Agent skills · Cloud & DevOps

50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

1. emerging-techniques-knowledge-distillation ★ 30,576
   Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained
2. emerging-techniques-speculative-decoding ★ 30,576
   Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference
3. evaluation-nemo-evaluator ★ 30,576
   Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needin
4. infrastructure-lambda-labs ★ 30,576
   Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access,
5. infrastructure-modal ★ 30,576
   Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying
6. infrastructure-skypilot ★ 30,576
   Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple
7. loki-mode ★ 30,576
   Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA,
8. ml-engineer ★ 30,576
   Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testi
9. mlops-mlflow ★ 30,576
   Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-
10. mlops-tensorboard ★ 30,576
    Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBo
11. observability-langsmith ★ 30,576
    LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against da
12. observability-phoenix ★ 30,576
    Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces,
13. optimization-gguf ★ 30,576
    GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or wh
14. cto-advisor ★ 30,576
    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scal
15. resume-bullet-writer ★ 30,576
    Transform weak resume bullets into achievement-focused statements with metrics and impact. Use when the user wants to rewrite bullets, stren
16. resume-quantifier ★ 30,576
    Find opportunities to add metrics and estimate numbers when exact data is unavailable. Use when the user wants to quantify achievements, add
17. tech-resume-optimizer ★ 30,576
    Optimize resumes for software engineering, product management, and technical roles. Use when the user mentions software engineer, developer,
18. draw-io ★ 30,576
    draw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG conversion, layout adjustment, and AWS icon usage.
19. tailwind-patterns ★ 30,576
    Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
20. using-neon ★ 30,576
    Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connect
21. android-cicd ★ 30,576
    "Automated Android CI/CD pipeline to Google Play — supports TWA, React Native, Flutter, and native Android. Run npx android-cicd to set up k
22. aws-serverless ★ 30,576
    "Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS eve
23. azure-functions ★ 30,576
    "Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization,
24. backend-dev-guidelines ★ 30,576
    Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repos
25. bash-pro ★ 30,576
    'Master of defensive Bash scripting for production automation, CI/CD
26. cloud-architect ★ 30,576
    Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost o
27. cloud-devops ★ 30,576
    "Cloud infrastructure and DevOps workflow covering AWS, Azure, GCP, Kubernetes, Terraform, CI/CD, monitoring, and cloud-native development."
28. cloud-run-basics ★ 30,576
    Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run eve
29. cloudflare-deploy ★ 30,576
    Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy,
30. convex ★ 30,576
    "Convex reactive backend expert: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deploymen
31. deployment-procedures ★ 30,576
    Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, no
32. devops-iac-engineer ★ 30,576
    Implements infrastructure as code using Terraform, Kubernetes, and cloud platforms. Designs scalable architectures, CI/CD pipelines, and obs
33. django-pro ★ 30,576
    Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and
34. docker-expert ★ 30,576
    Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestrati
35. fastmcp-server ★ 30,576
    Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment. Use when
36. flutter-expert ★ 30,576
    Master Flutter development with Dart 3, advanced widgets, and multi-platform deployment.
37. gcp-cloud-run ★ 30,576
    "Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functi
38. gh-fix-ci ★ 30,576
    Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after us
39. github-actions-creator ★ 30,576
    "Use when the user wants to create, generate, or set up a GitHub Actions workflow. Handles CI/CD pipelines, testing, deployment, linting, se
40. gke-basics ★ 30,576
    Plans, creates, and configures production-ready Google Kubernetes Engine (GKE) clusters using the golden path Autopilot configuration. Cover
41. google-cloud-networking-observability ★ 30,576
    Investigates Google Cloud networking issues by analyzing logs, metrics, and diagnostics. Use when investigating VPC Flow Logs, NAT, firewall
42. google-cloud-onboarding ★ 30,576
    Guides developers through their first steps on Google Cloud, covering account creation, billing setup, project management, CLI installation,
43. google-cloud-waf-cost-optimization ★ 30,576
    Generates cost optimization guidance for Google Cloud workloads based on the Google Cloud Well-Architected Framework (WAF). Use to evaluate
44. google-cloud-waf-reliability ★ 30,576
    Generates reliability-focused guidance for Google Cloud workloads based on the Google Cloud Well-Architected Framework. Use to evaluate a wo
45. grafana-dashboards ★ 30,576
    "Create and manage production-ready Grafana dashboards for comprehensive system observability."
46. helm-chart-scaffolding ★ 30,576
    "Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications."
47. incident-responder ★ 30,576
    Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management.
48. it-operations ★ 30,576
    Manages IT infrastructure, monitoring, incident response, and service reliability. Provides frameworks for ITIL service management, observab
49. kubernetes-architect ★ 30,576
    Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container o
50. manifest ★ 30,576
    Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys or endpoints, t