amd/skills

tracelens-analysis-orchestrator

Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel…

Trending #5239 First seen Jul 2, 2026

Installation

$ npx skills add https://github.com/amd/skills
Feature your product here Skill page unit · reach builders installing agent skills View pricing →

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from amd/skills · top by installs.

npx skills add https://github.com/amd/skills

Browse all from amd/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 336
License LICENSE
Default branch main
Open issues 44
Status Active

History

  1. First seen on skills.sh
  2. First recorded snapshot · 203 installs

SKILL.md

<!-- 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, 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 the Task tool only where reference.md says “subagent” (Steps 7, 8, 10). The orchestrator runs everything else, including Step 8.5, using the command prefix from <outputdir>/cache/cmdprefix.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: systemfindings/, categoryfindings/, categorydata/, metadata/, perfreport*.xlsx, CSV folders — see package README for layout.

Agent layout

Project subagents ship with this skill: TraceLens/Agent/Analysis/skills/analysis-orchestrator/agents/*.md.