What problem does it solve? Users often receive answers that are too long or too short for their needs, wasting tokens and time. This Skill intercepts the response flow to let users choose exactly how much depth and length they want before the answer is generated. ## Core Features & Use Cases - Heuristic Token Estimation: Estimates input tokens using word-count and character-count heuristics, then projects a response window based on prompt complexity. - Four Depth Levels: Offers Essential (25%), Moderate (50%), Detailed (75%), and Exhaustive (100%) response tiers with estimated token counts for each. - Shortcut Commands: Recognizes direct signals like "short version", "tldr", "50% depth", or "exhaustive answer" to skip the selection prompt, and maintains the chosen level for the rest of the session. - Use Case: A developer asks a complex architecture question but only wants a quick summary first; they say "give me the 25% version" and receive a concise direct answer, then request the full breakdown later. ## Quick Start Ask Claude to give you the short version of its answer or specify a depth level like 50% before it responds to your question.
