ai-mlops
Production MLOps and ML/LLM/agent security skill for deploying and operating ML systems in production (registry + CI/CD, serving, monitoring/drift, evaluation loops, incident response/runbooks, and governance), including GenAI security (prompt injection, jailbreaks, RAG security, privacy, and supply chain).
npx skills add majiayu000/claude-skill-registry --skill ai-mlops --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Production ML lifecycle with modern security practices, covering data ingestion, model deployment, and operations, plus security and governance aspects (prompt injection, jailbreak defense, RAG security, output filtering, privacy, supply chain). The skill emphasizes versioning, eval-driven deployments, and incident playbooks.
How it works
It outlines concrete tasks and patterns across the ML lifecycle:
- Data ingestion: load data from APIs and databases to warehouses; uses dlt pattern references for ingestion templates.
- Model deployment: supports batch, real-time, hybrid deployments; includes monitoring for drift and automated retraining pipelines.
- Operations: real-time monitoring, drift detection, automated retraining, incident response with rollback and postmortems; governance on privacy and supply chain security.
- Security and governance: guidance on threat modeling, prompt injection mitigation, jailbreak defense, RAG security, output filtering, privacy protection, SBOM and artifact signing, and safety evaluation.
- References to templates and patterns: deployment lifecycle, data ingestion patterns, model registry, monitoring templates, incident runbooks, and agent observability.
When to use it
Use this skill for deployment, operations, monitoring, incident handling, or governance of ML/LLM/agent systems, including scenarios like setting up prod pipelines, designing batch+online scoring, adding drift monitoring, writing incident runbooks, packaging LLM/RAG pipelines as APIs, planning retraining and promotion workflows, and data ingestion from APIs/databases.
What it can touch
Not applicable in this excerpt beyond the stated tools; the skill mentions tools like dlt, Airflow/Dagster/Prefect, FastAPI/Flask, vLLM/TorchServe, MLflow, Prometheus/Grafana, and AgentOps/Langfuse/LangSmith in the referenced task table for deployment patterns and monitoring.
Caveats
Licensed under MIT. Declares security-focused governance and incident readiness patterns, including threat models and prompt safety; no guarantees of specific outcomes are provided beyond the described patterns and templates.
# MLOps & ML Security - Complete Reference (Jan 2026) Production ML lifecycle with **modern security practices**. This skill covers: - **Production**: Data ingestion, deployment, drift detection, monitoring, incident response - **Security**: Prompt injection, jailbreak defense, RAG security, output filtering - **Governance**: Privacy protection, supply chain security, safety evaluation 1. **Data ingestion** (dlt): Load data from APIs, databases to warehouses 2. **Model deployment**: Batch jobs, real-time APIs, hybrid systems, event-driven automation 3. **Operations**: Real-time monitoring, drift detection, automated retraining, incident response **Modern Best Practices (Jan 2026)**: - Version everything that can change: model artifacts, data snapshots, feature definitions, prompts/configs, and agent graphs; require reproducibility, rollbacks, and audit logs (NIST SSDF: https://csrc.nist.gov/pubs/sp/800/218/final). - Gate changes with evals (offline + online) and safe rollout (shadow/canary/blue-green); treat regressions in quality, safety, latency, and cost as release blockers. - Align controls and documentation to risk posture (EU AI Act: https://eur-lex.europa.eu/eli/reg/2024/168
- Quick Reference
- Use This Skill When
- Decision Tree: Choosing Deployment Strategy
- Core Concepts (Vendor-Agnostic)
- Do / Avoid
- Core Patterns Overview
- Data & Infrastructure Patterns
- Serving Patterns
- Operations Patterns
- Resources (Detailed Guides)
- Templates
- Data Ingestion (dlt)
- Deployment & Packaging
- Monitoring & Operations
What does the ai-mlops skill do?
Production MLOps and ML/LLM/agent security skill for deploying and operating ML systems in production (registry + CI/CD, serving, monitoring/drift, evaluation loops, incident response/runbooks, and governance), including GenAI security (prompt injection, jailbreaks, RAG security, privacy, and supply chain).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ai-mlops --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.