Individual skill

tracelens-analysis-orchestrator

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, run it from config <run.yaml>, analyze a trace, compare two traces, or mentions standalone or comparative TraceLens analysis.

skills/tracelens-analysis-orchestrator/SKILL.md

Read pinned source

Source commit e6ee0b7c2e78babc7c7240b34f3fea0a6f510a65

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 481
Repository last updated: Nov 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

operations Derived category
data Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.federated.jsonasset · 354 bytes
SKILL.mdcore · 3,088 bytes
agents/convolution-analyzer.mddoc · 7,916 bytes
agents/cpu-idle-analyzer.mddoc · 6,408 bytes
agents/elementwise-analyzer.mddoc · 7,250 bytes
agents/gemm-analyzer.mddoc · 6,412 bytes
agents/generic-op-analyzer.mddoc · 9,730 bytes
agents/kernel-coherence-agent.mddoc · 6,420 bytes
agents/kernel-fusion-analyzer.mddoc · 14,920 bytes
agents/kernel-stem-preprocessing-agent.mddoc · 5,449 bytes
agents/kernel-unification-agent.mddoc · 5,735 bytes
agents/model-identification-agent.mddoc · 4,290 bytes
agents/moe-analyzer.mddoc · 8,665 bytes
agents/multi-kernel-analyzer.mddoc · 11,732 bytes
agents/norm-analyzer.mddoc · 6,876 bytes
agents/reduce-analyzer.mddoc · 6,456 bytes
agents/sdpa-analyzer.mddoc · 10,880 bytes
agents/semantic-comparison-agent.mddoc · 10,861 bytes
agents/triton-analyzer.mddoc · 7,016 bytes
evals/.gitignoreasset · 266 bytes
evals/EVAL_RUBRICS.mddoc · 17,847 bytes
evals/README.mddoc · 19,259 bytes
evals/analysis_tests/combined_traces_comparative.csvasset · 5,191 bytes
evals/analysis_tests/combined_traces_standalone.csvasset · 10,541 bytes
evals/eval_scripts/generate_ref.shruns · 14,339 bytes
evals/eval_scripts/kill_eval_jobs.shruns · 4,127 bytes
evals/eval_scripts/pack_test_archives.shruns · 4,732 bytes
evals/eval_scripts/run_pi_analysis_in_docker.shruns · 20,031 bytes
evals/eval_scripts/run_repeatability_parallel.shruns · 24,915 bytes
evals/eval_utils/aggregate_repeatability.pyruns · 24,657 bytes
evals/eval_utils/compare_lca_partitions.pyruns · 16,624 bytes
evals/eval_utils/manual_eval_checklist.mddoc · 3,436 bytes
evals/eval_utils/merge_results.pyruns · 3,023 bytes
evals/eval_utils/quality_scripted_evals.pyruns · 8,988 bytes
evals/eval_utils/report_section_rules.yamlasset · 3,890 bytes
evals/eval_utils/workflow_scripted_evals.pyruns · 54,748 bytes
evals/evals.jsonasset · 3,133 bytes
evals/machine.ymlasset · 285 bytes
evals/partial_tests/README.mddoc · 5,465 bytes
evals/partial_tests/eval_utils/semantic_partition_scripted_evals.pyruns · 6,004 bytes
evals/partial_tests/eval_utils/semantic_purity_aggregate.pyruns · 9,397 bytes
evals/partial_tests/generate_gold_ref.shruns · 4,977 bytes
evals/partial_tests/partial_test_cases.csvasset · 1,044 bytes
evals/partial_tests/run_partial_tests.shruns · 7,962 bytes
reference.mddoc · 36,459 bytes
skill-card.mddoc · 396 bytes
templates/analysis_template.mddoc · 26,630 bytes
templates/sub_agent_spec.mddoc · 22,192 bytes

Read excerpt


<!--
Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.

See LICENSE for license information.
-->

# Analysis 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](reference.md)** for every step (user prompts, `<prefix>` / `{CMD}` usage, CLI commands, subagent launch text, validation, report `tee` order, and plot embedding).