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.
Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA.
Install Oob Perf Analysis
$ npx skills add intel/torch-xpu-ops --skill oob-perf-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install intel/torch-xpu-ops oob-perf-analysis --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/intel/torch-xpu-ops.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/oob-perf-analysis .claude/skills/oob-perf-analysis && 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 "oob-perf-analysis" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysis into .claude/skills/oob-perf-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oob-perf-analysis", 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/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysisType 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 intel/torch-xpu-ops --skill oob-perf-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install intel/torch-xpu-ops oob-perf-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/oob-perf-analysis .agents/skills/oob-perf-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "oob-perf-analysis" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysis into .agents/skills/oob-perf-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oob-perf-analysis", 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 intel/torch-xpu-ops --skill oob-perf-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install intel/torch-xpu-ops oob-perf-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/oob-perf-analysis .cursor/skills/oob-perf-analysis && 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 "oob-perf-analysis" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysis into .cursor/skills/oob-perf-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oob-perf-analysis", 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/intel/torch-xpu-ops.git --path .claude/skills/oob-perf-analysis--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 intel/torch-xpu-ops --skill oob-perf-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install intel/torch-xpu-ops oob-perf-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/oob-perf-analysis .gemini/skills/oob-perf-analysis && 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 "oob-perf-analysis" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysis into .gemini/skills/oob-perf-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oob-perf-analysis", 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 intel/torch-xpu-ops oob-perf-analysisInstalls 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 intel/torch-xpu-ops --skill oob-perf-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/oob-perf-analysis .github/skills/oob-perf-analysis && 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 "oob-perf-analysis" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysis into .github/skills/oob-perf-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oob-perf-analysis", 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 intel/torch-xpu-ops --skill oob-perf-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install intel/torch-xpu-ops oob-perf-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/oob-perf-analysis .opencode/skills/oob-perf-analysis && 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 "oob-perf-analysis" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/oob-perf-analysis into .opencode/skills/oob-perf-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oob-perf-analysis", 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
oob-perf-analysis- GitHub stars
- 115
- Token cost
- ~681 tokens
- SKILL.md length
- 226 words
- Files
- 9 (incl. references)
- Skills in repo
- 29
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA.
- Works in 3 steps: Read methodology.md before computing any… → Read inputs.md before accessing any… → Report structure is deterministic — same…
- Working with eager profiling artifacts
- SKILL.md covers References, Usage Modes and Operating Rules
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Oob Perf Analysis is an agent skill from intel/torch-xpu-ops, published by the product's own GitHub organization. Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA. Use when working with eager profiling artifacts, per-model reports, fleet summaries, graph consistency, or XPU-vs-CUDA software efficiency analysis.
Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `config/hardware_specs.yaml`, `references/fleet-summary.md` and `references/graph-consistency.md`).
It sits in AI & LLM Engineering, covering Deep learning. It works with CUDA, NVIDIA AI Platform and PyTorch. The licence is Apache-2.0.
When your agent uses it
- Working with eager profiling artifacts
- Per-model reports
- Fleet summaries
- Graph consistency
Example prompts
- “/oob-perf-analysis”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Read methodology.md before computing any metric.
- Read inputs.md before accessing any artifact.
- Report structure is deterministic — same inputs produce same section layout.
What it can do on your machine
Read from SKILL.md and the folder at commit 0187b3b. 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
Oob Perf Analysis loads about 681 tokens when it runs, and up to ~9.4k if it reads all its reference files. Until then it costs about 69 tokens; SKILL.md has 226 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 intel/torch-xpu-ops at commit 0187b3b, republished under its Apache-2.0 licence (© intel). 226 words, ~681 tokens.
Download SKILL.mdSave it as
.claude/skills/oob-perf-analysis/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- oob-perf-analysis
- description
- Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA. Use when working with eager profiling artifacts, per-model reports, fleet summaries, graph consistency, or XPU-vs-CUDA software efficiency analysis.
OOB Perf Analysis Skill
Analyzes OOB eager-mode performance using T1/T2/R roofline methodology to compare XPU and CUDA software efficiency.
Core outputs (all under agent_space_xpu/, git-ignored):
- Per-model markdown reports under
agent_space_xpu/reports/<session>/models/ - Fleet summary under
agent_space_xpu/reports/<session>/summary_eager_inference.md - Graph consistency report under
agent_space_xpu/reports/<session>/graph_consistency_eager_inference.md - Insights summary under
agent_space_xpu/reports/<session>/insights_summary.md
References
| File | Purpose |
|---|---|
| methodology.md | T1/T2/R definitions, formulas, classification thresholds |
| inputs.md | Input file formats, completeness rules, output paths |
| per-model-report.md | Per-model analysis steps and 5-section report structure |
| fleet-summary.md | Fleet aggregation steps and 7-section report structure |
| graph-consistency.md | Graph consistency analysis |
| insights.md | Developer-facing insights summary |
| troubleshooting.md | Diagnosing abnormal R, trace issues, and data problems |
Usage Modes
Per-Model Report Mode
User has raw artifacts and wants model-level T1/T2/R analysis.
Follow: methodology.md → inputs.md → per-model-report.md
Fleet Summary Mode
User wants fleet-wide comparison, model scorecards, op ranking, or projection-quality aggregation.
Follow: fleet-summary.md (references graph-consistency.md for Section 7)
Graph Consistency Mode
User wants to compare CUDA vs XPU computational graphs.
