About tracelens-analysis-orchestrator
A skill for coordinating system-level and GPU-kernel analysis of performance traces. It is aimed at analysis agents and combines shared trace preparation, parallel subagents, validation, and an aggregated `analysis.md` report.
Key features
- 01Shared trace loading and preparation
- 02Parallel system-level analysis
- 03Parallel kernel-category analysis
- 04Findings aggregation and validation
- 05`analysis.md` report generation
Use cases
- 01Reviewing system and kernel behavior from a performance trace
- 02Comparing GPU kernel categories in one analysis workflow
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/tracelens-analysis-orchestratorin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
.federated.jsonagents/convolution-analyzer.mdcpu-idle-analyzer.mdelementwise-analyzer.mdgemm-analyzer.mdgeneric-op-analyzer.mdkernel-coherence-agent.mdkernel-fusion-analyzer.mdkernel-stem-preprocessing-agent.mdkernel-unification-agent.mdmodel-identification-agent.mdmoe-analyzer.mdmulti-kernel-analyzer.mdnorm-analyzer.mdreduce-analyzer.mdsdpa-analyzer.mdsemantic-comparison-agent.mdtriton-analyzer.mdevals/.gitignoreEVAL_RUBRICS.mdevals/analysis_tests/combined_traces_comparative.csvcombined_traces_standalone.csvevals/eval_scripts/generate_ref.shkill_eval_jobs.shpack_test_archives.shrun_pi_analysis_in_docker.shrun_repeatability_parallel.shevals/eval_utils/aggregate_repeatability.pycompare_lca_partitions.pymanual_eval_checklist.mdDetails
From the project READMEAnalysis orchestrator
Coordinate system-level analysis (CPU/idle, kernel fusion, multi-kernel / comm / memcpy) and compute-kernel analysis (GEMM, SDPA, elementwise, etc.): one trace load, shared prep, parallel subagents, then aggregation into analysis.md.
Full procedure
Follow reference.md for every step (user prompts, <prefix> / {CMD} usage, CLI commands, subagent launch text, validation, report tee order, plot embedding, and trace diagnostics).
Workflow index
0. Query User Inputs (Platform, Trace Path(s), Analysis Mode, Environment Setup)
1. Generate Performance Report (branches on analysis mode: training vs inference then, comparison scope)
2. Trace-Quality Gate → Deterministic fallback analysis
3-6. Prepare Category Data (GPU Util, Top Ops, Tree Data, Multi-Kernel Data, Category Filtering)
7. System-Level Analysis (PARALLEL) → system_findings/
8. Compute Kernel Subagents (PARALLEL) → category_findings/
8.5. Aggregate → priority_data.json::findings[]
9. Validate Subagent Outputs
10. load_findings + Model Identification (subagent) → metadata/model_info.json
11. Render performance PNG if agent_extension.py is absent
12. Generate analysis.md (orchestrator writes via <prefix> tee), optional extension, embed PNG
Rules
- Subagents: Use your runner's subagent primitive (the Task tool in Claude Code or Cursor,
spawn_agentunder Codex) only where reference.md says “subagent” (Steps 7, 8, 10). The orchestrator runs everything else, including Step 8.5, using the command prefix from<output_dir>/cache/cmd_prefix.txt({CMD}substitution). - 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.
- Subagent prompts: Point each subagent at the checked-in agent file under
TraceLens/Agent/Analysis/skills/analysis-orchestrator/agents/<name>.md(see reference.md for exact paths and prompt shells).
Primary outputs
- Deliverable:
<output_dir>/analysis.md - Internals:
system_findings/,category_findings/,category_data/,metadata/,perf_report*.xlsx, CSV folders — see package README for layout.
Agent layout
Project subagents ship with this skill: TraceLens/Agent/Analysis/skills/analysis-orchestrator/agents/*.md.