Skill UI

TensorBoard delivers a unified interface to track training metrics, debug network behavior, compare experiments, inspect model graphs, and profile performance for PyTorch or TensorFlow workflows.

Utilizes structured critical reasoning to rigorously stress-test ideas, plans, and decisions. This skill allows you to play devil's advocate, conduct pre-mortems, execute red-teaming exercises, or audit underlying assumptions. It employs multiple advanced modes, including Socratic questioning, Hegelian dialectics, and Falsificationism, to identify blind spots, weaknesses, and unstated assumptions before commitment.

This comprehensive skill provides advanced architectural patterns for implementing robust API throttling and rate limiting policies. It covers critical concepts like concurrency limiting, priority queuing, circuit breakers, and adaptive throttling that adjust limits based on real-time backend health metrics (p95/p99 latency). Use this when designing resilient, scalable backend services that must protect themselves from overload and maintain stability under high load.

Automates time series decomposition work in data analytics by guiding through patterns and best practices, generating production-ready code/configuration, and validating outputs for SQL, visualization, and BI workflows.

Automate Token Metrics operations through Composio’s toolkit by orchestrating Rube MCP searches, connection checks, and schema-compliant executions so every `RUBE_MULTI_EXECUTE_TOOL` call runs with up-to-date tooling details and pagination awareness.

This skill provides advanced guidelines for designing robust and effective tools specifically for autonomous AI agents. It shifts the focus from traditional developer APIs to contracts optimized for Language Models (LLMs). Key topics covered include treating tool descriptions as prompt engineering, implementing namespacing, applying the Consolidation Principle, and utilizing Architectural Reduction patterns (like file system access) to maximize agent reliability and workflow complexity.

A comprehensive tool for tracking and analyzing cryptocurrency derivatives markets. It aggregates key metrics such as funding rates, open interest, liquidations, and options flow across major CEX and DEX exchanges. Use it to identify arbitrage opportunities, gauge market sentiment, predict trend strength, and perform deep risk analysis on perpetual swaps and futures contracts.

A comprehensive foundation skill for monitoring cryptocurrency markets. It provides real-time quotes, 24-hour change metrics, and deep historical price data for over 10,000 coins. Users can track specific symbols, view predefined watchlists (e.g., DeFi, Top 10), or export detailed OHLCV data in CSV format. This skill serves as the foundational data layer for crypto portfolio management, tax calculation, and DeFi analysis applications.

Defines and monitors SLAs, SLIs, and SLOs so teams can set performance targets, track metrics like error budgets and availability, and react before issues impact customers.

Automates the end-to-end training of machine learning models by analyzing datasets, selecting suitable algorithms, tuning parameters, performing cross-validated training, and emitting performance metrics plus a saved model artifact.

Guides Claude to automatically tune machine learning model hyperparameters via grid, random, or Bayesian search, generating runnable Python code, executing validations, and reporting best configurations plus performance metrics for accuracy or other goals.

Provides comprehensive observability for the TwinMind AI meeting system. This skill allows users to monitor critical performance metrics, including transcription quality (using Ear-3 model), meeting coverage, action item extraction accuracy, and memory vault health. It is essential for implementing robust, enterprise-grade AI workflows and managing the operational status of advanced meeting AI applications.