The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
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…
Install Tracelens Analysis Orchestrator
$ npx skills add amd/skills --skill tracelens-analysis-orchestrator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install amd/skills tracelens-analysis-orchestrator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/amd/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tracelens-analysis-orchestrator .claude/skills/tracelens-analysis-orchestrator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tracelens-analysis-orchestrator" agent skill from https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestrator into .claude/skills/tracelens-analysis-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tracelens-analysis-orchestrator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestratorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add amd/skills --skill tracelens-analysis-orchestrator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install amd/skills tracelens-analysis-orchestrator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tracelens-analysis-orchestrator .agents/skills/tracelens-analysis-orchestrator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tracelens-analysis-orchestrator" agent skill from https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestrator into .agents/skills/tracelens-analysis-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tracelens-analysis-orchestrator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add amd/skills --skill tracelens-analysis-orchestrator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install amd/skills tracelens-analysis-orchestrator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tracelens-analysis-orchestrator .cursor/skills/tracelens-analysis-orchestrator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tracelens-analysis-orchestrator" agent skill from https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestrator into .cursor/skills/tracelens-analysis-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tracelens-analysis-orchestrator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/amd/skills.git --path skills/tracelens-analysis-orchestrator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add amd/skills --skill tracelens-analysis-orchestrator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install amd/skills tracelens-analysis-orchestrator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tracelens-analysis-orchestrator .gemini/skills/tracelens-analysis-orchestrator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tracelens-analysis-orchestrator" agent skill from https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestrator into .gemini/skills/tracelens-analysis-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tracelens-analysis-orchestrator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install amd/skills tracelens-analysis-orchestratorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add amd/skills --skill tracelens-analysis-orchestrator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/amd/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tracelens-analysis-orchestrator .github/skills/tracelens-analysis-orchestrator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tracelens-analysis-orchestrator" agent skill from https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestrator into .github/skills/tracelens-analysis-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tracelens-analysis-orchestrator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add amd/skills --skill tracelens-analysis-orchestrator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install amd/skills tracelens-analysis-orchestrator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tracelens-analysis-orchestrator .opencode/skills/tracelens-analysis-orchestrator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tracelens-analysis-orchestrator" agent skill from https://github.com/amd/skills/tree/main/skills/tracelens-analysis-orchestrator into .opencode/skills/tracelens-analysis-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tracelens-analysis-orchestrator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
tracelens-analysis-orchestrator- GitHub stars
- 398
- Token cost
- ~760 tokens
- SKILL.md length
- 170 words
- Files
- 42
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- The user asks to follow the analysis orchestrator
- SKILL.md covers Full procedure, Workflow index, Rules and Primary outputs, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Run the agentic analysis workflow
What it does
Tracelens Analysis Orchestrator is an agent skill from amd/skills. 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.
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 43 other files (for example `.federated.json`, `agents/convolution-analyzer.md` and `agents/cpu-idle-analyzer.md`).
It sits in AI & LLM Engineering, covering Subagents, Performance optimization and Deep learning. It works with PyTorch. The repository describes itself as: Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack. The licence is MIT.
When your agent uses it
- The user asks to follow the analysis orchestrator
- Run the agentic analysis workflow
- Analyze a trace
- Compare two traces
Example prompts
- “Use the tracelens-analysis-orchestrator skill to orchestrate modular PyTorch profiler trace analysis with TraceLens: generates perf reports…”
- “/tracelens-analysis-orchestrator”
What it can do on your machine
Read from SKILL.md and the folder at commit 6c92b41. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tracelens Analysis Orchestrator loads about 760 tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 170 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from amd/skills at commit 6c92b41, republished under its MIT licence (© amd). 170 words, ~760 tokens.
Download SKILL.mdSave it as
.claude/skills/tracelens-analysis-orchestrator/SKILL.md (or your agent's skills folder). This skill also uses 41 other files; get the full folder from GitHub.- name
- tracelens-analysis-orchestrator
- description
- 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.
- license
- MIT
<!--
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 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 PNGRules
- 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.
© amd, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 41 other files in skills/tracelens-analysis-orchestrator of amd/skills.
