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 Run Training

by inclusionAI in inclusionAI/AReno

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

Apache-2.0Auto-check passedAI & LLM Engineering

Install Areno Run Training

skills CLI
$ npx skills add inclusionAI/AReno --skill areno-run-training -a claude-code

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

GitHub CLI
$ gh skill install inclusionAI/AReno areno-run-training --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-run-training .claude/skills/areno-run-training && 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-run-training
GitHub stars
323
Token cost
~782 tokens
SKILL.md length
328 words
Files
7 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Works in 8 steps: Record git rev-parse HEAD, environment… → Classify SFT, DPO, rollout RL, or… → Inspect both the raw schema and the… → …
  • Training commands
  • SKILL.md covers Select the path, Workflow, Capacity invariants and Completion evidence
  • Runs Python scripts from its folder; calls python and git

What it does

Areno Run Training is an agent skill from inclusionAI/AReno. Run, configure, retry, and validate AReno SFT, DPO, GSPO, GRPO, PPO, and agentic training. Use for training commands, dataset or reward setup, smoke validation, real-step execution, checkpoint saving, or failed training retries. Do not use for serving-only tasks or framework implementation work.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/algorithm-matrix.md` and `references/data-contracts.md`).

It sits in AI & LLM Engineering, covering Fine-tuning and Reinforcement learning. 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

  • Training commands
  • Smoke validation
  • Real-step execution
  • Checkpoint saving

Example prompts

  • “/areno-run-training”

Requirements

  • Python 3

Workflow steps

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

  1. Record git rev-parse HEAD, environment facts from areno env --json and areno check, GPU state, checkpoint source, ModelScope dataset…
  2. Classify SFT, DPO, rollout RL, or agentic RL. Read references/data-contracts.md.
  3. Inspect both the raw schema and the normalized schema. Treat a missing rollout prompt/messages as a required-loader error, not a warning.
  4. Build the smallest command expressing the requested real workload. Preserve user-provided max_new_tokens and max_context_len, and include…
  5. Use smoke or tune only when useful. Smoke is capacity evidence, not task completion.
  6. Run the real job. Confirm the requested trainer step advances. For rollout, inspect one coherent sample and reward.
  7. On failure, use references/failure-triage.md. Fix the first causal error.
  8. If saving is requested, verify output and reload it through the intended adapter.

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
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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 Run Training loads about 782 tokens when it runs, and up to ~1.4k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 328 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~782
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.4k

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). 328 words, ~782 tokens.

Download SKILL.mdSave it as .claude/skills/areno-run-training/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
areno-run-training
description
Run, configure, retry, and validate AReno SFT, DPO, GSPO, GRPO, PPO, and agentic training. Use for training commands, dataset or reward setup, smoke validation, real-step execution, checkpoint saving, or failed training retries. Do not use for serving-only tasks or framework implementation work.

Run AReno Training

Read repository AGENTS.md, CODEMAP.md, and current areno train --help before building a command.

For remote model or dataset references, explicitly pass --model-hub modelscope. Do not substitute a Hugging Face download when the ModelScope asset is missing; request a valid ModelScope ID or local path.

Select the path

Read references/algorithm-matrix.md. Inspect a bounded dataset sample with:

bash
python .agents/skills/areno-run-training/scripts/inspect_dataset.py \
  --dataset-path <path-or-ref> --model-hub modelscope \
  [--loader examples/.../dataset_loader.py] --algo <algo>

Do not build or run the training command until this inspection returns "ok": true. If raw rollout rows lack prompt or messages, select a dataset loader and rerun the inspection with --loader; pass the same path to training as --dataset-loader-fn. For GSM8K-style question/answer rows, use examples/math/dataset_loader.py.

Use scripts/read_metrics.py to inspect event keys or selected scalar series. Do not parse stdout as the metric source.

