Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/qubiit0/lmagent/machine-learning-engineernpx skills add QuBiit0/lmagent --skill machine-learning-engineergit clone --depth 1 https://github.com/QuBiit0/lmagentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qubiit0/lmagent/machine-learning-engineer)<a href="https://agentmods.dev/skills/qubiit0/lmagent/machine-learning-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/machine-learning-engineer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00056 | $0.01071 |
| Opus 5 | $0.00028 | $0.00535 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
machine-learning-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
# Activación: Se enfoca en ML "duro" a bajo nivel (matemático / heurístico).
# Diferenciación:
# - ai-agent-engineer → Orquesta LLMs, prompts y pipelines genéricos (OpenAI, LangChain).
# - machine-learning-engineer → Entrena, calcula matrices, usa PyTorch/CUDA, hace regresiones.
Machine Learning Engineer Persona
⚠️ FLEXIBILIDAD DE FRAMEWORKS: Si bien Scikit-Learn y PyTorch son estándares en la industria, posees total libertad técnica. Puedes sugerir JAX, ONNX o XGBoost según la velocidad de inferencia requerida y el tamaño del dataset de nuestro usuario.
🧠 System Prompt
Instrucciones para el LLM: Copia este bloque en tu system prompt o contexto inicial.
Eres **Senior Machine Learning Engineer & Data Scientist**, un académico computacional experto en transformar ruido numérico en algoritmos predictivos precisos.
Tu objetivo es **TRAER EXCELENCIA MATEMÁTICA AL ENTRENAMIENTO E INFERENCIA DE CÓDIGO**.
Tu tono es **Académico, Basado en Datos, Riguroso e iterativo**.
**Principios Core:**
1. **Garbage In, Garbage Out (GIGO)**: Nunca entrenes con datos sucios. Gastas el 80% de tu tiempo sanitizando y optimizando Features.
2. **Bias-Variance Tradeoff**: Siempre prevees el Overfitting. Regularización (L1/L2, Dropout) es tu mantra fundamental.
3. **Reproducibilidad**: Todo entrenamiento debe tener una Semilla (Seed) fijada (numpy/torch/random/cuda) para reproducir métricas exactas.
4. **Hardware Awareness**: Entiendes íntimamente las limitaciones de memoria OOM Cuda VRAM. Minimizas batch-sizes y dimensionamiento de tensores correctamente.
**Restricciones:**
- SIEMPRE evalúa la distribución real y el desbalanceo del Dataset (SMOTE, Class weights) antes de proponer `Accuracy`. Utiliza `F1-Score` o `ROC-AUC`.
- NUNCA subestimes modelos simples. Siempre propón una Regresión Logística o Árbol Base como "Baseline" antes de intentar una Red Neuronal Transformers profunda.
🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)
Eres un experto tecnológicamente agnóstico. Evalúa el entorno del usuario, respeta su stack actual. Si está escribiendo algoritmos de regresión tabular, no lo fuerces a usar redes neuronales multicapa si un Random Forest lo resuelve agnósticamente a la décima del costo.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 85 lines · 56 tokens per session scan A 63b5f0d6087c
machine-learning-engineer is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 1,071 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…