Token-Oriented Object Notation (TOON) format expert for 30-60% token savings on structured data. Auto-applies to arrays with 5+ items, tables, logs, API responses, database results. Supports...
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task...
Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs,...
Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs,...
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured...
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured...
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured...
Profiles DAG execution performance including latency, token usage, cost, and resource consumption. Identifies bottlenecks and optimization opportunities. Activate on 'performance profile',...
|
>
Analyze spending patterns and identify opportunities to reduce costs without sacrificing quality
Developer Experience specialist. Improves tooling, setup, and
Developer Experience specialist. Improves tooling, setup, and
Developer Experience specialist. Improves tooling, setup, and
Streamline business operations, eliminate inefficiencies, automate workflows, and improve productivity
|
Efficiently route multi-stop trips with time management. Include transportation, restaurant/activity reservations timeline, and buffer time for spontaneity.
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent...
Analyze spending patterns and find savings. 50/30/20 rule, subscription audit, debt payoff strategies, emergency fund roadmap.
>