인프라·DevOps 스킬

Investigate AWS production incidents using reusable CloudWatch log queries and metric calculations. Narrow affected resources, compare alarms with deployment events, and reconstruct a timeline to identify changes that may explain the symptoms.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate error spikes, slow responses, and memory exhaustion
• Compare alarm transitions with recent deployments
• Narrow an incident to affected services and resources

Retrieve current Azure retail prices and estimate monthly or annual costs by service, region, and configuration. Compare payment options and calculate Copilot Studio credit usage and estimated costs from expected agent activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Estimate monthly and annual Azure costs
• Compare prices across regions and configurations
• Compare reservations, savings plans, and spot pricing

Ask plain-language questions about AWS resources, settings, and costs, and receive readable tables using read-only AWS CLI commands. Inspect services and filter results by region, state, or tags without creating, changing, or deleting resources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Listing running EC2 instances
• Checking S3 encryption and public access settings
• Finding unattached EBS volumes

Create, review, migrate, or troubleshoot Azure Developer CLI projects. Align application settings, infrastructure definitions, deployment environments, secrets, and automated delivery workflows while checking that configuration files and deployment requirements agree.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an Azure Developer CLI project structure
• Reviewing azure.yaml against Bicep or Terraform definitions
• Organizing environment settings and secret handling

Diagnose Arch Linux problems by reviewing recent updates, service logs, and packages. Get a step-by-step investigation plan, ready-to-copy repair commands, verification steps, and guidance for rollback or cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating problems after an Arch Linux update
• Diagnosing services that fail to start
• Planning repairs with verification and rollback steps

Develop and troubleshoot distributed applications with Aspire. Coordinate services written in different languages through AppHost, configure connections and startup dependencies, inspect logs and metrics, and prepare deployment settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an Aspire application from a template
• Connecting services written in different languages
• Diagnosing services through logs and traces

Review AWS infrastructure code and deployed resources against the six Well-Architected pillars. Produce risk-ranked findings, remediation examples, and an architecture diagram, then create GitHub issues for tracking improvements after user confirmation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review AWS infrastructure code and deployed resources
• Prioritize findings by risk
• Prepare infrastructure code remediation examples

Set up a Python project with AWS CDK, a toolkit for defining cloud infrastructure in code. Follow guidance on prerequisites, AWS credentials, virtual environments, dependencies, template generation, deployment preparation, and reviewing changes before deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a new Python project for AWS CDK
• Preparing a virtual environment and dependencies
• Generating templates and reviewing deployment changes

Manage Azure Container Registry, a service for storing container images, with Azure CLI. Build images in the cloud, copy them between registries, clean up stored artifacts, and configure authentication and network access.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build container images in Azure without local Docker
• Copy images from another registry
• Clean up unused images and tags

Prepare and guide software releases using rules discovered in the project and its automated build workflows. It tracks version files, helps draft release notes, runs release steps with confirmation, and checks the published result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a software version release
• Updating version numbers across multiple files
• Drafting release notes from commit history

Define repeatable workflows and their dependencies in JSON, then execute them through a CLI. Combine commands, read-only agent tasks, parallel branches, and human approval steps, with journal records that support recovery after interruption.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running repeatable build and test workflows
• Resuming a workflow after a crash
• Adding human approval before deployment

Review records across OMC sessions to find recurring obstacles in the agent's working environment. It turns evidence from timelines, logs, and notes into ranked proposals for checks, guidance, tools, or information access, with changes requiring user approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating errors repeated across sessions
• Reviewing missing or disconnected automated checks
• Improving access to logs and service state

Diagnose installation and configuration problems in oh-my-claudecode, including version mismatches, duplicate legacy hooks, and missing runtime requirements. Receive a status report with recommended fixes, with confirmed repairs preserving unrelated settings and custom content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnosing problems after installation
• Checking configuration after an update
• Investigating duplicate legacy hooks

Monitor selected GitHub Actions checks on an SGLang pull request until they pass on its latest commit. Diagnose failures, push small validated fixes, and retry only failed jobs within defined limits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitor selected PR checks until they pass
• Separate code failures from infrastructure problems
• Apply small fixes and track the resulting checks

Calculate how to divide serving memory between recurrent state and KV cache, two memory pools used by hybrid models. Use startup logs and workload settings to recommend a ratio, estimate concurrency, and identify the limiting pool.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a memory ratio for a hybrid model
• Investigating limits on concurrent requests
• Recalculating memory allocation for context length

Understand and modify SGLang's CI pipelines, including test stage order, start conditions, early stopping after failures, and workload splitting. Use the guide to add jobs and investigate failed, skipped, or cancelled checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a test job to an SGLang CI stage
• Investigate failed or skipped CI checks
• Update test partitions and waiting job counts

Collect and review SGLang startup logs to identify unnecessary output and trace its source. Get saved logs and specific cleanup proposals while preserving useful diagnostics, with runtime changes left for user approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating repeated messages in startup logs
• Checking which startup warnings need attention
• Comparing startup logs across models and GPU counts

Launch an SGLang server, run a quick accuracy check, and capture an execution trace for performance inspection. Return the trace location and generated files, ready to open in Perfetto or Chrome tracing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capture an execution trace of SGLang inference
• Check basic accuracy before profiling
• Record input processing and token generation separately

Prepare batches of merged SGLang pull requests for a release branch. It checks conflicts and previous attempts, starts the cherry-pick workflow, monitors completion, and reports created pull requests or failure reasons.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare multiple merged PRs for a release branch
• Check conflicts before starting workflows
• Detect previous cherry-pick PRs

Investigate SGLang serving failures by collecting server state, preserving failing requests, and replaying them on a clean target. Summarize evidence and likely causes, then choose the next debugging tool for crashes, stalls, or performance regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate failed health checks and growing queues
• Reproduce request-specific timeouts or crashes
• Investigate output changes after deployment

Retrieve an EagleEye traceId, an identifier linking a request across logs, using Arthas without changing application code. Observe request-handling methods, capture parameters when needed, and inspect method calls and timings to investigate problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieving a request's traceId without code changes
• Matching request parameters with related logs
• Inspecting method calls and execution times

Design and review infrastructure managed with Terraform or OpenTofu. Get guidance on reusable modules, testing choices, automated deployment workflows, and security checks, with approaches suited to different software versions and the cost of running tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing reusable infrastructure modules
• Choosing infrastructure testing methods
• Setting up automated infrastructure deployment

Prepare a local Terraform environment by checking installation, choosing a macOS or Linux installation method, initializing configuration folders, and validating files. It also addresses plugin download failures and common initialization errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Install Terraform for the first time
• Fix a missing terraform command
• Initialize and validate a folder containing .tf files

Find installation steps, configuration guidance, and command examples for Alibaba Cloud CLI using local Chinese documentation. The skill checks its quick reference or relevant documentation pages before suggesting commands, parameters, and options.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Look up installation and configuration steps
• Check commands for querying ECS instances
• Find output filtering and pagination options