What problem does it solve? AI assistance drops the cost of doing work properly to near-zero, yet developers still default to quick hacks that accumulate technical debt. This Skill forces every decision point to be scored on a Thoroughness Rating (T:1-10) so the higher-quality option is chosen whenever the AI-assisted effort delta is small. ## Core Features & Use Cases - Thoroughness Rating Scale: Scores every option from T:1 (untested copy-paste) to T:10 (full edge cases, tests, docs) with a defined rubric. - Structured Option Presentation: Re-states project, branch, and task context, then rates each option with manual vs AI-assisted effort estimates and a coverage delta. - Scope Classification: Distinguishes contained work (score and execute at T:8+) from unbounded work (break into independently shippable pieces before scoring). - Use Case: When adding rate limiting to an API endpoint, the Skill presents a full sliding-window Redis-backed limiter (T:9, ~20 min with AI) versus a basic in-memory counter (T:4, ~5 min), quantifies what the extra 15 minutes buys, and recommends the thorough option. ## Quick Start Ask the AI to score the implementation options for your current task using thoroughness scoring and recommend the highest-rated approach.
