Devops Pulumi

Use when the user asks about Pulumi, Pulumi stacks and config, state backends, ComponentResource, the Automation API, Pulumi ESC and secrets, CrossGuard policy packs, or migrating from Terraform to Pulumi. Produces Pulumi programs in TypeScript, Python, Go or C#. Not for Terraform HCL (use terraform).

45 stars 6 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill devops-pulumi
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/devops/pulumi ~/.claude/skills/devops-pulumi

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Pulumi IaC

## Purpose
Provision, manage, and version cloud infrastructure using Pulumi's programming language approach, enabling real code constructs (loops, conditionals, functions, classes) for infrastructure definition.

## Agent Protocol

### Trigger
Exact user phrases: "Pulumi", "IaC", "infrastructure as code", "Pulumi stack", "Pulumi AWS", "Pulumi Kubernetes", "Automation API", "component resource", "Pulumi state", "Pulumi migrate".

### Input Context
Before activating, verify:
- Target cloud provider (AWS, Azure, GCP, Kubernetes) and region.
- Programming language preference (TypeScript, Python, Go, C#).
- Current state backend (Pulumi Cloud, S3, Azure Blob, GCS).
- Whether migrating from Terraform or creating new infrastructure.

### Output Artifact
Writes to `index.ts`, `__main__.py`, `main.go`, `Pulumi.yaml`, `Pulumi.{stack}.yaml`, and component resource classes.

### Response Format
Code files with Pulumi SDK imports, resource definitions, and stack configurations.

### Completion Criteria
This skill is complete when:
- [ ] Pulumi project initialized with `pulumi new`.
- [ ] Core infrastructure resources defined with proper typing.
- [ ] Stack configurations for all environments (dev, staging, prod).
- [ ] State backend configured and validated.
- [ ] `pulumi up` previews without errors.

### Max Response Length
Direct file write. No response text.

## Quick Start
Read the full skill on GitHub

Details

Skill name
devops-pulumi
Path
skills/devops/pulumi/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Devops Pulumi skill do?

Use when the user asks about Pulumi, Pulumi stacks and config, state backends, ComponentResource, the Automation API, Pulumi ESC and secrets, CrossGuard policy packs, or migrating from Terraform to Pulumi. Produces Pulumi programs in TypeScript, Python, Go or C#. Not for Terraform HCL (use terraform).

How do I install the Devops Pulumi skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill devops-pulumi. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Devops Pulumi popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Devops Serverless

45

j4flmao/agent-skills

Use when the user asks about choosing a serverless platform, AWS Lambda vs Azure Functions vs Cloud Run functions, Serverless Framework, AWS SAM, Knative, OpenFaaS, API Gateway backends, or serverless cost. Produces serverless architectures and deployment configs. Not for cold start latency (use cloud-native-serverless-cold-starts) or Lambda internals (use cloud-native-aws-serverless).

DevOps & Cloud

Devops Progressive Delivery

45

j4flmao/agent-skills

Use when the user asks to roll out a canary release with automatic rollback, blue-green deployments, Argo Rollouts, Flagger, analysis on Prometheus metrics, traffic shifting with Istio, Gateway API or NGINX, or feature flags in rollouts. Produces rollout manifests and metric gates. Not for in-app feature flag code (use backend-feature-flags) or a strategy overview (use kubernetes-architecture).

DevOps & Cloud

Devops Service Mesh

45

j4flmao/agent-skills

Use when the user asks about service mesh, Istio, Istio ambient mode, Linkerd, Envoy sidecars, mTLS between services, VirtualService and DestinationRule, mesh retries and timeouts, or mesh observability. Produces mesh install, traffic and security policies. Not for Cilium networking (use cilium-ebpf) or Consul (use consul).

DevOps & Cloud

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.