Ansible
Use when the user asks about Ansible playbooks, roles, inventory, ansible-playbook, ansible-galaxy collections, Jinja2 templates, ansible-vault, AWX or Ansible Automation Platform, or idempotent configuration management. Produces idempotent playbooks, roles and CI checks (ansible-lint, Molecule). Not for provisioning cloud resources (use terraform).
Install
npx skills add j4flmao/agent-skills --skill ansiblegit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/devops/ansible ~/.claude/skills/ansiblePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Ansible ## Purpose Automate configuration management, application deployment, and infrastructure orchestration using Ansible playbooks, roles, and modules with idempotency and security best practices. ## Agent Protocol ### Trigger Exact user phrases: "Ansible", "ansible-playbook", "playbook", "inventory", "role", "task", "ansible-galaxy", "ansible-vault", "Ansible Tower", "AWX", "Ansible Automation Platform". ### Input Context Before activating, verify: - Managed node OS (RHEL, Debian, Windows, network devices) — affects module selection. - Inventory source (static INI/YAML, dynamic from cloud/inventory plugin). - Authentication method (SSH key, password with sshpass, WinRM, API token). - Ansible control node version (2.9 vs 2.14+ changes module behavior). - Execution mode (ad-hoc, playbook, pull-mode, Tower/AWX workflow). ### Output Artifact Writes to Ansible playbooks YAML, role directory structure, inventory files, Jinja2 templates, and vars files. ### Response Format YAML playbooks/roles with inline configuration. No extraneous explanation. No preamble. No postamble. No explanations. No filler/hedging/transitions. ### Completion Criteria - [ ] Playbook defined with idempotent tasks. - [ ] Inventory configured (static or dynamic). - [ ] Variables externalized in group_vars/host_vars. - [ ] Roles structured per Ansible Galaxy best practices. - [ ] Sensitive data encrypted with ansible-vault. - [ ] Idempotency verified (playbook can be re-run safely).
Details
- Skill name
ansible- Repository
- j4flmao/agent-skills
- Path
skills/devops/ansible/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Ansible skill do?
Use when the user asks about Ansible playbooks, roles, inventory, ansible-playbook, ansible-galaxy collections, Jinja2 templates, ansible-vault, AWX or Ansible Automation Platform, or idempotent configuration management. Produces idempotent playbooks, roles and CI checks (ansible-lint, Molecule). Not for provisioning cloud resources (use terraform).
How do I install the Ansible skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill ansible. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Ansible popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/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).
AI Agent Architectures
45j4flmao/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 Agent Core Loop
45j4flmao/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).
Apm Observability
45j4flmao/agent-skills
Use when the user asks about APM tools such as Datadog, New Relic, Dynatrace or Elastic APM, RUM, synthetic monitoring, APM tracing, or choosing and costing an observability vendor. Produces vendor APM setup, dashboards and cost controls. Not for vendor-neutral OpenTelemetry pipelines (use devops-opentelemetry) or Prometheus stacks (use prometheus-grafana).
Alibaba Cloud
45j4flmao/agent-skills
Use when the user asks about Alibaba Cloud (Aliyun), ECS, ACK, OSS, SLB/ALB, ApsaraDB RDS, PolarDB, RAM policies, Function Compute, or the Terraform alicloud provider. Produces Alibaba Cloud architectures, RAM and network configs and IaC. Not for AWS (use aws), Azure (use devops-azure) or GCP (use devops-gcp).
Argo CD
45j4flmao/agent-skills
Use when the user asks about Argo CD, syncing cluster state from git with Argo CD, Application or AppProject CRDs, sync policy, sync waves, the argocd CLI, Argo CD RBAC and SSO, or multi-cluster Argo CD. Produces Argo CD manifests, sync settings and access controls. Not for Flux or GitOps repo strategy (use gitops) or ApplicationSets at scale (use devops-gitops-advanced).
Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.