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 Validate Correctness

by inclusionAI in inclusionAI/AReno

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

Apache-2.0Auto-check passedAI & LLM Engineering

Install Areno Validate Correctness

skills CLI
$ npx skills add inclusionAI/AReno --skill areno-validate-correctness -a claude-code

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

GitHub CLI
$ gh skill install inclusionAI/AReno areno-validate-correctness --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-validate-correctness .claude/skills/areno-validate-correctness && 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-validate-correctness
GitHub stars
323
Token cost
~389 tokens
SKILL.md length
113 words
Files
5 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Works in 6 steps: State baseline commit and candidate… → Capture environment and workload metadata. → Run baseline and candidate… → …
  • Regression validation
  • SKILL.md covers Primitives and Workflow
  • Runs Python scripts from its folder; calls python

What it does

Areno Validate Correctness is an agent skill from inclusionAI/AReno. Compare an AReno branch, model, checkpoint, algorithm, scheduler, or kernel against a baseline. Use for regression validation, logprob or metric comparison, checkpoint round trips, and correctness gates. Keep performance reporting separate.

Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/validation-matrix.md` and `scripts/compare_arrays.py`).

It sits in AI & LLM Engineering. 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

  • Regression validation
  • Metric comparison
  • Checkpoint round trips
  • Correctness gates

Example prompts

  • “/areno-validate-correctness”

Requirements

  • Python 3

Workflow steps

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

  1. State baseline commit and candidate commit.
  2. Capture environment and workload metadata.
  3. Run baseline and candidate independently. Do not switch the user's dirty worktree.
  4. Compare the earliest meaningful boundary, then downstream outputs.
  5. Explain numerical scale before choosing tolerance. Never loosen it merely to pass.
  6. Report correctness separately from throughput, step time, and memory.

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 2 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 Validate Correctness loads about 389 tokens when it runs, and up to ~522 if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 113 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~389
With references · SKILL.md plus every file in references/, read only if the agent opens them
~522

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). 113 words, ~389 tokens.

Download SKILL.mdSave it as .claude/skills/areno-validate-correctness/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
areno-validate-correctness
description
Compare an AReno branch, model, checkpoint, algorithm, scheduler, or kernel against a baseline. Use for regression validation, logprob or metric comparison, checkpoint round trips, and correctness gates. Keep performance reporting separate.

Validate AReno Correctness

Create an isolated baseline worktree. Keep checkpoint, input, seed, algorithm, topology, dtype, and bounded step count identical.

Primitives

bash
python .agents/skills/areno-validate-correctness/scripts/compare_metrics.py BASE_DIR CANDIDATE_DIR --metric train/loss
python .agents/skills/areno-validate-correctness/scripts/compare_arrays.py base.json candidate.json --atol 1e-5 --rtol 1e-4
python .agents/skills/areno-model-adaptation/scripts/inspect_checkpoint.py /path/to/checkpoint

Read references/validation-matrix.md. Select invariants based on ownership; final loss alone is insufficient for model, algorithm, scheduler, or kernel changes.

Workflow

  1. State baseline commit and candidate commit.
  2. Capture environment and workload metadata.
  3. Run baseline and candidate independently. Do not switch the user's dirty worktree.
  4. Compare the earliest meaningful boundary, then downstream outputs.
  5. Explain numerical scale before choosing tolerance. Never loosen it merely to pass.
  6. Report correctness separately from throughput, step time, and memory.

Completion requires reproducible commands, artifacts, comparison output, and a nonzero exit on failed invariants.

© 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 4 other files (scripts, references) in .agents/skills/areno-validate-correctness of inclusionAI/AReno.

  • SKILL.md
  • agents/openai.yaml
  • references/validation-matrix.md
  • scripts/compare_arrays.py
  • scripts/compare_metrics.py

Open the folder on GitHubat commit 25f5fed

Compare with similar skills

Areno Validate Correctness 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 Validate Correctness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Areno Validate Correctness this skillinclusionAI/AReno323—~389Automated safety check: PassApache-2.0
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
Add Oponnx/onnx22k—~1.2kAutomated safety check: PassApache-2.0
Add Function Bodyonnx/onnx22k—~1.1kAutomated safety check: PassApache-2.0
Add Shape Inferenceonnx/onnx22k—~1.3kAutomated safety check: PassApache-2.0
Onnxtxtonnx/onnx22k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • 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

  • Add Op

    onnx/onnx

    Add a new ONNX operator or update an existing operator to a new opset version.

    22k GitHub stars~1.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Add Function Body

    onnx/onnx

    Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops.

    22k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Add Shape Inference

    onnx/onnx

    Add or update type and shape inference for an ONNX operator.

    22k GitHub stars~1.3k tokensUpdated today
    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

  • Quality Flywheel

    GoogleCloudPlatform/vertex-ai-samples

    Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK.

    792 GitHub stars~2k 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 today
    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 today
    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 today
    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 today
    Auto-check passed

  • Areno Profile Performance

    inclusionAI/AReno

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

    323 GitHub stars~848 tokensUpdated today
    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 today
    Auto-check passed

Categories

Questions about Areno Validate Correctness

What does Areno Validate Correctness do?

Compare an AReno branch, model, checkpoint, algorithm, scheduler, or kernel against a baseline. Areno Validate Correctness is an agent skill from inclusionAI/AReno. Compare an AReno branch, model, checkpoint, algorithm, scheduler, or kernel against a baseline.

When should I use Areno Validate Correctness?

Areno Validate Correctness fits situations like: regression validation; metric comparison; checkpoint round trips; correctness gates.

How do I install Areno Validate Correctness in Claude Code?

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

How do I install Areno Validate Correctness in Codex?

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

Can I use Areno Validate Correctness 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-validate-correctness -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-validate-correctness, .gemini/skills/areno-validate-correctness, .github/skills/areno-validate-correctness and .opencode/skills/areno-validate-correctness in your project.

What does Areno Validate Correctness need to run?

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

Does Areno Validate Correctness 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 Validate Correctness 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 Validate Correctness use?

Areno Validate Correctness 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 Validate Correctness use?

About 389 tokens (SKILL.md is roughly 1.6k 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 133 tokens, read only when the agent opens those files.

What are the alternatives to Areno Validate Correctness?

Skills that share tags, products or a category with Areno Validate Correctness: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Op (onnx/onnx, 22k stars), Add Function Body (onnx/onnx, 22k stars) and Add Shape Inference (onnx/onnx, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Areno Validate Correctness?

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.