- SKILL.md
- .federated.json
- agents/convolution-analyzer.md
- agents/cpu-idle-analyzer.md
- agents/elementwise-analyzer.md
- agents/gemm-analyzer.md
- agents/generic-op-analyzer.md
- agents/kernel-fusion-analyzer.md
- agents/model-identification-agent.md
- agents/moe-analyzer.md
- agents/multi-kernel-analyzer.md
- agents/norm-analyzer.md
- agents/reduce-analyzer.md
- agents/sdpa-analyzer.md
- agents/triton-analyzer.md
- evals/.gitignore
- evals/EVAL_RUBRICS.md
- evals/README.md
- evals/analysis_tests
- … and 23 more
Open the folder on GitHubat commit 6c92b41
Compare with similar skills
Tracelens Analysis Orchestrator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tracelens Analysis Orchestrator this skillamd/skills | 398 | — | ~760 | Automated safety check: Pass | MIT | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| MUSA GPU Training Optimizeropen-infra-skills/infra-skills | 141 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.2k | Automated safety check: Pass | Apache-2.0 | |
| Torch Profiling Tilelang Programssablin39/tilelang-cuda-skills | 145 | — | ~1.3k | Automated safety check: Pass | None | |
| Torch Performance Optimizationalbumentations-team/albucore | 123 | — | ~895 | Automated safety check: Pass | MIT |
Similar skills
MUSA GPU Training Optimizer
open-infra-skills/infra-skills
Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.
Graphsignal
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
Torch Profiling Tilelang Programs
sablin39/tilelang-cuda-skills
Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.
Torch Performance Optimization
albumentations-team/albucore
Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.
Model Inference Optimize
majiayu000/spellbook
优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供…
More from amd/skills
All 9 skills in this repoApu Memory Tuner
amd/skills
Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the…
Lemonade Router Builder
amd/skills
Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.
Local AI Use
amd/skills
Makes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API.
Serving LLMs On Instinct
amd/skills
Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.
Serving LLMs On Epyc
amd/skills
Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda.
Hyperloom Workload Optimizer
amd/skills
Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer.
Related
Works with
Categories
Questions about Tracelens Analysis Orchestrator
What does Tracelens Analysis Orchestrator do?
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…. Tracelens Analysis Orchestrator is an agent skill from amd/skills.md).
When should I use Tracelens Analysis Orchestrator?
Tracelens Analysis Orchestrator fits situations like: the user asks to follow the analysis orchestrator; run the agentic analysis workflow; analyze a trace; compare two traces.
How do I install Tracelens Analysis Orchestrator in Claude Code?
Run `npx skills add amd/skills --skill tracelens-analysis-orchestrator -a claude-code`. Or copy the skill folder (skills/tracelens-analysis-orchestrator in amd/skills) into .claude/skills/tracelens-analysis-orchestrator in your project. Claude Code loads it when a task matches its description.
How do I install Tracelens Analysis Orchestrator in Codex?
Run `npx skills add amd/skills --skill tracelens-analysis-orchestrator -a codex`. Or copy the skill folder (skills/tracelens-analysis-orchestrator in amd/skills) into .agents/skills/tracelens-analysis-orchestrator in your project. Codex loads it when a task matches its description.
Can I use Tracelens Analysis Orchestrator in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add amd/skills --skill tracelens-analysis-orchestrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tracelens-analysis-orchestrator, .gemini/skills/tracelens-analysis-orchestrator, .github/skills/tracelens-analysis-orchestrator and .opencode/skills/tracelens-analysis-orchestrator in your project.
What does Tracelens Analysis Orchestrator need to run?
SKILL.md names no scripts, command-line tools or credentials: Tracelens Analysis Orchestrator is instructions for the agent only.
Does Tracelens Analysis Orchestrator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Tracelens Analysis Orchestrator safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Tracelens Analysis Orchestrator use?
Tracelens Analysis Orchestrator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tracelens Analysis Orchestrator use?
About 760 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Tracelens Analysis Orchestrator?
Skills that share tags, products or a category with Tracelens Analysis Orchestrator: The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars), MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars), Graphsignal (graphsignal/graphsignal, 257 stars) and Torch Profiling Tilelang Programs (sablin39/tilelang-cuda-skills, 145 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tracelens Analysis Orchestrator?
amd (a GitHub organization) maintains it in amd/skills, which has 398 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 7, 2026.
Source: amd/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.