Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
194 skills
NVIDIAOfficial
Configure observability, telemetry, and event export for NeMo Relay applications.
NVIDIAOfficial
A diagnostic tool for capturing system health snapshots on NVIDIA Jetson devices.
NVIDIAOfficial
Assists with configuring, building, and running the DOCA Telemetry Traceback application for local telemetry monitoring on BlueField DPUs and ConnectX NICs.
Samuel Berthe· Community
A comprehensive framework for implementing production-grade observability in Go services.
AWSOfficial
A structured workflow for executing and interpreting AWS Resilience Hub v2 failure mode assessments.
AWSOfficial
Measure and improve AgentCore agent performance through evaluation, observability, and cost management.
AWSOfficial
A routing and setup guide for CloudWatch Application Observability (Omni) and classic CloudWatch Application Signals.
AWSOfficial
Operate and troubleshoot live AWS workloads with autonomous incident investigation and release-readiness reviews.
AWSOfficial
A structured methodology for investigating AWS account incidents using evidence-based analysis of logs, deployment records, and data stores.
AWSOfficial
Plan, execute, and analyze chaos engineering experiments using AWS Fault Injection Service.
AWSOfficial
Diagnose and root-cause Amazon MWAA workflow failures for both Provisioned and Serverless environments.
AWSOfficial
Provides factual configuration reviews and investigation summaries for AWS security services using read-only APIs.
AWSOfficial
A systematic procedure for diagnosing and resolving AWS Lambda function timeout failures.
AWSOfficial
Expert guidance for installing, configuring, and troubleshooting Amazon CloudWatch Network Flow Monitor agents on EC2 instances.
Automated root-cause investigation for AWS operational incidents and service failures.
AWSOfficial
Strategic framework for designing organizational resilience programs, including tiered policy models and operational cadences.
AWSOfficial
Diagnose and resolve issues with your AgentCore agent, environment, or CLI.
AWSOfficial
Automated AWS Security Agent code scanning workflow for workspace vulnerability detection and remediation.
AWSOfficial
A comprehensive guide to the AWS resilience lifecycle using Resilience Hub v2, Fault Injection Service, and Application Recovery Controller.
AWSOfficial
Expert guidance for managing AWS observability using CloudWatch and CloudWatch Omni.
AWSOfficial
A structured procedure for diagnosing application failures by analyzing CloudWatch logs.
CloudflareOfficial
Profile and debug CPU and memory performance in Cloudflare Workers and Durable Objects.
MicrosoftOfficial
A systematic diagnostic framework for troubleshooting Azure production services using logs, metrics, and resource health.
MicrosoftOfficial
Python SDK for querying Azure Monitor metrics and Log Analytics workspaces.
