Search
AI & LLM Engineering · awslabs/agent-plugins
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). | awslabs/ | 916 | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 2 | Generates code that transforms datasets between ML schemas for model training or evaluation. | awslabs/ | 916 | 1 repo | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. | awslabs/ | 916 | — | ~604 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Diagnose performance issues on Amazon SageMaker HyperPod clusters — uneven NCCL bandwidth across nodes and poor filesystem throughput. | awslabs/ | 916 | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 5 | Diagnostic-only skill for Slurm scheduler and node-daemon issues on Amazon SageMaker HyperPod Slurm clusters. | awslabs/ | 916 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 6 | Remote command execution and file transfer on SageMaker HyperPod cluster nodes via AWS Systems Manager (SSM). | awslabs/ | 916 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 7 | Selects a base model for the user's use case by querying SageMaker Hub. | awslabs/ | 916 | — | ~844 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia)… | awslabs/ | 916 | — | ~910 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Generates code that fine-tunes a base model using SageMaker serverless training jobs. | awslabs/ | 916 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | Generates python code that evaluates SageMaker models. An agent skill from awslabs/agent-plugins. | awslabs/ | 916 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 11 | Diagnose NCCL failures and adjacent training-pod failures on HyperPod GPU clusters (EKS or Slurm) — training hangs, AllReduce / collective-op timeouts, EFA or libfabric errors, rendezvous failures… | awslabs/ | 916 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 12 | Discovers user intent and generates a structured, step-by-step plan for model customization workflows. | awslabs/ | 916 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 13 | Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. | awslabs/ | 916 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 14 | Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. | awslabs/ | 916 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 15 | Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. | awslabs/ | 916 | — | ~1k | Automated safety check: Pass | Apache-2.0 | yesterday |
