ai-slop-cleanerlisted

## Purpose Reduce AI-generated code bloat through systematic, smell-by-smell cleanup that preserves existing behavior and raises signal quality. ## When to Use - A code path works but feels bloated, noisy, repetitive, or over-abstracted. - A user asks to "cleanup", "refactor", or "deslop" AI-generated output. - Follow-up implementation left duplicate code, dead code, weak boundaries, or missing tests. - A disciplined cleanup workflow is needed without broad rewrites. - The user wants a reviewer-only anti-slop pass via `--review` mode. This skill accepts an optional **file list scope**. If a changed-files list is provided, keep the cleanup strictly bounded to those files. Do not silently expand a changed-file scope. ## Inputs - Codebase or module to clean (or explicit file list scope). - Existing test suite (required — behavior must be locked before editing). ## Workflow 1. **Lock behavior with regression tests first** - Identify the behavior that must not change. - Add or run targeted regression tests before touching cleanup candidates. - If behavior is currently untested, write the narrowest test coverage needed first. 2. **Create a cleanup plan before code** - List the specific smells to remove. - Bound the pass to the requested files/scope. - Order fixes from safest/highest-signal to riskiest. - Do not start coding until the cleanup plan is explicit. 3. **Categorize issues** - **Duplication** — repeated logic, copy-paste branches, redundan