Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Read and update application settings through APIs, including system prompts, reasoning limits, IP filters, and login requirements. Also manage proxy and cache settings, with guidance on how reasoning settings affect requests sent to AI providers.
Manage OmniRoute API keys and provider authentication from the command line. Register, rotate, or revoke keys, inspect usage and expiration, set spending and model restrictions, and start or check OAuth sign-in connections.
Inspect OmniRoute connection restrictions, usage quotas, and retry delays from the command line. Reset stuck providers and adjust failure thresholds, cooldowns, and recovery timing to manage how connections respond to errors.
Review AI call logs by provider, model, time range, status, and cost. Aggregate token usage, export logs, configure budgets, and inspect response times and prompt cache statistics to understand usage and performance.
Start, stop, and restart the OmniRoute server from the command line. Configure its port, background operation, automatic recovery, and system tray integration, or open the dashboard to manage the running server.
Inspect AI costs, token usage—the units used to measure model input and output—and call logs from the OmniRoute command line. Filter records, review spending by connection, and export usage reports for further review.
Back up and restore OmniRoute data from the command line. Manage incremental snapshots, scheduled backups, encryption, and cloud synchronization, with options to compare differences and preview data transfers or imports before applying them.
Monitor AI provider health, response times, usage quotas, and spending alerts in OmniRoute. Inspect circuit breakers, which temporarily block failing providers, and configure whether reaching a budget limit switches models, blocks requests, or issues warnings.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Coordinate tasks across multiple AI agents by tracking workloads and capacity. Redistribute queued work to available agents, adjust priorities and deadlines, and monitor resource use to identify uneven loads and scheduling bottlenecks.
Create and improve GitHub Actions workflows that automate building, testing, and deployment. The skill covers testing across multiple environments, dependency caching, build output management, and security settings such as limited permissions and protected deployment environments.
Monitor agent and system performance through live metrics, resource tracking, bottleneck analysis, and anomaly detection. Track response times and availability against service targets, and prepare dashboard data and performance reports.
Set up ruvector@0.3.3 with supporting packages, register its MCP server for agent access, and verify installation with diagnostic commands and smoke tests. Helps prepare the dependencies needed for initial use of /vector subcommands.
Monitor a swarm, a group of agents, and receive notifications when its status or agent count changes. A watcher script checks status periodically and streams changes through Monitor; separate tools provide one-time status and health checks.