인프라·DevOps 스킬

Automate Doppler Secretops operations through Rube MCP, a connection for agent tools. Find supported actions, check their required inputs and the service connection, then run individual or bulk operations with the discovered tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discovering supported Doppler Secretops operations
• Checking the connection before running tasks
• Running multiple supported operations together

Automate DigitalOcean operations through Rube MCP, a connection for agent tools. The skill discovers supported actions and current input requirements, checks authentication, and executes the selected tools, with guidance for bulk operations and paginated results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available DigitalOcean actions
• Running DigitalOcean tasks through an agent
• Preparing bulk operations in DigitalOcean

Automate Cloudflare API operations through Rube MCP, a connection to external tools. The skill discovers available actions, checks required inputs and connection status, and runs tasks through Composio’s Cloudflare API toolkit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available Cloudflare API actions
• Checking the Cloudflare API connection before a task
• Running multiple Cloudflare API operations together

Automate Cloudflare tasks through Rube MCP, a connection between the agent and external tools. It searches for supported actions and their current input requirements, checks connection status, and executes the selected operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discovering supported Cloudflare actions
• Checking current input requirements before execution
• Automating repeated Cloudflare operations

Automate Buildkite operations using Composio tools through Rube MCP, an agent tool connection. The workflow discovers supported actions and required inputs, verifies authentication, and covers execution, bulk operations, and retrieval of results split across pages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discover tools for Buildkite operations
• Check authentication before running tasks
• Run Buildkite operations in bulk

Automate Appcircle operations through Rube MCP, a connection for agent tools. Search for available actions, confirm the service connection, and execute requests with the correct inputs, including batch operations when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discovering available Appcircle actions
• Checking authentication before execution
• Automating repeated Appcircle tasks

Automate Better Stack operations through Rube MCP, a connection for agent tools. The skill searches for supported actions, retrieves their current input requirements, verifies the service connection, and executes the discovered tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding supported Better Stack actions
• Running Better Stack tasks through an agent
• Preparing bulk operations in Better Stack

Automate Anthropic Admin tasks involving API keys, usage, workspaces, and organization management through Rube MCP, a connection to external tools. The skill guides tool discovery, connection checks, multi-step workflows, and bulk operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Manage Anthropic Admin API keys
• Check Anthropic usage
• Handle workspace and organization management tasks

Coordinate Stripe pricing changes, Supabase database updates, and Vercel deployments through the Composio CLI, a command-line tool. Follow an ordered release workflow with post-deployment checks, Slack announcements, and guidance for reversing changes if verification fails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch billing, database, and frontend changes together
• Promote a preview build alongside pricing changes
• Script a recurring release process

Investigate failed automated checks on GitHub pull requests using gh, GitHub’s command-line tool. Retrieve GitHub Actions logs, summarize failures, and propose a repair plan before implementing code changes with user approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate failed GitHub Actions checks on a pull request
• Review failure logs and relevant excerpts
• Approve a repair plan before code changes

Search and aggregate Datadog logs through the Composio CLI. Filter by service, environment, and time range, follow requests across services, and export structured JSON for incident analysis or scheduled daily digests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate sudden increases in errors or latency
• Compare logs around a deployment
• Follow one request across multiple services

Sign in to command-line tools through a browser or device verification code, then save the login to a keychain. Later commands can request the saved credentials by handle, an identifier, without exposing token contents in the conversation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sign in to AWS CLI through AWS SSO
• Authenticate gh or glab through a browser
• Save a gcloud login for later commands

Sign in to a cloud provider’s command-line tool using a verification URL and one-time code approved on the user’s device. Check installation and account identity, save the login, and run commands within that user’s permissions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sign in to a cloud CLI from a separate device
• Check whether required CLIs and helpers are installed
• Verify the cloud account before running commands

Deploy QM to Fly.io or AWS, set up administrator access, and configure connectors. The workflow covers model provider and sign-in choices, optional Slack activation, automated live checks, and a manual web acceptance check.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying QM to Fly.io or AWS
• Setting up initial administrator access
• Configuring connectors and optional Slack access

Deploy the QM package from an organization-owned deployment repository to Fly.io or AWS. Set up an administrator, choose a model provider and sign-in method, configure connectors, and optionally activate Slack, with acceptance checks before handoff.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploy QM to Fly.io or AWS
• Set up an initial QM administrator
• Configure a model provider and sign-in method

Help QM organization admins inspect settings, stored memory, conversations, files, and operational records across the organization. It also supports confirmed configuration changes and external user management, while keeping admin grant changes in the dashboard.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether the requester is an organization admin
• Inspect or update organization and channel settings
• Investigate agent behavior using transcripts and captured prompts

Deploy internal web apps and dashboards to a runtime that stays available after the conversation ends. Share a stable link with authorized people, publish updates as separate versions, and restore an earlier version when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publish an internal dashboard
• Keep a web app available after a conversation
• Share an app with a team or channel

Use shared organization credentials to call search services, paid APIs, or Git remotes through a broker, an intermediary that adds authentication without revealing the secret. Requests stay within the configured hosts, paths, and permitted operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search with an organization’s shared API credential
• Retrieve data from a paid API or data feed
• Fetch or push Git changes through a shared account

Run the current working copy locally with a real language model and Postgres database. Choose web, Slack, or both to test a branch end to end, with separate Slack apps for concurrent instances.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test a branch through Slack
• Check web and admin screens locally
• Run several working copies at once

Diagnose failed GitHub Actions runs by finding the first meaningful error, separating code problems from infrastructure issues and intermittent failures, and comparing the base branch. Get a focused report explaining the PR’s involvement and recommended next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failed PR checks
• Separating intermittent test failures from code defects
• Checking whether the base branch already fails

Investigate service errors in Sentry by project, environment, and time period. Rank problems by event counts and affected users, compare releases or earlier periods, and report findings with links and a clear search scope.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing errors affecting production
• Checking changes after a release
• Comparing service stability across periods

Investigate a possible incident in Superset’s hosted services by checking deployments, error spikes, and service health. Produce a proposed severity and status page update for human review, without changing services or publishing messages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a reported Superset outage
• Checking the scope of a sudden increase in errors
• Drafting an incident severity and status page update

Diagnose Superset connection, host, terminal, authentication, and update problems using status checks and logs. Get a matching fix, approve changes before they run, and verify whether the original problem is resolved.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a Superset connection failure
• Recovering an offline host
• Checking terminal attachment problems

Configure a repository for Superset so new isolated Git workspaces have dependencies, environment files, and service access ready. Create lifecycle scripts in .superset/config.json and verify the setup by starting a real test workspace.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a repository for use with Superset
• Install dependencies automatically in new workspaces
• Provide environment files when creating workspaces