amazon-bedrock — Builds generative AI applications on Amazon Bedrock.
amazon-braket — Runs quantum computing workflows on AWS through Amazon Braket — discovering devices (QPUs and simulators) and their availability.
asr-transcribe-to-text — Transcribe audio/video to speaker-labeled text — who-said-what by default, plain-text opt-out; MLX-local on Apple Silicon or remote; local files, media URLs.
aws-ai-ml — Selects, deploys, and customizes AI models on Amazon SageMaker.
aws-cleanrooms — Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions.
benchmark-models — Cross-model benchmark for gstack skills. (gstack)
fine-tuning-expert — Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks.
llm-eval-harness — Test/evaluate any LLM behind an OpenAI- or Anthropic-compatible endpoint: availability (max_tokens-aware).
ml-pipeline — Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases.
querying-aws-sagemaker-catalog — Runs SQL analytics on SageMaker Catalog asset metadata tables exported as Apache Iceberg in S3 Tables.
rag-architect — Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines.
stepfun-asr — Transcribe audio with StepFun's stepaudio-3-asr-max — an SSE endpoint (NOT /v1/audio/transcriptions).
stepfun-tts — Generate Chinese / Japanese speech with StepFun's Contextual TTS — default `stepaudio-2.5-tts` (blind-judged better on neutral/emotive preset voices).
storing-and-querying-vectors — Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors).