인프라·DevOps 스킬

Plan controlled failure experiments to uncover system weaknesses. Define normal operating metrics, estimate affected users and reliability risk, set abort and recovery conditions, and turn experiment results into a structured review with follow-up actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a controlled failure experiment
• Estimating affected users and reliability risk
• Planning a team failure response exercise

Plan Azure infrastructure around application needs, scale, and budget. Generate Bicep templates, files that define cloud resources as code, then review estimated costs, configure deployment pipelines, and check security settings before production.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning Azure infrastructure for a web app
• Choosing services for microservices or event-driven processing
• Generating Bicep templates and deployment pipelines

Design AWS infrastructure around application needs, traffic, budget, and team experience. Generate templates that define infrastructure as code, compare service choices and estimated costs, and guide deployment, monitoring, and cost reduction.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a serverless backend for an MVP
• Planning AWS infrastructure for a growing SaaS
• Generating CloudFormation infrastructure templates

Manage Microsoft 365 setup, bulk user onboarding and offboarding, licenses, and security reviews. Generate PowerShell scripts and setup plans, with workflows for checking inputs, reviewing changes, and validating results before applying them across an organization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan and configure a new Microsoft 365 environment
• Create user accounts and assign licenses in bulk
• Block departing users and prepare shared mailboxes

Inspect project files to identify languages and build tools, then generate starter GitHub Actions or GitLab CI workflows. Set up automated checks, caching, and deployment stages that reflect the project’s commands and target environments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up automated checks for a new project
• Reworking fragile pipeline configuration
• Moving between GitHub Actions and GitLab CI

Organize responses to service outages and degraded performance, from initial assessment through recovery review. Classify severity, reconstruct event timelines, draft stakeholder updates, and create response guides and follow-up actions based on incident findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify outage severity and plan initial response
• Reconstruct an incident timeline from scattered events
• Draft incident updates for customers and internal teams

Create CI/CD configurations, which automate build, test, and deployment steps, alongside Terraform infrastructure templates and Kubernetes deployment files. Generate health-check and rollback instructions to review before applying changes to cloud infrastructure or application environments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up GitHub Actions or CircleCI pipelines
• Creating Terraform modules for AWS, GCP, or Azure
• Preparing blue/green or rolling deployments

Design Google Cloud infrastructure around application needs, scale, and budget. Get service recommendations, cost estimates, infrastructure configuration files, and deployment guidance, with support for automated delivery and security configuration reviews.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a mobile backend on Cloud Run
• Planning a SaaS architecture on GKE
• Building an event analytics pipeline with BigQuery

Prepare a graded Claude Managed Agent for recurring schedules, event triggers, or on-demand use. Validate timing, build deployment request data, optionally include self-evaluation for each run, and document the next steps in a roadmap.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Schedule an agent to run every morning or weekly
• Prepare a curl trigger for an external event
• Add self-evaluation to each recurring run

Turn a validated build sheet into four API request files and a resumable launch script for Claude Managed Agent. Check the files for exposed keys before users launch with their own Anthropic key.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing launch files from a validated build sheet
• Checking generated files for exposed API keys
• Preparing a launch that can resume after interruption

Close out a launched Claude Managed Agent by listing its recorded components and completed phases. Refresh a shareable, self-contained HTML overview and rank the next one or two upgrades from deferred work and operational improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing the components of a launched agent
• Updating a shareable agent overview page
• Choosing the next one or two upgrades

Run commands and coding agents on existing cmux Cloud machines, monitor work that continues after disconnection, and present results through workspaces or service URLs. The skill guides machine selection, background execution, and result verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run long commands that continue after disconnection
• Assign coding work to a remote agent
• Monitor remote work without opening panes

Prepare and troubleshoot cmux releases by collecting changelog entries, updating versions, checking release readiness, and publishing tags. Follow requirements for macOS disk images, signing, notarization, and update feeds that guide installed apps to new versions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a new cmux release
• Collecting changelog entries from merged PRs
• Troubleshooting a failed pre-tag check

Deploy web projects to Netlify with its command-line tool. The skill checks authentication and project settings, links or creates a site, and publishes a preview or production version with deployment URLs and log links.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publishing a web project on Netlify
• Sharing a preview URL before production
• Linking a project to an existing Netlify site

Deploy apps and websites to Vercel and get a URL to share. The workflow defaults to preview deployments, supports production when explicitly requested, and includes an alternative deployment script when CLI credentials are unavailable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Share an app through a preview URL
• Deploy a project folder or existing tarball
• Publish to production on explicit request

Investigate failed pull request checks in GitHub Actions using the GitHub CLI. The skill gathers logs, summarizes failures, proposes a repair plan, and applies changes after explicit approval, with a summary of changes and tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failed GitHub Actions checks
• Reviewing a repair plan before approving changes
• Summarizing failure logs for a pull request

Inspect production errors recorded in Sentry using read-only queries. The skill summarizes recent issues, retrieves details of individual error occurrences, and accesses AI-generated cause analysis or fix plans through the command-line tool.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing unresolved production issues from the last 24 hours
• Inspecting an issue by its short ID
• Checking individual error occurrences and release details

Deploy applications to Render by inspecting code and preparing build settings, environment variables, and required services. Generates render.yaml deployment configuration or creates services through MCP, then checks deployment status, logs, and basic health.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publish a web application on Render
• Prepare deployment configuration for multiple services
• Set up databases and scheduled jobs

Deploy applications and infrastructure on Cloudflare by matching project needs to services such as Workers and Pages. Guides service selection and authentication checks, with references covering storage, AI, networking, security, and infrastructure configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publish a website or application on Cloudflare
• Deploy serverless functions with Workers
• Choose storage for databases and files

Prepare and publish FastMCP releases, from reviewing changes and crediting contributors to updating changelogs, creating release tags, checking Python package publication on PyPI, and confirming that the documentation site reflects the release.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Previewing changes for the next FastMCP release
• Preparing release notes and contributor credits
• Publishing a patch or maintenance release

Investigate stalled, retrying, or failed Symphony runs by connecting Linear issue identifiers with Codex sessions. Trace log events in time order, identify the failing stage, and collect evidence for the probable cause.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate a stalled run
• Trace repeated retries
• Identify where a Codex session failed

Prepare a Symphony release by updating its version, running checks, merging the change, and tagging the merged commit. Then monitor the Burrito release workflow and verify that the GitHub release contains the expected assets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Release a specified Symphony version
• Prepare the next patch release
• Tag the merged release commit

Coordinate a game release from candidate preparation through testing, release approval, and deployment. Assign work to role-based agents and collect quality results, patch notes, launch messaging, and a post-release monitoring plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a release candidate and checklist
• Collect testing and release readiness results
• Decide whether a release should proceed

Prepare software releases by detecting version files, reviewing changes, and writing changelogs in multiple languages. The workflow updates versions, creates annotated tags with release notes, and can publish GitHub Releases or fill in missing historical releases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a new version from recent changes
• Updating changelogs in multiple languages
• Previewing release changes without modifying files