6.8K skills · sorted by popularity
Check and control OmniRoute’s MCP server, which connects agents to tools. Inspect tool permission scopes, enable or restart the server, and invoke tools with JSON arguments from the command line.
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.
Repair confirmed failures in CI, the automated build and test process, starting with the base branch. Then prepare affected pull requests individually, recording checks for the exact code candidate and unresolved issues for owner review.
Manage OmniRoute API keys by creating, listing, rotating, and revoking them. Set access permissions, allowed models, spending limits, and expiration dates for each key to control access to proxy and management endpoints.
Configure HTTP, HTTPS, and SOCKS proxies for requests to external providers. Manage shared or provider-specific rules, test connections, and control proxy rotation to define which intermediary servers handle outgoing requests.
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.
Check OmniRoute server health, component status, and live metrics from the command line. Filter alerts or watch a refreshing dashboard to see provider status and circuit breakers, which interrupt requests when failures occur.
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.
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.
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.
Summarizes recorded system metrics for a chosen period, including completed tasks, errors, memory use, and token consumption. It compares values with historical baselines and flags unusual changes to help assess agent team health.
Run a ruflo agent on your ruOS cloud desktop through an authenticated connection. Follow its output as it runs, record execution status in ruflo, and release the task claim when the run finishes.
Inspect how a task ran across agents by collecting recorded execution spans, or timed processing steps. Build a trace tree showing agent activity, duration, errors, and bottlenecks, with a summary of the execution flow.
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.
Detect and classify unusual readings from Cognitum Seed devices, including spikes, flatlines, and drift. Review anomaly scores, recommend quarantine for scores above 0.9, and save detected patterns for future reference.
Organize Cognitum Seed devices into fleets, or device groups. Create and list fleets, add or remove devices, and delete fleets through dedicated commands, with explicit confirmation required before deletion.
Prepare a node to participate in federation, a setup connecting multiple nodes. Generate an ed25519 keypair and configuration, optionally set a compliance mode, and display the public key and endpoint to share with peers.
Manage firmware updates across IoT device fleets through staged rollouts. Check a small initial group for anomalies before expanding deployment, inspect rollout status, and roll back updates with explicit user approval for device changes.
Check federation health, the connectivity between agents in separate installations. Summarize connected peers, trust levels and scores, active sessions, message exchanges, personal information redactions, and threat detections, with a search of stored federation history.
Register a Cognitum Seed device at a supplied endpoint or its default USB Ethernet address. The workflow establishes an agent connection, retrieves device identity, assigns initial trust, optionally pairs the device, and records registration.
Export recorded AI usage costs and budgets as Prometheus metrics or JSON. Feed external dashboards with totals, model tier breakdowns, session costs, and budget utilization, or send the same data to a webhook endpoint.
Compare two saved cost-summary JSON snapshots to identify changes in total spending, sessions, and model costs. Set limits on spending increases or token growth to flag cost regressions during pull request checks.