv\u002Fpi-setup --skill tracelens-analysis-orchestrator",{"tool":37,"command":38},"bunx","bunx skills add vvvdwbvvv\u002Fpi-setup --skill tracelens-analysis-orchestrator",{"tool":40,"command":41},"pnpm","pnpm dlx skills add vvvdwbvvv\u002Fpi-setup --skill tracelens-analysis-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,79,83,87,91,95,99,103,107,113,117,121,125,129],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},".federated.json","REFERENCE","参考文档",354,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002F.federated.json",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"agents\u002Fconvolution-analyzer.md",7913,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fconvolution-analyzer.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"agents\u002Fcpu-idle-analyzer.md",6390,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fcpu-idle-analyzer.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"agents\u002Felementwise-analyzer.md",7238,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Felementwise-analyzer.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"agents\u002Fgemm-analyzer.md",6409,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fgemm-analyzer.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"agents\u002Fgeneric-op-analyzer.md",9727,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fgeneric-op-analyzer.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"agents\u002Fkernel-fusion-analyzer.md",15145,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fkernel-fusion-analyzer.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"agents\u002Fmodel-identification-agent.md",4364,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fmodel-identification-agent.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"agents\u002Fmoe-analyzer.md",8649,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fmoe-analyzer.md",{"path":84,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":85,"sourceHtmlUrl":86},"agents\u002Fmulti-kernel-analyzer.md",12133,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fmulti-kernel-analyzer.md",{"path":88,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":89,"sourceHtmlUrl":90},"agents\u002Fnorm-analyzer.md",6873,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fnorm-analyzer.md",{"path":92,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":93,"sourceHtmlUrl":94},"agents\u002Freduce-analyzer.md",6453,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Freduce-analyzer.md",{"path":96,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":97,"sourceHtmlUrl":98},"agents\u002Fsdpa-analyzer.md",10880,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Fsdpa-analyzer.md",{"path":100,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":101,"sourceHtmlUrl":102},"agents\u002Ftriton-analyzer.md",7013,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fagents\u002Ftriton-analyzer.md",{"path":104,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":105,"sourceHtmlUrl":106},"evals\u002Fevals.json",2438,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fevals\u002Fevals.json",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"evals\u002Fhooks.py","SCRIPT","脚本",6503,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fevals\u002Fhooks.py",{"path":114,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":115,"sourceHtmlUrl":116},"evals\u002Fmachine.yml",12,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fevals\u002Fmachine.yml",{"path":118,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":119,"sourceHtmlUrl":120},"reference.md",33331,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Freference.md",{"path":122,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":123,"sourceHtmlUrl":124},"skill-card.md",396,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Fskill-card.md",{"path":126,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":127,"sourceHtmlUrl":128},"templates\u002Fanalysis_template.md",25675,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Ftemplates\u002Fanalysis_template.md",{"path":130,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":131,"sourceHtmlUrl":132},"templates\u002Fsub_agent_spec.md",20803,"https:\u002F\u002Fgithub.com\u002Fvvvdwbvvv\u002Fpi-setup\u002Fblob\u002Fmain\u002Fpayload\u002Fhome\u002F.agents\u002Fskills\u002Ftracelens-analysis-orchestrator\u002Ftemplates\u002Fsub_agent_spec.md",[]]