New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Areno Profile Performance

by inclusionAI in inclusionAI/AReno

Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Areno Profile Performance

skills CLI
$ npx skills add inclusionAI/AReno --skill areno-profile-performance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install inclusionAI/AReno areno-profile-performance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/inclusionAI/AReno.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/areno-profile-performance .claude/skills/areno-profile-performance && rm -rf skills-src

Use ~/.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/

Facts

Skill name
areno-profile-performance
GitHub stars
323
Token cost
~848 tokens
SKILL.md length
261 words
Files
10 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance.

  • Works in 9 steps: Record workload, commit, model,… → Find the parent AReno PID and monitor… → Capture per-GPU utilization, memory,… → …
  • Step time is slow and evidence from metrics
  • Runs Python scripts from its folder; calls python
  • Nsight is required

What it does

Areno Profile Performance is an agent skill from inclusionAI/AReno. Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance. Use when throughput or step time is slow and evidence from metrics, py-spy, or Nsight is required. Do not optimize before correctness is established.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/profile-policy.md` and `scripts/build_nsys_command.py`).

It sits in AI & LLM Engineering. It works with Python. The repository describes itself as: An easy-to-use, fast toolkit to scale up RL post-training on a single node. The licence is Apache-2.0.

When your agent uses it

  • Step time is slow and evidence from metrics
  • Nsight is required

Example prompts

  • “/areno-profile-performance”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Record workload, commit, model, topology, token lengths, concurrency, GPU, and dependency versions.
  2. Find the parent AReno PID and monitor its process tree. For train jobs, attach during at least two post-warmup steps. For serve jobs, use…
  3. Capture per-GPU utilization, memory, power, and target-process memory. Memory capacity, compute utilization, and throughput are separate…
  4. For train, list TensorBoard scalar names before selecting series. Summarize stage time, tokens/throughput, communication, optimizer, loss…
  5. For serve, measure TTFT and total request latency with streaming enabled while the GPU and process monitors run. Record prompt/output…
  6. Exclude initialization, checkpoint load, compilation, and CUDA graph capture from steady-state conclusions, but report them separately…
  7. Use py-spy record -p -o /tmp/areno.svg --duration 30 for Python scheduling, data processing, serialization, blocking I/O, or compilation…
  8. Use a bounded Nsight Systems capture for GPU compute, communication, synchronization, allocator activity, or launch gaps. Read…
  9. Compare baseline and candidate with identical workloads and multiple steady-state observations, then re-run correctness validation after…

What it can do on your machine

Read from SKILL.md and the folder at commit 25f5fed. 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

    Ships 7 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Areno Profile Performance loads about 848 tokens when it runs, and up to ~1.1k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~848
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.1k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from inclusionAI/AReno at commit 25f5fed, republished under its Apache-2.0 licence (© inclusionAI). 261 words, ~848 tokens.

Download SKILL.mdSave it as .claude/skills/areno-profile-performance/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
areno-profile-performance
description
Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance. Use when throughput or step time is slow and evidence from metrics, py-spy, or Nsight is required. Do not optimize before correctness is established.

Profile AReno Performance

Profile a bounded, representative train or serve workload. Collect low-overhead time, GPU, process, and TensorBoard evidence first; use sampling or tracing only after those signals identify the subsystem to inspect.

bash
python .agents/skills/areno-profile-performance/scripts/monitor_gpu.py \
  --pid <areno-pid> --duration 60 --output /tmp/areno-gpu.jsonl
python .agents/skills/areno-profile-performance/scripts/monitor_process.py \
  --pid <areno-pid> --duration 60 --output /tmp/areno-process.jsonl
python .agents/skills/areno-profile-performance/scripts/summarize_monitor.py \
  /tmp/areno-gpu.jsonl
python .agents/skills/areno-profile-performance/scripts/summarize_monitor.py \
  /tmp/areno-process.jsonl
python .agents/skills/areno-profile-performance/scripts/summarize_events.py \
  <metrics-dir> --list
python .agents/skills/areno-profile-performance/scripts/summarize_events.py \
  <metrics-dir> --pattern 'time/*' --pattern '*throughput*' --drop-first 1
python .agents/skills/areno-profile-performance/scripts/probe_openai_latency.py \
  --base-url http://127.0.0.1:8000 --model <model> --requests 16 --concurrency 4
python .agents/skills/areno-profile-performance/scripts/build_nsys_command.py \
  --output /tmp/areno-profile -- <bounded-command> [args...]

Workflow

  1. Record workload, commit, model, topology, token lengths, concurrency, GPU, and dependency versions.
  2. Find the parent AReno PID and monitor its process tree. For train jobs, attach during at least two post-warmup steps. For serve jobs, use a fixed request set and concurrency.
  3. Capture per-GPU utilization, memory, power, and target-process memory. Memory capacity, compute utilization, and throughput are separate signals.
  4. For train, list TensorBoard scalar names before selecting series. Summarize stage time, tokens/throughput, communication, optimizer, loss, and memory metrics that actually exist; do not assume fixed tags.
  5. For serve, measure TTFT and total request latency with streaming enabled while the GPU and process monitors run. Record prompt/output lengths and active concurrency.
  6. Exclude initialization, checkpoint load, compilation, and CUDA graph capture from steady-state conclusions, but report them separately when startup is the problem.
  7. Use py-spy record -p <pid> -o /tmp/areno.svg --duration 30 for Python scheduling, data processing, serialization, blocking I/O, or compilation orchestration.
  8. Use a bounded Nsight Systems capture for GPU compute, communication, synchronization, allocator activity, or launch gaps. Read references/profile-policy.md.
  9. Compare baseline and candidate with identical workloads and multiple steady-state observations, then re-run correctness validation after optimization.

