Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
majiayu000/claude-skill-registry 163
-
gitops-principles-skill
Comprehensive GitOps methodology and principles skill for cloud-native operations. Use when (1) Designing GitOps architecture for Kubernetes deployments, (2) Implementing declarative infrastructure with Git as single source of truth, (3) Setting up continuous deployment pipelines with ArgoCD/Flux/Kargo, (4) Establishing branching strategies and repository structures, (5) Troubleshooting drift, sync failures, or reconciliation issues, (6) Evaluating GitOps tooling decisions, (7) Teaching or explaining GitOps concepts and best practices, (8) Deploying ArgoCD on Azure Arc-enabled Kubernetes or AKS with workload identity. Covers the 4 pillars of GitOps (OpenGitOps), patterns, anti-patterns, tooling ecosystem, Azure Arc integration, and operational guidance.
majiayu000/claude-skill-registry 163
-
literature-synthesis
Synthesize multiple sources into coherent narratives with explicit evidence tracking and confidence ceilings.
majiayu000/claude-skill-registry 163
-
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.
majiayu000/claude-skill-registry 163
-
terminal-execution
Best practices for reliable terminal command execution and output capture. Use this skill when running shell commands, especially in environments like WSL where output might be truncated or lost, to ensure results are properly captured and inspected.
majiayu000/claude-skill-registry 163
-
kubernetes-helm-deployment
Kubernetes deployment patterns with Helm charts. Covers deployments, services, ConfigMaps, Secrets, Dapr sidecar injection, health probes, and resource management.
majiayu000/claude-skill-registry 163
-
fly-ssh
Use when asked to run "fly ssh console", SSH into Fly.io machines, inspect files on production machines, check processes on Fly.io, or examine deployed machine state. Covers critical pitfalls like no shell support and Debian vs macOS command differences.
majiayu000/claude-skill-registry 163
-
portfolio-planning
Strategic portfolio planning skill for multi-project coordination, capacity assessment,
and portfolio optimization. Provides framework for portfolio-level decision making.
majiayu000/claude-skill-registry 163
-
elixir-discipline
MANDATORY pre-check before ANY response - ensures you use applicable skills and follow best practices. Use this skill FIRST before responding to any Elixir/Phoenix request.
majiayu000/claude-skill-registry 163
-
using-git-spice
Use when working with stacked branches, managing dependent PRs/CRs, or uncertain about git-spice commands (stack vs upstack vs downstack) - provides command reference, workflow patterns, and common pitfalls for the git-spice CLI tool
majiayu000/claude-skill-registry 163
-
select
Explicit-only: pick the next `bd ready` bead via risk-first heuristics; verify dependency/readiness, add missing deps, then mark in progress and comment.
majiayu000/claude-skill-registry 163
-
session-compression
AI session compression techniques for managing multi-turn conversations efficiently through summarization, embedding-based retrieval, and intelligent context management.
majiayu000/claude-skill-registry 163
-
infra-engineer
Comprehensive infrastructure engineering covering DevOps, cloud platforms, FinOps, and DevSecOps. Platforms: AWS (EC2, Lambda, S3, ECS, EKS, RDS, CloudFormation), Azure basics, Cloudflare (Workers, R2, D1, Pages), GCP (GKE, Cloud Run, Cloud Storage), Docker, Kubernetes. Capabilities: CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins), GitOps, infrastructure as code (Terraform, CloudFormation), container orchestration, cost optimization, security scanning, vulnerability management, secrets management, compliance (SOC2, HIPAA). Actions: deploy, configure, manage, scale, monitor, secure, optimize cloud infrastructure. Keywords: AWS, EC2, Lambda, S3, ECS, EKS, RDS, CloudFormation, Azure, Kubernetes, k8s, Docker, Terraform, CI/CD, GitHub Actions, GitLab CI, Jenkins, ArgoCD, Flux, cost optimization, FinOps, reserved instances, spot instances, security scanning, SAST, DAST, vulnerability management, secrets management, Vault, compliance, monitoring, observability. Use when: deploying to AWS/Azure/GCP/Cloudflare, setting up CI/CD pipelines, implementing GitOps workflows, managing Kubernetes clusters, optimizing cloud costs, implementing security best practices, managing infrastructure as code, container orchestration, compliance requirements, cost analysis and optimization.
majiayu000/claude-skill-registry 163
-
pycse
Use when performing regression analysis with confidence intervals, solving ODEs, fitting models to experimental data, or caching expensive scientific computations - provides convenient wrappers around scipy that automatically calculate confidence intervals and prediction bounds for linear, nonlinear, and polynomial regression
majiayu000/claude-skill-registry 163
-
klingai-pricing-basics
Manage understand Kling AI pricing, credits, and cost optimization. Use when budgeting or optimizing
costs for video generation. Trigger with phrases like 'kling ai pricing', 'klingai credits',
'kling ai cost', 'klingai budget'.
majiayu000/claude-skill-registry 163
-
multi-model-research
Orchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive research using LLM Council pattern with peer review and synthesis
majiayu000/claude-skill-registry 163
-
daily-standups
Master daily standup facilitation with focus, time management, and effective patterns for team synchronization and impediment identification.
majiayu000/claude-skill-registry 163
-
memorystore-config
Memorystore Config - Auto-activating skill for GCP Skills.
Triggers on: memorystore config, memorystore config
Part of the GCP Skills skill category.
majiayu000/claude-skill-registry 163
-
effect-concurrency-fibers
Concurrency with Effect.all, forEach concurrency, Fiber lifecycle, race and timeouts. Use for parallelizing tasks safely.
majiayu000/claude-skill-registry 163
-
ci-cd-practices
CI/CD and operations practices including GitHub Actions, Kubernetes, and operational tooling. Use when working with deployment and infrastructure.
majiayu000/claude-skill-registry 163
-
azure-artifacts-manager
Manage Azure Artifacts including package feeds, versions, and dependencies. Use when publishing or managing artifact packages.
majiayu000/claude-skill-registry 163
-
adr-review
Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.
majiayu000/claude-skill-registry 163
-
legal-counsel
Senior Legal Counsel with 20+ years experience in corporate law. Use for legal advice, contract drafting, compliance checks, data protection (GDPR/CCPA), employment law, or risk assessment. Auto-triggers penalty warnings and statute citations. Adapts to user's jurisdiction.
majiayu000/claude-skill-registry 163
-
dotnet-cicd-patterns
Implement CI/CD for .NET applications with GitHub Actions, Azure DevOps, Docker, Kubernetes deployments, automated testing, and release pipelines. Use when setting up continuous integration and deployment for .NET projects.
majiayu000/claude-skill-registry 163