andisab

Write commit messages following the Conventional Commits format. Use when composing, reviewing, or fixing git commit messages.

Amazon Web Services CLI operations and infrastructure patterns for AWS resource management. Activate when user mentions: aws, AWS, Amazon Web Services, EC2, EKS, ECS, S3, RDS, Lambda, CloudFormation, CloudWatch, IAM roles, IAM policies, aws cli commands, AWS deployment, AWS infrastructure, ECR, ALB, NLB, VPC, Route53, DynamoDB, SQS, SNS, EventBridge, Systems Manager, Secrets Manager, CloudTrail, AWS Organizations. Use for: AWS resource provisioning, aws cli commands, AWS service configuration, infrastructure-as-code for AWS, AWS best practices, OIDC authentication, IAM roles for service accounts (IRSA), AWS security patterns, multi-region deployments, high availability configurations, cost optimization, disaster recovery, Spot instances. Do NOT use for: GCP-specific resources, Azure-specific resources, Kubernetes manifests (use kubernetes-native skill), generic shell scripting unrelated to AWS, Terraform/Pulumi DSL syntax (use terraform-modules or pulumi-cdk skills for IaC DSLs).

AWS EKS cluster provisioning, configuration best practices, security hardening, cost optimization, IRSA (IAM Roles for Service Accounts), VPC CNI networking, node group management, cluster addons, and Kubernetes 1.31+ features including Gateway API v1 and native sidecar containers. Activate when user mentions: AWS EKS, Elastic Kubernetes Service, EKS cluster, eksctl, EKS node groups, managed node groups, self-managed nodes, Fargate profiles, EKS addons, VPC CNI, CoreDNS, kube-proxy, EKS OIDC provider, IRSA, IAM roles for service accounts, EKS security groups, pod security groups, EKS encryption, KMS encryption, EKS logging, control plane logs, EKS access entries, EKS cluster autoscaler, Karpenter, Gateway API on EKS, AWS Load Balancer Controller, EBS CSI driver, EFS CSI driver. Use for: EKS cluster architecture design, Terraform/Pulumi EKS provisioning, security configuration, IRSA setup, VPC networking for EKS, node group optimization, spot instance integration, cluster addon management, multi-AZ high availa

Dockerfile best practices, multi-stage builds, security scanning patterns, CI/CD validation pipelines, and container optimization strategies. Activate when user mentions: Dockerfile, container image, multi-stage build, container security, image optimization, docker build, container layers, base image, distroless, alpine, scratch image, container scanning, vulnerability scanning, dockerfile lint, hadolint, trivy, security pipeline, SBOM generation, container validation, CI/CD security gates, image attestation. Use for: Dockerfile generation patterns, security hardening, build optimization, layer caching strategies, CI/CD security integration, vulnerability management, SBOM generation, policy-as-code validation. Do NOT use for: Runtime orchestration (use kubernetes-native skill), CI/CD pipelines (use github-actions-iac skill), infrastructure provisioning (use terraform-patterns skill).

Crossplane composition patterns for cloud-native infrastructure provisioning. Provides XRD (CompositeResourceDefinition), Composition, and Claim patterns for AWS, Azure, GCP resources with security best practices, validation pipelines, and hallucination detection for AI-generated compositions. Activate when user mentions: crossplane, XRD, composite resource, composition, claim, provider config, managed resources, crossplane composition, infrastructure composition, declarative infrastructure, control plane. Use for: Generating Crossplane compositions, XRDs, Claims, ProviderConfigs, and managed resource patterns following cloud-native best practices with multi-phase validation and cost optimization. Do NOT use for: Direct Terraform/Pulumi code, CloudFormation templates, Kubernetes operators (unless Crossplane-specific), raw cloud provider APIs.

GitHub Actions CI/CD pipeline patterns for IaC deployments. Provides secure workflow configurations with OIDC authentication, multi-environment deployment strategies, reusable workflow architectures, and infrastructure validation with modern security scanning tools. Activate when user mentions: GitHub Actions, CI/CD, workflow, pipeline, deployment, OIDC, GitHub workflow, actions workflow, CI pipeline, continuous deployment, automated deployment, workflow file, .github/workflows, reusable workflows Use for: Generating GitHub Actions workflows for Terraform, Kubernetes, Helm deployments with security best practices (OIDC, Trivy scanning, validation gates, reusable patterns). Do NOT use for: GitLab CI, Jenkins, CircleCI, or other CI/CD platforms. For those, recommend platform-specific tooling.

