Loading...
Loading...
Found 1,230 Skills
AIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource health, inspect logs, or run a comprehensive health check across cloud functions, CloudRun services, databases, and other CloudBase resources.
Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.
Write, validate, and optimise PromQL queries for Prometheus and Grafana Cloud Metrics. Use when the user asks to query metrics, write a PromQL expression, calculate rates, aggregate across labels, build histogram quantiles, create recording rules, debug query performance, or understand metric cardinality. Triggers on phrases like "PromQL", "Prometheus query", "write a metric query", "calculate rate", "histogram_quantile", "recording rule", "metric cardinality", "sum by", "rate vs irate", "absent()", or "query is slow".
JingSwap STX↔sBTC cycle monitor and participation agent. Reads live cycle state and prices directly from the Stacks contract via Hiro API and Pyth oracle — no API key required. Outputs PARTICIPATE / MONITOR / WAIT_FOR_DEPOSIT_PHASE / NO_SBTC_AVAILABLE with oracle-vs-DEX discount analysis.
Monitor STX stacking positions — status, PoX cycles, reward payouts, and delegation eligibility for autonomous agents.
Use when viewing service runtime or build logs. Use when user says "show logs", "why did deploy fail", "check build output", or "debug runtime error".
Grafana Alerting, Incident Response Management (IRM), and SLOs. Covers Grafana-managed and data source-managed alert rules, notification policies, contact points (Slack/PagerDuty/email/webhook), silences, muting, on-call scheduling, incident management workflows, and SLO configuration with burn-rate alerts. Use when configuring alerts, debugging notification routing, setting up on-call rotations, managing incidents, defining SLOs, or provisioning alerting via YAML/API.
Grafana Alloy OpenTelemetry collector and telemetry pipeline configuration. Covers the Alloy configuration language (blocks, attributes, expressions), components for collecting metrics/logs/traces/profiles, sending data to Grafana Cloud/Prometheus/Loki/Tempo, clustering, Fleet Management remote config, and building telemetry pipelines. Use when configuring Alloy, writing Alloy config files (.alloy), building data collection pipelines, setting up scraping, or troubleshooting Alloy deployments.
Free, no-auth multi-chain DEX pair data — prices, volume, liquidity, transactions, and token profiles
Interactive TUI dashboard for visualizing Claude Code token usage, costs, and task breakdowns by project, model, and activity type.
Identify early warning signals of potential PR crises through pattern recognition, escalation triggers, and risk assessment
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.