Follow: graph-consistency.md
Insights Mode
Per-model reports and fleet summary exist; user wants a concise developer-facing summary.
Follow: insights.md
Troubleshooting Mode
User asks why R is abnormal, why traces disagree, or why results look suspicious.
Follow: troubleshooting.md
Operating Rules
- Read
methodology.mdbefore computing any metric. - Read
inputs.mdbefore accessing any artifact. - Report structure is deterministic — same inputs produce same section layout.
If a calling workflow explicitly requires a skill marker, append this exact literal final line: Custom skills applied: oob-perf-analysis.
© intel, Apache-2.0. 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 8 other files (references) in .claude/skills/oob-perf-analysis of intel/torch-xpu-ops.
- SKILL.md
- config/hardware_specs.yaml
- references/fleet-summary.md
- references/graph-consistency.md
- references/inputs.md
- references/insights.md
- references/methodology.md
- references/per-model-report.md
- references/troubleshooting.md
Open the folder on GitHubat commit 0187b3b
Compare with similar skills
Oob Perf Analysis 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 |
|---|---|---|---|---|---|---|
| Oob Perf Analysis this skillintel/torch-xpu-ops | 115 | — | ~681 | Automated safety check: Pass | Apache-2.0 | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.2k | Automated safety check: Pass | Apache-2.0 | |
| Hyperpod Version Checkerawslabs/agent-plugins | 912 | 1 repos | ~910 | Automated safety check: Pass | Apache-2.0 | |
| Quark Env Preflightamd/Quark | 181 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Spark Environment Setupwshobson/agents | 40k | — | ~2k | Automated safety check: Pass | MIT | |
| GPU OptimizerMathews-Tom/armory | 327 | — | ~3.5k | Automated safety check: Notes | MIT |
Similar skills
- Official
Hyperpod Version Checker
awslabs/agent-plugins
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia)…
Quark Env Preflight
amd/Quark
Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.
Spark Environment Setup
wshobson/agents
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13).
GPU Optimizer
Mathews-Tom/armory
GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.
Torch Tensorrt
VectorSpaceLab/AREX-Skill
A skill your agent uses for Torch-TensorRT tasks: compiling PyTorch models with TensorRT, dynamic-shape/export workflows, runtime optimization, Triton/C++/distributed deployment, debugging…
More from intel/torch-xpu-ops
All 29 skills in this repo- Official
Intel GPU Device Selection
intel/torch-xpu-ops
Select the Intel GPU device to use when a system has multiple Intel GPU devices.
- Official
Xpu CI Health Check
intel/torch-xpu-ops
Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list…
- Official
At Dispatch V2
intel/torch-xpu-ops
Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code.
- Official
PR Review
intel/torch-xpu-ops
Review pull requests for XPU operator or backend code. An agent skill from intel/torch-xpu-ops.
- Official
Skill Writer
intel/torch-xpu-ops
Guide users through creating Agent Skills for Claude Code. An agent skill from intel/torch-xpu-ops.
- Official
Ut Issue Authoring
intel/torch-xpu-ops
Read the evidence a nightly UT run produced, decide which failures share a root cause and which are machine breakage rather than product bugs, and write one issue draft per root cause to drafts.json.
Related
Works with
Categories
Questions about Oob Perf Analysis
What does Oob Perf Analysis do?
Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA. Oob Perf Analysis is an agent skill from intel/torch-xpu-ops, published by the product's own GitHub organization. Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA.
When should I use Oob Perf Analysis?
Oob Perf Analysis fits situations like: working with eager profiling artifacts; per-model reports; fleet summaries; graph consistency.
How do I install Oob Perf Analysis in Claude Code?
Run `npx skills add intel/torch-xpu-ops --skill oob-perf-analysis -a claude-code`. Or copy the skill folder (.claude/skills/oob-perf-analysis in intel/torch-xpu-ops) into .claude/skills/oob-perf-analysis in your project. Claude Code loads it when a task matches its description.
How do I install Oob Perf Analysis in Codex?
Run `npx skills add intel/torch-xpu-ops --skill oob-perf-analysis -a codex`. Or copy the skill folder (.claude/skills/oob-perf-analysis in intel/torch-xpu-ops) into .agents/skills/oob-perf-analysis in your project. Codex loads it when a task matches its description.
Can I use Oob Perf Analysis 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 intel/torch-xpu-ops --skill oob-perf-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/oob-perf-analysis, .gemini/skills/oob-perf-analysis, .github/skills/oob-perf-analysis and .opencode/skills/oob-perf-analysis in your project.
What does Oob Perf Analysis need to run?
SKILL.md names no scripts, command-line tools or credentials: Oob Perf Analysis is instructions for the agent only.
Does Oob Perf Analysis 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 Oob Perf Analysis 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 Oob Perf Analysis use?
Oob Perf Analysis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Oob Perf Analysis use?
About 681 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.7k tokens, read only when the agent opens those files.
What are the alternatives to Oob Perf Analysis?
Skills that share tags, products or a category with Oob Perf Analysis: Graphsignal (graphsignal/graphsignal, 257 stars), Hyperpod Version Checker (awslabs/agent-plugins, 912 stars), Quark Env Preflight (amd/Quark, 181 stars) and Spark Environment Setup (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Oob Perf Analysis?
intel (a GitHub organization, an official publisher) maintains it in intel/torch-xpu-ops, which has 115 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 6, 2026.
Source: intel/torch-xpu-ops on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.