Machine learning

Load before writing or revising human-facing text.

What fiction readers want (reader reward channels) and the specific ways LLM training damages them.

Design and build use cases, POCs and production systems with TypeSafe's Jev decision model (System One): choose a design mode and a use-case archetype, build…

Reviews code for security vulnerabilities and guides secure implementation using OWASP Top 10:2025, ASVS 5.0, the OWASP Top 10 for LLM Applications (2026)…

Creative-writing addendum to /llm-writing.

NVIDIA DeepStream SDK development with Python pyservicemaker API.

Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end…

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI…

Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation…

Use when a pr-council-review (PR or branch mode) result needs independent corroboration from a different model family before trusting a GREEN verdict —…

npcpy LLM prompting and JSON formatting patterns.

Used for header-only preflight of one DICOM series folder before conversion or inference.

Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence…

Amazon Redshift expert.

Getting a first Qdrant Managed Cloud cluster running and connected safely: Free, Standard, and Premium tiers, choices that can't be changed later, creating…

Guides embedding model migration in Qdrant without downtime.

Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications.

Covers everything about search in MongoDB: Atlas Search (full-text), Vector Search (semantic), and Hybrid Search.

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

Use this skill when diagnosing IAM and access failures for Bedrock and SageMaker.

Use this skill for GPU training or inference clusters on SageMaker HyperPod (Slurm or EKS), ParallelCluster, or self-managed EC2/EKS GPU instances.

Cost guardrail for AWS DevOps Agent that covers ALL AWS services and native agent tools.

Amazon SageMaker AI Operational Review.

Manage Venice API keys.