Workflow

  1. Record git rev-parse HEAD, environment facts from areno env --json and areno check, GPU state, checkpoint source, ModelScope dataset source, and resolved local paths.
  2. Classify SFT, DPO, rollout RL, or agentic RL. Read references/data-contracts.md.
  3. Inspect both the raw schema and the normalized schema. Treat a missing rollout prompt/messages as a required-loader error, not a warning.
  4. Build the smallest command expressing the requested real workload. Preserve user-provided max_new_tokens and max_context_len, and include the verified loader with --dataset-loader-fn.
  5. Use smoke or tune only when useful. Smoke is capacity evidence, not task completion.
  6. Run the real job. Confirm the requested trainer step advances. For rollout, inspect one coherent sample and reward.
  7. On failure, use references/failure-triage.md. Fix the first causal error.
  8. If saving is requested, verify output and reload it through the intended adapter.

Capacity invariants

  • batch_size * n_samples is total sample demand; max_running_prompts is concurrent active capacity.
  • Rollout memory follows cache/context/concurrency. Train memory follows mini_bs, sequence length, activation and optimizer state.
  • --drop-rollout-state changes lifecycle memory, not task semantics.
  • Reduce concurrency or microbatch before semantic token limits.

Completion evidence

Report command, commit, model/dataset, topology, observed step and key metrics, plus save/reload evidence when required. Model load or smoke alone is not completion.

© 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 6 other files (scripts, references) in .agents/skills/areno-run-training of inclusionAI/AReno.

  • SKILL.md
  • agents/openai.yaml
  • references/algorithm-matrix.md
  • references/data-contracts.md
  • references/failure-triage.md
  • scripts/inspect_dataset.py
  • scripts/read_metrics.py

Open the folder on GitHubat commit 25f5fed

Compare with similar skills

Areno Run Training 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 Run Training compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Areno Run Training this skillinclusionAI/AReno323—~782Automated safety check: PassApache-2.0
Train RlOpenPipe/ART11k—~2.4kAutomated safety check: PassApache-2.0
Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide1.7k—~830Automated safety check: PassApache-2.0
Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs13k6 repos~2.9kAutomated safety check: PassMIT
Optim AgentOptim-Agent/optim-agent801—~1.3kAutomated safety check: PassMIT
Safactory WorkflowsAI45Lab/SAfactory236—~1.8kAutomated safety check: PassNone

Similar skills

  • Train Rl

    OpenPipe/ART

    RL training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Qwopus27b Rl Training

    R6410418/Jackrong-llm-finetuning-guide

    Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.

    1.7k GitHub stars~830 tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Fine Tuning With Trl

    Orchestra-Research/AI-Research-SKILLs

    Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.

    13k GitHub starsUsed in 6 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Optim Agent

    Optim-Agent/optim-agent

    A skill your agent uses when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies…

    801 GitHub stars~1.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Safactory Workflows

    AI45Lab/SAfactory

    Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training.

    236 GitHub stars~1.8k tokensUpdated 17 days ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face LLM Trainer

    huggingface/skills

    Official

    Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.

    11k GitHub starsUsed in 1 repo~7.2k tokens
    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 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 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 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

Categories

Questions about Areno Run Training

What does Areno Run Training do?

Run, configure, retry, and validate AReno SFT, DPO, GSPO, GRPO, PPO, and agentic training. Areno Run Training is an agent skill from inclusionAI/AReno. Run, configure, retry, and validate AReno SFT, DPO, GSPO, GRPO, PPO, and agentic training.

When should I use Areno Run Training?

Areno Run Training fits situations like: training commands; smoke validation; real-step execution; checkpoint saving.

How do I install Areno Run Training in Claude Code?

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

How do I install Areno Run Training in Codex?

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

Can I use Areno Run Training 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-run-training -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-run-training, .gemini/skills/areno-run-training, .github/skills/areno-run-training and .opencode/skills/areno-run-training in your project.

What does Areno Run Training need to run?

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

Does Areno Run Training access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Areno Run Training 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 Run Training use?

Areno Run Training 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 Run Training use?

About 782 tokens (SKILL.md is roughly 3.1k 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 568 tokens, read only when the agent opens those files.

What are the alternatives to Areno Run Training?

Skills that share tags, products or a category with Areno Run Training: Train Rl (OpenPipe/ART, 11k stars), Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars), Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Optim Agent (Optim-Agent/optim-agent, 801 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Areno Run Training?

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.