基础设施与 DevOps技能

Set up WizTelemetry Auditing to collect Kubernetes and KubeSphere audit events, records of system operations. Configure storage and retention, then query events by user, action, resource, response status, or time.

中文简介正在准备中。当前显示英语简介。

• Deploy audit event collection to selected clusters
• Find operations by user, action, resource, and time
• Configure audit storage and retention

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Automate Dnsfilter operations through Rube MCP and Composio by discovering available tools, checking the account connection, and executing requests using current input requirements. Includes guidance for bulk operations and retrieving complete results.

中文简介正在准备中。当前显示英语简介。

• Find available tools for a Dnsfilter task
• Check the Dnsfilter account connection
• Execute requests using current input requirements

Automate Docker Hub administration through Composio: create organizations and repositories, list teams, invite members, and configure webhooks that notify other services when container images are pushed to a repository.

中文简介正在准备中。当前显示英语简介。

• Create a Docker Hub organization or repository
• Review repositories with filters and sorting
• List teams and invite organization members

Automate Docker Hub repository, image, and tag management through Rube MCP. Discover available operations and their required inputs, then carry out individual tasks, connected workflows, or bulk operations using Composio’s toolkit.

中文简介正在准备中。当前显示英语简介。

• Manage Docker Hub repositories, images, and tags
• Check available Docker Hub operations
• Connect multiple registry management steps

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

• 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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

• 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

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.

中文简介正在准备中。当前显示英语简介。

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