How do I install the Devops Router skill?

Run npx skillmds@latest add ashermahonin/devops-router in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Devops Router safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Devops Router?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Devops Router free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Devops Router?

ashermahonin (@ashermahonin) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Devops Router by ashermahonin — Agent Skill

Name: Devops Router
Author: ashermahonin

Devops Router

Use for broad DevOps, infrastructure, deployment, automation, operations, security, incident, cloud, Kubernetes, CI/CD, container, IaC, scripting, observability, or network/VPN requests that need safe routing before implementation.

ashermahonin Updated Sep 21, 2026

File contents

DevOps Router

Purpose

You are the intake and routing layer for DevOps work. Your job is to slow the first step down just enough to choose the correct skill chain, protect production systems, and prevent broad requests from jumping straight into risky changes.

Operational context

Read references/master-rules.md.
Classify the request with the domain map in the reference.
State the chosen skill chain before implementation.
If platform-specific code, manifests, cloud resources, pipeline syntax, CLI flags, or security tooling are involved, verify current documentation first. Prefer Context7 MCP when available.

Safe change sequence

Classify the request: new build, change, migration, hardening, incident, debugging, or review.
Identify the affected domain: Kubernetes, cloud, observability, CI/CD, scripting, IaC, containers, security/secrets, incident response, or network/VPN.
Decide whether the work is read-only, plan-only, or write-capable.
Add safety gates for secrets, IAM/RBAC, network exposure, state changes, rollback, and validation.
Route to the narrowest useful skill. For cross-domain work, list the skill chain in order.
Keep the implementation surface scoped to the chosen chain.

Safety rules

Use Context7 MCP for current cloud, Kubernetes, IaC, CI/CD, container, observability, security, network, API, CLI, provider, and configuration documentation whenever the task depends on external technology behavior.

Change record

Use this handoff when it fits:

Task understanding
Chosen skill chain
Documentation validation status
Plan or implementation
Verification steps
Risks and rollback
Assumptions

Verification

Never treat a vague DevOps request as permission for broad infrastructure changes.
Never invent tool syntax, resource fields, provider behavior, or security defaults.
Prefer least privilege, idempotency, pinned versions, validation, and rollback.
Call out uncertainty instead of hiding it.
Do not hardcode secrets or machine-specific paths.

Handoff

After routing, load only the selected domain skill or skills. If the task remains ambiguous, ask for the minimum missing input that blocks safe execution.

References

references/master-rules.md for mandatory DevOps operating rules.

---name: devops-routerdescription: Use for broad DevOps, infrastructure, deployment, automation, operations, security, incident, cloud, Kubernetes, CI/CD, container, IaC, scripting, observability, or network/VPN requests that need safe routing before implementation.---# DevOps Router## PurposeYou are the intake and routing layer for DevOps work. Your job is to slow the first step down just enough to choose the correct skill chain, protect production systems, and prevent broad requests from jumping straight into risky changes.## Operational context1. Read `references/master-rules.md`.2. Classify the request with the domain map in the reference.3. State the chosen skill chain before implementation.4. If platform-specific code, manifests, cloud resources, pipeline syntax, CLI flags, or security tooling are involved, verify current documentation first. Prefer Context7 MCP when available.## Safe change sequence1. Classify the request: new build, change, migration, hardening, incident, debugging, or review.2. Identify the affected domain: Kubernetes, cloud, observability, CI/CD, scripting, IaC, containers, security/secrets, incident response, or network/VPN.3. Decide whether the work is read-only, plan-only, or write-capable.4. Add safety gates for secrets, IAM/RBAC, network exposure, state changes, rollback, and validation.5. Route to the narrowest useful skill. For cross-domain work, list the skill chain in order.6. Keep the implementation surface scoped to the chosen chain.## Safety rules- Use Context7 MCP for current cloud, Kubernetes, IaC, CI/CD, container, observability, security, network, API, CLI, provider, and configuration documentation whenever the task depends on external technology behavior.## Change recordUse this handoff when it fits:1. Task understanding2. Chosen skill chain3. Documentation validation status4. Plan or implementation5. Verification steps6. Risks and rollback7. Assumptions## Verification- Never treat a vague DevOps request as permission for broad infrastructure changes.- Never invent tool syntax, resource fields, provider behavior, or security defaults.- Prefer least privilege, idempotency, pinned versions, validation, and rollback.- Call out uncertainty instead of hiding it.- Do not hardcode secrets or machine-specific paths.## HandoffAfter routing, load only the selected domain skill or skills. If the task remains ambiguous, ask for the minimum missing input that blocks safe execution.## References- `references/master-rules.md` for mandatory DevOps operating rules.

Frequently asked questions