dirien

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.

Prepares Go applications to work effectively with AI coding agents. Use when setting up a new Go project or retrofitting an existing one to ensure: structured JSON logging (slog/Zap/ZeroLog/Logrus), machine-readable command output, thorough golangci-lint configuration, non-interactive CLI design with --yes flags, structured error handling with meaningful exit codes, proper context.Context propagation, graceful shutdown, health check endpoints, and a standardized Makefile. Triggers when a user asks to make their Go app "agent-ready," "AI-friendly," wants to improve agent tooling/observability in a Go project, or needs to audit an existing Go project against agent-readiness best practices.

Validate commit messages against the Conventional Commits specification. Auto-detects and installs commitlint CLI if missing. Checks project config or falls back to sensible defaults. Use when validating commit messages, preparing PRs, or enforcing commit conventions.

Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

Safe systematic dependency upgrade with vulnerability scanning and rollback capability. Detects project ecosystem, audits outdated and vulnerable packages, presents a prioritized upgrade plan, and executes upgrades one at a time with test verification after each. Use when updating dependencies, fixing vulnerability alerts, or performing periodic dependency maintenance.

Audit a codebase against well-known software design principles: SOLID, DRY, YAGNI, KISS, Law of Demeter, Separation of Concerns, Composition over Inheritance, and the code-relevant 12-Factor subset. Scores findings by impact and effort, runs adversarial debate on contested violations, and generates a prioritized DESIGN_AUDIT.md. Use when reviewing code quality beyond what linters catch, assessing design health before a refactor, or onboarding to an unfamiliar codebase. Can be invoked standalone or delegated from tech-debt.

Bootstraps Flux CD on Kubernetes clusters, creates and manages GitOps sources (Git/Helm/OCI/Bucket), configures kustomizations and Helm releases, reconciles resources, sets up image automation and alerting, and pushes OCI artifacts. Use this skill whenever the user mentions the flux CLI, flux bootstrap, flux create source, flux create kustomization, flux create helmrelease, flux reconcile, flux get, Flux CD, GitOps with Flux, or asks about managing Kubernetes deployments via GitOps. Also trigger when users ask about creating Git/Helm/OCI/Bucket sources, building or diffing kustomizations, pushing OCI artifacts, setting up image automation, creating Flux alerts/receivers, or bootstrapping Flux on GitHub/GitLab/Gitea/Bitbucket. Even if the user just says "flux" in a Kubernetes context, this skill applies.

Builds Flux manifests locally, diffs YAML files, patches FluxInstance upgrades, creates authentication secrets, traces GitOps delivery pipelines, and bootstraps clusters with the Flux Operator. Use this skill whenever the user mentions flux-operator, FluxInstance, FluxReport, ResourceSet, ResourceSetInputProvider, Flux CD operator management, or asks about GitOps CLI tooling for Kubernetes with Flux. Also trigger when users ask about building Flux manifests, diffing YAML, patching Flux instances, creating Flux secrets, tracing GitOps delivery pipelines, or bootstrapping clusters with Flux. Even if the user just says "flux operator" or "flux-operator cli" without details, this skill has the authoritative reference.

Rotate a leaked or expiring secret using Pulumi ESC — find every environment that references it, rotate it at the source, and verify consumers pick up the new value. Use when someone reports a leaked credential, a key that needs rotating, or asks to "rotate", "revoke", or "roll" a secret/token/API key.

Scaffold a new service on our golden path — a Pulumi project wired to ESC for config, OIDC for cloud auth (no static keys), standard tags, and a preview-before-apply workflow. Use when someone asks to start a new service, stack, or infrastructure-as-code project, or to "follow the golden path".

Triage a production incident on Kubernetes or cloud infra — gather diagnostics, classify severity, propose a stabilization plan, and draft the comms/postmortem. Use when someone reports an outage, a degraded service, a CrashLoopBackOff, a pending/unschedulable pod, or asks to "triage" or "investigate" a prod issue.

Use this skill for every message containing the word "minectl". Claude has zero built-in knowledge of minectl — it is an obscure, third-party CLI for deploying Minecraft servers to cloud providers. Without this skill, any response about minectl will be fabricated. This covers all minectl topics: manifests, create/delete/update commands, RCON troubleshooting, authentication errors, cloud provider selection, instance sizing, budget optimization, TPS tuning, plugin uploads, and edition choice. Do NOT trigger for Minecraft servers managed via Docker, Kubernetes, Ansible, Terraform, or Pulumi — only for minectl-based workflows.

End-to-end docker-compose test harness for the minecraft-prometheus-exporter. Spins up an itzg/minecraft-server:latest vanilla server alongside a freshly built exporter and walks the user through verifying metrics in a live browser/Prometheus session. Use this skill whenever the user wants to "test the exporter end-to-end", "verify metrics against a real Minecraft server", "spin up a local MC server", "run the docker compose test", scrape /metrics from a vanilla MC server, or sanity-check a code change in this repo before opening a PR — including cases where the user just says "let me see if it works" or "run the exporter against MC" without naming the compose file.

Sort the "My Projects" section in the GitHub profile README template by star count. Use this skill when the user asks to sort projects, reorder projects by stars, update project ordering, or refresh the project list ranking. Also use when the user adds a new project and wants it placed correctly by popularity.

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.

Create events on Meetup and Luma using the pulumi-events MCP server tools. Use this skill whenever the user asks to create, schedule, or publish an event on Meetup or Luma — including single-group events, Pro network events that fan out to multiple chapters, online events, or cross-posting from Meetup to Luma. Also use when the user asks to edit an existing event's time, title, or details. Triggers on phrases like "create a meetup", "schedule an event", "publish to all groups", "network event", "cross-post to Luma", "edit the event time", or "set up a workshop on Meetup".