What problem does it solve? AI coding agents tend to fill codebases with decorative, redundant, or noisy comments — banner separators, step-by-step narration, signature echoes, and vague TODOs — that add reading load without adding information. This Skill gives agents concrete rules to strip that slop while protecting comments that carry real knowledge. ## Core Features & Use Cases - Slop Pattern Detection: Identifies eight comment anti-patterns including decorative separators, restating the obvious, workflow narration, empty labels, vague placeholders, signature echoes, decorative emoji, and end markers. - Preservation Guardrails: Explicitly protects comments explaining business logic, security, performance trade-offs, API contracts, workarounds, and edge cases. - Scope Safety: Enforces a strict guardrail that only comments may be modified — never executable code, identifiers, formatting, or logic. - Use Case: After an AI agent generates a large feature, run this Skill to clean the diff so every remaining comment explains something the code does not already show. ## Quick Start Review the comments in the files I just changed, remove any generic AI-slop comments, and keep only the ones that explain non-obvious behavior.
