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 Model Adaptation

by inclusionAI in 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…

Apache-2.0Auto-check passedAI & LLM Engineering

Install Areno Model Adaptation

skills CLI
$ npx skills add inclusionAI/AReno --skill areno-model-adaptation -a claude-code

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

GitHub CLI
$ gh skill install inclusionAI/AReno areno-model-adaptation --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-model-adaptation .claude/skills/areno-model-adaptation && 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-model-adaptation
GitHub stars
323
Token cost
~722 tokens
SKILL.md length
277 words
Files
9 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

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…

  • Works in 7 steps: Config and construction: implement… → Load: implement checkpoint mapping and… → Inference: compare bounded reference… → …
  • AI & LLM Engineering work in your project
  • SKILL.md covers Inventory first, Gated phases and Completion evidence
  • Runs Python scripts from its folder; calls python and pip

What it does

Areno Model Adaptation is an agent skill from 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, and checkpoint round trips. Use only when model-specific implementation or compatibility changes are required.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/checkpoint-contract.md` and `references/kernel-policy.md`).

It sits in AI & LLM Engineering. It works with CUDA. 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

  • AI & LLM Engineering work in your project

Example prompts

  • “/areno-model-adaptation”

Requirements

  • Python 3

Workflow steps

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

  1. Config and construction: implement model-family matching and ModelConfig translation. Verify local TP shapes.
  2. Load: implement checkpoint mapping and prove claimed key coverage. Read references/checkpoint-contract.md.
  3. Inference: compare bounded reference logits or staged activations, then decode coherent text. Multimodal paths must verify processor…
  4. Training: run forward/backward and verify finite nonzero gradients. Then run an end-to-end training job for at least two consecutive…
  5. Save: implement inverse mapping, save, reload, and compare assets/tensors using the scripts in this directory.
  6. Parallel/runtime: validate requested TP, packed/sequence-parallel positions, lifecycle hooks, and CUDA graph decode.
  7. Performance: optimize only after prior gates pass. Read references/kernel-policy.md.

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

    Shell commands in SKILL.md call:

    • python
    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, 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 Model Adaptation loads about 722 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 277 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~722
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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). 277 words, ~722 tokens.

Download SKILL.mdSave it as .claude/skills/areno-model-adaptation/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
areno-model-adaptation
description
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, and checkpoint round trips. Use only when model-specific implementation or compatibility changes are required.

Adapt an AReno Model

Read AGENTS.md, CODEMAP.md, the nearest registered adapter, and the upstream reference implementation. External frameworks define semantics only unless AReno explicitly owns the dependency.

Develop in a dedicated local branch and update a remote GPU checkout only by pulling that committed branch. Read references/remote-validation.md. Obtain model assets from ModelScope as described in references/modelscope-assets.md.

Inventory first

bash
python .agents/skills/areno-model-adaptation/scripts/inspect_checkpoint.py <checkpoint> \
  [--pattern 'model.layers.*'] [--limit 200]

Record architecture/config fields, tokenizer or processor class, tensor names/shapes/dtypes, fused projection order, tied weights, and reference outputs. Never infer layout from class names.

Gated phases

  1. Config and construction: implement model-family matching and ModelConfig translation. Verify local TP shapes.
  2. Load: implement checkpoint mapping and prove claimed key coverage. Read references/checkpoint-contract.md.
  3. Inference: compare bounded reference logits or staged activations, then decode coherent text. Multimodal paths must verify processor order, vision tower, projector/merger, token replacement, and position IDs.
  4. Training: run forward/backward and verify finite nonzero gradients. Then run an end-to-end training job for at least two consecutive successful steps with the adapted model. Verify finite losses, metrics, and gradients on both steps. For rollout algorithms, also compare rollout and fixed-token train logprobs.
  5. Save: implement inverse mapping, save, reload, and compare assets/tensors using the scripts in this directory.
  6. Parallel/runtime: validate requested TP, packed/sequence-parallel positions, lifecycle hooks, and CUDA graph decode.
  7. Performance: optimize only after prior gates pass. Read references/kernel-policy.md.

If areno/accel changes, install remotely with pip install -e . --no-deps --no-build-isolation; otherwise pull the branch without reinstalling.

Completion evidence

Provide config mapping, checkpoint coverage, reference comparison, coherent decode, evidence from at least two successful end-to-end training steps, save/reload comparison, requested topology, and CUDA graph evidence. A successful weight load or a single backward pass 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 8 other files (scripts, references) in .agents/skills/areno-model-adaptation of inclusionAI/AReno.

  • SKILL.md
  • agents/openai.yaml
  • references/checkpoint-contract.md
  • references/kernel-policy.md
  • references/modelscope-assets.md
  • references/remote-validation.md
  • scripts/compare_assets.py
  • scripts/compare_ckpt_diff.py
  • scripts/inspect_checkpoint.py

Open the folder on GitHubat commit 25f5fed

Compare with similar skills

Areno Model Adaptation 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 Model Adaptation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Areno Model Adaptation this skillinclusionAI/AReno323—~722Automated safety check: PassApache-2.0
Esmfold2JimLiu/science-skills2284 repos~2.5kAutomated safety check: PassApache-2.0
MUSA GPU Training Optimizeropen-infra-skills/infra-skills141—~1.7kAutomated safety check: PassApache-2.0
Benchmark TuneMesh-LLM/mesh-llm3.5k—~1.6kAutomated safety check: PassApache-2.0
Cuda Kernel OptimizerKernelFlow-ops/cuda-optimized-skill214—~4.3kAutomated safety check: PassMIT
Hugging Face Local Modelshuggingface/skills11k3 repos~945Automated safety check: PassApache-2.0

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    228 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • 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.

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

  • Benchmark Tune

    Mesh-LLM/mesh-llm

    A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

    3.5k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Cuda Kernel Optimizer

    KernelFlow-ops/cuda-optimized-skill

    Iteratively optimize a CUDA/CUTLASS/Triton kernel only when strict on-device compilation, correctness, timing, and NCU evidence gates pass.

    214 GitHub stars~4.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Models

    huggingface/skills

    Official

    Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.

    11k GitHub starsUsed in 3 repos~945 tokens
    AI & LLM EngineeringAuto-check passed

  • Megatron-LM on SLURM

    NVIDIA/Megatron-LM

    Official

    Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

    18k GitHub stars~1.8k 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 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

Works with

Categories

Questions about Areno Model Adaptation

What does Areno Model Adaptation do?

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…. Areno Model Adaptation is an agent skill from 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, and checkpoint round trips.

When should I use Areno Model Adaptation?

Areno Model Adaptation fits situations like: AI & LLM Engineering work in your project.

How do I install Areno Model Adaptation in Claude Code?

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

How do I install Areno Model Adaptation in Codex?

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

Can I use Areno Model Adaptation 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-model-adaptation -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-model-adaptation, .gemini/skills/areno-model-adaptation, .github/skills/areno-model-adaptation and .opencode/skills/areno-model-adaptation in your project.

What does Areno Model Adaptation need to run?

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

Does Areno Model Adaptation access the network?

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

Is Areno Model Adaptation 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 Model Adaptation use?

Areno Model Adaptation 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 Model Adaptation use?

About 722 tokens (SKILL.md is roughly 2.9k 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 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Areno Model Adaptation?

Skills that share tags, products or a category with Areno Model Adaptation: Esmfold2 (JimLiu/science-skills, 228 stars), MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars), Benchmark Tune (Mesh-LLM/mesh-llm, 3.5k stars) and Cuda Kernel Optimizer (KernelFlow-ops/cuda-optimized-skill, 214 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Areno Model Adaptation?

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.