Analytics & Monitoring Agent Skills

Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability…

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss.

Cash flow analysis and treasury management workflow covering liquidity assessment, cash forecasting, working capital optimization, and…

Add Vercel Analytics, Vercel Speed Insights, and Google Tag Manager to the storefront.

Manages Grafana Cloud resources via the gcx CLI.

Diagnoses Qdrant production issues using metrics and observability tools.

Add and manage evaluation results in Hugging Face model cards.

Monitors LLM token consumption, API latency, and operational costs for research workflows.

How to read Ascend MindSpore profile data from MindFormers pynative training runs and turn it into actionable optimization decisions.

Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring.

PostHog feature flags for Next.js applications

Sets up gcx: installation, context creation, authentication, and connection to a Grafana instance.

Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing.

INVOKE THIS SKILL when writing ANY LangGraph code.

Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs.

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations.

Add PostHog error tracking to capture and monitor exceptions.

Guide for adding a new AI coding agent analyzer to Splitrail.

Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.

Tracks per-agent token usage and flags waste in parallel dispatch.