Report raw workload metadata, selected window, GPU peak/average memory and utilization, process CPU/RSS, stage breakdown or TTFT/latency, bottleneck evidence, profiler overhead, and before/after metrics. A single warmup step is not a benchmark.

© inclusionAI, 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 9 other files (scripts, references) in .agents/skills/areno-profile-performance of inclusionAI/AReno.

  • SKILL.md
  • agents/openai.yaml
  • references/profile-policy.md
  • scripts/build_nsys_command.py
  • scripts/monitor_gpu.py
  • scripts/monitor_process.py
  • scripts/probe_openai_latency.py
  • scripts/summarize_events.py
  • scripts/summarize_monitor.py
  • scripts/summarize_time_metrics.py

Open the folder on GitHubat commit 25f5fed

Compare with similar skills

Areno Profile Performance 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.

Areno Profile Performance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Areno Profile Performance this skillinclusionAI/AReno323—~848Automated safety check: PassApache-2.0
LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs13k8 repos~3kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs13k7 repos~2.3kAutomated safety check: PassMIT
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k7 repos~1.7kAutomated safety check: PassMIT
Paddle Design DistributedPaddlePaddle/Paddle24k—~660Automated safety check: PassApache-2.0

Similar skills

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Paddle Design Distributed

    PaddlePaddle/Paddle

    A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…

    24k GitHub stars~660 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Onnxtxt

    onnx/onnx

    Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

    22k GitHub stars~1.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from inclusionAI/AReno

All 10 skills in this repo

  • Areno Debug Runtime

    inclusionAI/AReno

    Diagnose failed, hung, slow, OOM, NaN, illegal-memory-access, NCCL, compilation, rollout, or training runs in AReno.

    323 GitHub stars~486 tokensUpdated yesterday
    Auto-check passed

  • Areno Develop Kernel

    inclusionAI/AReno

    Develop, optimize, debug, and validate an AReno CUDA, Triton, fused, attention, convolution, routing, or MoE operator.

    323 GitHub stars~498 tokensUpdated yesterday
    Auto-check passed

  • Areno Run Training

    inclusionAI/AReno

    Run, configure, retry, and validate AReno SFT, DPO, GSPO, GRPO, PPO, and agentic training.

    323 GitHub stars~782 tokensUpdated yesterday
    Auto-check passed

  • Areno Add Algorithm

    inclusionAI/AReno

    Add or modify an AReno algorithm, trainer, loss, advantage calculation, role model, or algorithm-specific configuration.

    323 GitHub stars~501 tokensUpdated yesterday
    Auto-check passed

  • Areno Validate Correctness

    inclusionAI/AReno

    Compare an AReno branch, model, checkpoint, algorithm, scheduler, or kernel against a baseline.

    323 GitHub stars~389 tokensUpdated yesterday
    Auto-check passed

  • Areno Model Adaptation

    inclusionAI/AReno

    Add or debug an AReno model family, including config conversion, module construction, checkpoint load/save, text or multimodal inference, training backward, tensor parallelism, CUDA graph decode…

    323 GitHub stars~722 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Areno Profile Performance

What does Areno Profile Performance do?

Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance. Areno Profile Performance is an agent skill from inclusionAI/AReno. Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance.

When should I use Areno Profile Performance?

Areno Profile Performance fits situations like: step time is slow and evidence from metrics; nsight is required.

How do I install Areno Profile Performance in Claude Code?

Run `npx skills add inclusionAI/AReno --skill areno-profile-performance -a claude-code`. Or copy the skill folder (.agents/skills/areno-profile-performance in inclusionAI/AReno) into .claude/skills/areno-profile-performance in your project. Claude Code loads it when a task matches its description.

How do I install Areno Profile Performance in Codex?

Run `npx skills add inclusionAI/AReno --skill areno-profile-performance -a codex`. Or copy the skill folder (.agents/skills/areno-profile-performance in inclusionAI/AReno) into .agents/skills/areno-profile-performance in your project. Codex loads it when a task matches its description.

Can I use Areno Profile Performance 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 inclusionAI/AReno --skill areno-profile-performance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/areno-profile-performance, .gemini/skills/areno-profile-performance, .github/skills/areno-profile-performance and .opencode/skills/areno-profile-performance in your project.

What does Areno Profile Performance need to run?

Going by SKILL.md and its folder, Areno Profile Performance needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Areno Profile Performance 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 Areno Profile Performance 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Areno Profile Performance use?

Areno Profile Performance 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 Areno Profile Performance use?

About 848 tokens (SKILL.md is roughly 3.4k 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 302 tokens, read only when the agent opens those files.

What are the alternatives to Areno Profile Performance?

Skills that share tags, products or a category with Areno Profile Performance: LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Areno Profile Performance?

inclusionAI (a GitHub organization) maintains it in inclusionAI/AReno, which has 323 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 10, 2026.

Source: inclusionAI/AReno on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.