Skill UI

Provides strategies to optimize costs when utilizing the Cohere API. This guide covers model tier selection (economy, standard, premium), implementing token budgets, reducing embedding storage costs (e.g., using int8), and establishing comprehensive usage trackers. It is essential for maintaining cost predictability in production AI deployments.

This guide provides step-by-step instructions to configure access to the CoreWeave Kubernetes Service (CKS). It covers downloading the kubeconfig file, setting API tokens, and verifying GPU node access using standard `kubectl` commands. This is essential for deploying AI/ML workloads on bare-metal GPU infrastructure.

This guide addresses critical LangGraph streaming pitfalls, including state overdraw, proxy buffering issues (Nginx, Cloud Run), and excessive event noise. It provides a production-grade pattern for implementing robust SSE/WebSocket endpoints using FastAPI. Learn how to correctly select the `stream_mode` (messages, updates, values) and implement server-side event filtering to reliably build live-token chat UIs and perform comprehensive state visualization.

A comprehensive guide on how to write, organize, and optimize skills for AI agents using a Test-Driven Development (TDD) approach, focusing on Claude Search Optimization (CSO) and token efficiency.

This skill implements advanced 'Gatekeeper' logic to optimize AI agent performance in long-running workflows. It prevents context window bloat by sharding metadata, allocating token budgets, and enforcing Atomic Precision to deliver purely functional, filler-free responses. Ideal for complex coding, multi-step reasoning, and large document analysis where conciseness is critical.

This tool audits the token consumption across all components (agents, skills, rules, MCP servers) within a Claude Code session. It analyzes token overhead, identifies bloat (e.g., overly long descriptions, redundant components), and generates a detailed context budget report. Use it to maintain optimal context window usage, improve performance, and prevent context saturation.

This skill wraps the `getCompactContext` functionality to efficiently retrieve a compacted ReasoningBank context, specifically optimized for cost-analysis queries. It generates a detailed report summarizing critical metrics such as tokens saved, memories retrieved, and agentic-flow availability. It is essential for monitoring and optimizing resource usage in complex AI workflows, providing deep visibility into the efficiency and cost of the context retrieval mechanism.

This tool automatically reads usage data from active AI coding sessions (JSONL format). It tallies token usage per model and tier, calculates the total cost in USD using specified pricing models, and persists a structured record into the cost-tracking namespace. Use this after completing a chunk of work or at the end of a session to provide accurate data for cost reporting and optimization.

This skill intercepts the AI response flow to allow users to explicitly control the desired depth, length, and token usage of the generated answer before the model begins writing. By analyzing the prompt's complexity and the user's intent (e.g., 'short version', 'detailed answer'), it estimates the appropriate token range and prompts the user to select a granularity level (25%, 50%, 75%, or 100%).

This comprehensive guide outlines best practices for achieving rigorous reproducibility in complex AI and knowledge graph research. It details how to pin every component—from tokenizers and KGs to LLM prompts and environment settings—ensuring that results are fully documented and verifiable by peers, even when proprietary data is involved.