GitHub organization
Agent skills by awslabs
- skills
- 51
- official
- 51
- repositories
- 4
Repositories by awslabs
- agent-pluginsOfficialAgent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.912 stars · 33 skills
- cli-agent-orchestratorOfficialMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions1.4k stars · 14 skills
- loomOfficialLoom for AWS is an enterprise-grade platform for building, deploying, integrating, and operating AI agents on Amazon Bedrock AgentCore.191 stars · 3 skills
- nx-plugin-for-awsOfficialThe @aws/nx-plugin is a collection of code generators that automate the creation and configuration of cloud-native applications using AWS, TypeScript, Python and React within the Nx development ecosystem.151 stars · 1 skill
Skills by awslabs, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | 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/ | 912 | 2 repos | ~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/ | 912 | 2 repos | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman). | awslabs/ | 1.4k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Author live dashboard UI from an agent via the emitui MCP tool. | awslabs/ | 1.4k | — | ~2k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | 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/ | 912 | 1 repo | ~604 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 6 | Load the official MCP Apps builder skills (create-mcp-app, migrate-oai-app, add-app-to-server, convert-web-app) from github.com/modelcontextprotocol/ext-apps. | awslabs/ | 1.4k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | Create a new CAO (CLI Agent Orchestrator) plugin. An agent skill from awslabs/cli-agent-orchestrator. | awslabs/ | 1.4k | — | ~3.1k | Automated safety check: Notes | Apache-2.0 | today |
| 8 | Evaluate, configure, and migrate workloads to AWS Lambda Managed Instances (LMI). | awslabs/ | 912 | — | ~4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Create a new CLI agent provider for CAO (CLI Agent Orchestrator). | awslabs/ | 1.4k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Finalize dev work on an issue branch — update docs, push, and open a PR. | awslabs/ | 191 | — | ~715 | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Generate comprehensive issue reports from HyperPod clusters (EKS and Slurm) by collecting diagnostic logs and configurations for troubleshooting and AWS Support cases. | awslabs/ | 912 | — | ~890 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 12 | Diagnose performance issues on Amazon SageMaker HyperPod clusters — uneven NCCL bandwidth across nodes and poor filesystem throughput. | awslabs/ | 912 | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 13 | Find and select the best installed CAO agent profile for a task before delegating with assign or handoff. | awslabs/ | 1.4k | — | ~552 | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Scaffold and build cloud-native applications on AWS using @aws/nx-plugin generators. | awslabs/ | 151 | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 15 | Diagnostic-only skill for Slurm scheduler and node-daemon issues on Amazon SageMaker HyperPod Slurm clusters. | awslabs/ | 912 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 16 | Implement a GitHub issue end-to-end — branch, code, test, docs, and commit. | awslabs/ | 191 | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Contribute changes to the CAO (CLI Agent Orchestrator) codebase — the local dev loop, the CI gate map, and the pre-PR checklist. | awslabs/ | 1.4k | — | ~4k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | Remote command execution and file transfer on SageMaker HyperPod cluster nodes via AWS Systems Manager (SSM). | awslabs/ | 912 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 19 | Increment the release version, draft release notes, and prepare a GitHub release. | awslabs/ | 191 | — | ~601 | Automated safety check: Pass | Apache-2.0 | today |
| 20 | 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/ | 912 | 1 repo | ~910 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 21 | Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. | awslabs/ | 1.4k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | today |
| 22 | Selects a base model for the user's use case by querying SageMaker Hub. | awslabs/ | 912 | — | ~844 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 23 | Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. | awslabs/ | 1.4k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Build, run, debug, and operate applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments that run inside a container with up to 8-hour lifetimes. | awslabs/ | 912 | 1 repo | ~4.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 25 | Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. | awslabs/ | 1.4k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 26 | Generates code that fine-tunes a base model using SageMaker serverless training jobs. | awslabs/ | 912 | 1 repo | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 27 | Generates python code that evaluates SageMaker models. An agent skill from awslabs/agent-plugins. | awslabs/ | 912 | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 28 | Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. | awslabs/ | 1.4k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 29 | Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. | awslabs/ | 912 | 1 repo | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 30 | Supervisor-side orchestration patterns for assign, handoff, and idle inbox delivery in CAO | awslabs/ | 1.4k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 31 | Validates the user's environment for SageMaker AI operations — checks SDK version, AWS region, and execution role. | awslabs/ | 912 | 1 repo | ~248 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 32 | Integrates Amazon Location Service APIs for AWS applications. | awslabs/ | 912 | — | ~4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 33 | Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). | awslabs/ | 912 | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 34 | Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries. | awslabs/ | 912 | — | ~3.8k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 35 | Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. | awslabs/ | 912 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 36 | This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs… | awslabs/ | 912 | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 37 | Diagnose and remediate cluster-wide HyperPod (EKS or Slurm) problems — creation / deployment failures (CloudFormation, EFA health check, lifecycle scripts, capacity), EKS access, node replacement… | awslabs/ | 912 | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 38 | 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/ | 912 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 39 | Discovers user intent and generates a structured, step-by-step plan for model customization workflows. | awslabs/ | 912 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 40 | Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. | awslabs/ | 912 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 41 | Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket). | awslabs/ | 912 | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 42 | Design, build, deploy, test, and debug serverless applications with AWS Lambda. | awslabs/ | 912 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 43 | AWS SAM and AWS CDK deployment for serverless applications. An agent skill from awslabs/agent-plugins. | awslabs/ | 912 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 44 | Build workflows with AWS Step Functions state machines using the JSONata query language. | awslabs/ | 912 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 45 | Deploy applications to AWS. An agent skill from awslabs/agent-plugins. | awslabs/ | 912 | — | ~665 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 46 | Deploy to AWS Elastic Beanstalk, in either Beanstalk Standard mode (EC2) or Beanstalk Cluster mode (managed EKS). | awslabs/ | 912 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 47 | Manages project directory setup and artifact organization. An agent skill from awslabs/agent-plugins. | awslabs/ | 912 | — | ~426 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 48 | Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user. | awslabs/ | 1.4k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill by awslabs?
Dataset Evaluation (official) from awslabs/agent-plugins ranks first of the 51 skills by awslabs listed here, with the highest score: its repository has 912 GitHub stars, 2 other GitHub owners carry a copy, its SKILL.md loads about 1.3k tokens and it passes the automated safety check with no findings. Next come Dataset Transformation and Cao MCP Apps.
Are awslabs's skills official?
51 of the 51 skills by awslabs are official, published by the vendor's own GitHub organization: Dataset Evaluation, Dataset Transformation, Cao MCP Apps, Agui Author, Finetuning Technique and 46 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.