AgentStack
SKILL verified MIT Self-run

Tracelens Analysis Orchestrator

skill-amd-skills-tracelens-analysis-orchestrator · by amd

>-

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-amd-skills-tracelens-analysis-orchestrator

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Tracelens Analysis Orchestrator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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, ` / {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)
2-5. Prepare Category Data (GPU Util, Top Ops, Tree Data, Multi-Kernel Data, Category Filtering)
6. System-Level Analysis (PARALLEL) → system_findings/
7. Compute Kernel Subagents (PARALLEL) → category_findings/
   7.5. Aggregate → priority_data.json::findings[]
8. Validate Subagent Outputs
9. load_findings + Model Identification (subagent) → metadata/model_info.json
10. Render performance PNG if agent_extension.py is absent
11. Generate analysis.md (orchestrator writes via  tee), optional extension, embed PNG

Rules

  • 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 /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/.md (see reference.md for exact paths and prompt shells).

Primary outputs

  • Deliverable: /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.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

  • Author: amd
  • Source: amd/skills
  • License: MIT
  • Homepage: https://developer.amd.com/

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.