Installation

1. 1
   Make sure Claude is on your device and in your terminal.

   Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

   One-time setup

   Copy

   npm i -g @anthropic-ai/claude-code

   Already have it? Skip ahead.

2. 2
   Paste into Claude Code or into your terminal.

   Install

   Sign up to copy

   git clone ht••••••••••••••••••••••••••••••••• •••••••••••••••••• •• ••••• •• ••••••••••••••••••••••••••••••••••• •• •• •• ••••••••••••••••••••••••••••••••••••••••••••• ••••••••••••••••••••••••••••••••••••

   Sign up free to reveal

   This copies the whole skill folder into ~/.claude/skills/domain-ml-moeru-ai/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

   Faster alternative (instruction-only skills)

   Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

   Quick install (SKILL.md only)

   Sign up to copy

   mkdir -p ~/.•••••••••••••••••••••••••••••••• •• •••• ••••• ••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••• •• ••••••••••••••••••••••••••••••••••••••••••••

   Sign up free to reveal
3. 3
   Restart Claude Code.

   Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

4. 4
   Just ask Claude.

   Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理

What this skill does

RULE: Avoid copying large tensors
WHY: Memory bandwidth is bottleneck
RUST: References, views, in-place ops

RULE: Batch operations for GPU efficiency
WHY: GPU overhead per kernel launch
RUST: Batch sizes, async data loading

RULE: Use standard model formats
WHY: Train in Python, deploy in Rust
RUST: ONNX via tract or candle

"Need efficient data pipelines"
    ↓ m10-performance: Streaming, batching
    ↓ polars: Lazy evaluation

"Need GPU inference"
    ↓ m07-concurrency: Async data loading
    ↓ candle/tch-rs: CUDA backend

"Need model loading"
    ↓ m12-lifecycle: Lazy init, caching
    ↓ tract: ONNX runtime

use std::sync::OnceLock;
use tract_onnx::prelude::*;

static MODEL: OnceLock<SimplePlan<TypedFact, Box<dyn TypedOp>, Graph<TypedFact, Box<dyn TypedOp>>>> = OnceLock::new();

fn get_model() -> &'static SimplePlan<...> {
    MODEL.get_or_init(|| {
        tract_onnx::onnx()
            .model_for_path("model.onnx")
            .unwrap()
            .into_optimized()
            .unwrap()
            .into_runnable()
            .unwrap()
    })
}

async fn predict(input: Vec<f32>) -> anyhow::Result<Vec<f32>> {
    let model = get_model();
    let input = tract_ndarray::arr1(&input).into_shape((1, input.len()))?;
    let result = model.run(tvec!(input.into()))?;
    Ok(result[0].to_array_view::<f32>()?.iter().copied().collect())
}

async fn batch_predict(inputs: Vec<Vec<f32>>, batch_size: usize) -> Vec<Vec<f32>> {
    let mut results = Vec::with_capacity(inputs.len());

    for batch in inputs.chunks(batch_size) {
        // Stack inputs into batch tensor
        let batch_tensor = stack_inputs(batch);

        // Run inference on batch
        let batch_output = model.run(batch_tensor).await;

        // Unstack results
        results.extend(unstack_outputs(batch_output));
    }

    results
}