Senior ML Engineer

What it does

When your agent uses it

• The user asks about deploying ML models to production
• Setting up MLOps infrastructure (MLflow
• Monitoring model performance
• Building RAG pipelines

Example prompts

• “/senior-ml-engineer”

Requirements

• Python 3
• Docker

Workflow steps

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

1. 1Export model to standardized format (ONNX, TorchScript, SavedModel)
2. 2Package model with dependencies in Docker container
3. 3Deploy to staging environment
4. 4Run integration tests against staging
5. 5Deploy canary (5% traffic) to production
6. 6Monitor latency and error rates for 1 hour
7. 7Promote to full production if metrics pass
8. 8Validation: p95 latency < 100ms, error rate < 0.1%

What it can do on your machine

Read from SKILL.md and the folder at commit 19392f7. 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

  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

Senior ML Engineer loads about 2.4k tokens when it runs, and up to ~9.1k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 819 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~141

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~9.1k

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

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 alirezarezvani/claude-skills at commit 19392f7, republished under its MIT licence (© alirezarezvani). 819 words, ~2,441 tokens.

name

senior-ml-engineer

description

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization. Use when the user asks about deploying ML models to production, setting up MLOps infrastructure (MLflow, Kubeflow, Kubernetes, Docker), monitoring model performance or drift, building RAG pipelines, or integrating LLM APIs with retry logic and cost controls. Focused on production and operational concerns rather than model research or initial training.

triggers

MLOps pipeline, model deployment, feature store, model monitoring, drift detection, RAG system, LLM integration, model serving, A/B testing ML, automated…

FROM python:3.11-slim

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY model/ /app/model/
COPY src/ /app/src/

HEALTHCHECK CMD curl -f http://localhost:8080/health || exit 1

EXPOSE 8080
CMD ["uvicorn", "src.server:app", "--host", "0.0.0.0", "--port", "8080"]

from feast import Entity, Feature, FeatureView, FileSource

user = Entity(name="user_id", value_type=ValueType.INT64)

user_features = FeatureView(
    name="user_features",
    entities=["user_id"],
    ttl=timedelta(days=1),
    features=[
        Feature(name="purchase_count_30d", dtype=ValueType.INT64),
        Feature(name="avg_order_value", dtype=ValueType.FLOAT),
    ],
    online=True,
    source=FileSource(path="data/user_features.parquet"),
)

from abc import ABC, abstractmethod
from tenacity import retry, stop_after_attempt, wait_exponential

class LLMProvider(ABC):
    @abstractmethod
    def complete(self, prompt: str, **kwargs) -> str:
        pass

@retry(stop=stop_after_attempt(3), wait=wait_exponential(min=1, max=10))
def call_llm_with_retry(provider: LLMProvider, prompt: str) -> str:
    return provider.complete(prompt)

from scipy.stats import ks_2samp

def detect_drift(reference, current, threshold=0.05):
    statistic, p_value = ks_2samp(reference, current)
    return {
        "drift_detected": p_value < threshold,
        "ks_statistic": statistic,
        "p_value": p_value
    }

python scripts/model_deployment_pipeline.py --model model.pkl --target staging

python scripts/rag_system_builder.py --config rag_config.yaml --analyze

python scripts/ml_monitoring_suite.py --config monitoring.yaml --deploy

© alirezarezvani, MIT. 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 engineering-team/skills/senior-ml-engineer of alirezarezvani/claude-skills.

• SKILL.md
• references/llm_integration_guide.md
• references/mlops_production_patterns.md
• references/rag_system_architecture.md
• scripts/ml_monitoring_suite.py
• scripts/model_deployment_pipeline.py
• scripts/rag_system_builder.py

Open the folder on GitHubat commit 19392f7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in alirezarezvani/claude-skills, which our catalogue first saw on October 7, 2026.

• LeoYeAI/openclaw-master-skillsskills/senior-ml-engineer