What problem does it solve? AI coding agents tend to leave behind generic, decorative comments—banner separators, step-by-step narration, restated signatures, vague TODOs—that add noise without information. This Skill gives agents a concrete rulebook for cleaning up those comments while protecting the ones that carry real meaning. ## Core Features & Use Cases - Slop Pattern Detection: Identifies decorative separators, restated-obvious comments, workflow narration, empty labels, vague TODOs, signature echoes, decorative emoji, and end markers, each with a Tell/Why/Fix entry tied to a core rule number. - Preservation Guardrails: Explicitly protects comments explaining business logic, security, performance trade-offs, concurrency, API contracts, workarounds, and edge cases. - Scope Guardrail: Modifies comments only—never executable code, identifiers, imports, formatting, or control flow. - Use Case: After an AI agent generates a module full of // Step 1: Validate input and // ===== ROUTES ===== comments, run this Skill to strip the noise and keep only the comments explaining non-obvious behavior. ## Quick Start Review the comments in this file, remove the generic AI-slop ones, and keep only comments that explain something the code does not already show.
