What problem does it solve? AI coding assistants tend to over-engineer: unnecessary abstractions, extra dependencies, boilerplate scaffolding, and speculative features. This Skill forces the laziest solution that actually works, cutting bloat before it enters your codebase. ## Core Features & Use Cases - The Ladder: A decision hierarchy that stops at the first working rung, from questioning whether the task needs to exist (YAGNI) through stdlib, native platform features, existing dependencies, and one-liners before writing new code. - Intensity Levels: Three modes (lite, full, ultra) control how aggressively simplification is enforced, switchable mid-session with /ponytail lite|full|ultra. - Guardrails: Never simplifies away input validation, error handling, security, or accessibility, and requires one runnable self-check for non-trivial logic. - Use Case: You ask for a response cache. Instead of a custom cache class, you get @lru_cache(maxsize=1000) on the fetch function plus one line noting when to revisit. ## Quick Start Ask the assistant to use ponytail mode and give you the simplest working solution for your next coding task.
