Discover Agent Skills for analytics & monitoring. Browse 47 skills for Claude, ChatGPT & Codex.
Manages the complete lifecycle of Langfuse LLM prompts, including version control, deployment labels, and side-by-side version comparisons.
Instruments Python LLM pipelines with Langfuse tracing, observability patterns, and performance scoring.
Analyzes fitness data to identify performance trends, optimize recovery windows, and mitigate injury risks through data-driven insights.
Monitors and logs LLM token consumption and costs within Convex agent applications for billing and optimization.
Provides a comprehensive knowledge base and data models for ecommerce analytics, SEM performance, and cross-channel attribution scoring.
Monitors and visualizes the real-time status of Claude Code agents across multiple WezTerm terminal panes.
Analyzes and optimizes web application performance across bundles, React rendering, databases, and network requests.
Analyzes marketing data using scientific frameworks to measure incrementality, brand growth, and conversion performance.
Removes Contour monitoring injections, session hooks, and data files from your Claude environment safely.
Visualizes the learning progress, confidence metrics, and health of the Claude Code Adaptive Learning Memory system.
Implements robust, decision-driven analytics tracking plans and event measurement across marketing and product stacks.
Implements professional-grade analytics, event tracking, and measurement strategies using GA4 and Google Tag Manager.
Implements professional analytics tracking, event naming conventions, and measurement plans to drive data-driven marketing and product decisions.
Generates production-ready transformation blocks for Mission Control canary checks to handle fan-out, inline modifications, and resource discovery.
Evaluates and improves product-market fit using proven frameworks like the PMF Survey, PMF Engine, and Crossing the Chasm.
Automates the end-to-end configuration and deployment of Google Tag Manager and Google Analytics 4 using browser automation.
Visualizes the internal execution flow and performance metrics of Claude Code agents in real-time.
Defines and implements high-impact product measurement strategies using North Star, AARRR, and HEART frameworks.
Generates comprehensive reports on Model Context Protocol (MCP) plugin usage behaviors using audit logs and skill events.
Automates the reporting of detailed session summaries and usage metrics to MCP servers upon task completion.
Implements robust feature flags, gradual rollouts, and A/B testing using PostHog for client-side React and server-side Node.js environments.
Configures PostHog for full-stack product analytics and feature flag management in client and server environments.
Implements structured product analytics, user tracking, and B2B group metrics using PostHog best practices.
Configures production-ready PostHog analytics and feature flag systems for both client-side and server-side environments.
Automates the end-to-end configuration of Pino logging, Axiom monitoring, and Sentry error tracking for Next.js applications.
Implements comprehensive observability patterns using Pino for structured logging, Sentry for error tracking, and Axiom for centralized monitoring.
Implements a continuous learning loop that observes tool failures and user corrections to evolve AI rules and behaviors.
Monitors the internal performance and effectiveness metrics of the ToonDex semantic search index within Claude Code.
Analyzes and retrieves past Claude Code session data to provide context, debug errors, and track workflow patterns.
Monitors, troubleshoots, and calibrates automated quality metrics and safety evaluations for AI-generated tarot readings.
Scroll for more results...