GitLab CI/CD pipeline patterns for Infrastructure-as-Code deployments. Provides secure .gitlab-ci.yml configurations with OIDC authentication, DAG pipeline optimization, GitLab Agent for Kubernetes GitOps integration, reusable job templates, multi-environment deployment strategies, and security scanning with modern validation tools. Activate when user mentions: GitLab CI, .gitlab-ci.yml, GitLab pipelines, DAG pipelines, GitLab Agent, GitLab Runner, GitLab GitOps, CI/CD pipelines, stages, jobs, rules, needs, artifacts, GitLab deployment, GitLab security scanning, parent-child pipelines, pipeline efficiency, Flux integration with GitLab Agent. Use for: Generating GitLab CI/CD pipelines for Terraform, Kubernetes, Helm, Docker builds with security best practices (OIDC, workload identity, DAG optimization, security scanning, validation gates, artifact management, and GitLab Agent for GitOps). Do NOT use for: GitHub Actions, Jenkins, CircleCI, or other CI/CD platforms. For those, recommend platform-specific tooling

GitOps patterns and best practices for Argo CD continuous delivery. Provides Argo CD Application and ApplicationSet manifests, multi-environment deployment strategies, sync wave orchestration, security hardening patterns, and cost optimization configurations with CI/CD integration. Activate when user mentions: Argo CD, ArgoCD, GitOps, Application manifest, ApplicationSet, sync waves, progressive rollouts, image updater, App of Apps, declarative deployment, automated sync, Argo Rollouts integration, GitHub Actions GitOps, GitLab Agent, Flux integration. Use for: Generating Argo CD resources, multi-tenant patterns, progressive delivery, dependency management via sync waves, health checks, automated image updates, OIDC authentication, security scanning integration, cost-optimized workload deployment, CI/CD pipeline integration with GitHub Actions and GitLab. Do NOT use for: Standalone Kubernetes manifests (use kubernetes-native skill), Flux CD patterns, Jenkins pipelines, or non-GitOps deployment strategies.

Runs the research-team plugin's multi-agent research pipeline end-to-end from the main thread: decomposes a topic into 2-5 subtopics, spawns parallel research-team:research-specialist subagents for each, verifies their output on disk, then spawns a research-team:research-report-writer subagent to synthesize the final report. Activate ONLY when the user explicitly invokes this plugin — for example: "use research-team", "run the research-team coordinator", "research X with the research-team plugin", "research-team: research X", or when the user requests research that specifically needs Joplin-formatted output via this plugin's report-writer. Do NOT activate for generic research requests. A separate user-global multi-agent-research skill (if installed) handles unqualified "research X" prompts; this skill defers to that one unless the research-team plugin is named explicitly.

Shared multi-model CLI dispatch infrastructure for the adv plugin. Houses dispatch.sh, preflight.sh, run-phase.sh, scope.sh, and reviewer prompt templates used by the adv-review agent and adv-* commands.

Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle, or grouping multiple related tools into a service. Covers Python (FastMCP) and TypeScript (@modelcontextprotocol/sdk) patterns, packaging, and testing. Activate for: - "Create an MCP server" - "Build a server with multiple tools" - "Package tools for uvx/npx" - "Set up stdio transport" - "Register tools on a server" Do NOT use for: - Creating a single standalone tool function (use mcp-tool-dev) - General REST API development - Claude Code agents, skills, or commands

Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or implementing tool input validation. Covers FastMCP patterns, Anthropic tool description best practices, and testing strategies. Activate for: - "Create an MCP tool" - "Add a tool to my MCP server" - "Write a tool handler" - "Design a tool schema" - "Implement tool input validation" Do NOT use for: - Creating full MCP servers with multiple tools (use mcp-server-dev) - General API development without MCP - Claude Code slash commands or hooks

Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a sub-agent", "make a specialist", or mentions agent development. Ensures agents follow Anthropic best practices with focused responsibilities, discovery-optimized descriptions, and proper tool restrictions.

Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration. Automatically invoked when user requests "create a command", "make a slash command", "add a /command", or mentions custom command development.

Use this skill when creating or refining Claude Code hooks. Hooks are shell commands that execute at specific lifecycle events (tool use, prompt submit, notifications, session events). Helps design event handlers for notifications, formatting, logging, feedback, and permission control. Automatically invoked when user requests "create a hook", "add automation", "event handler", "workflow automation", or mentions hook development.

Use this skill when creating or refining Claude Code plugins. Plugins are bundled collections of agents, skills, commands, hooks, and MCP servers that provide cohesive functionality. Helps design proper directory structures, plugin.json configuration, marketplace distribution, and installation workflows. Automatically invoked when user requests "create a plugin", "bundle components", "distribute capabilities", or mentions plugin development.

Joplin-compatible markdown formatting rules with strict heading hierarchy, spacing, and CSS-aware styling. Activates for any Joplin note creation or reformatting task. Also invoked by joplin-research skill.

Research content templates and citation standards for Joplin notes. Routes to the correct template based on request type. Delegates all markdown formatting to the joplin-formatting skill.