score-ai-sloplisted

# Score AI Slop Give the author a quality-pass read: how much slop is here, by category, and is it ready to publish. This is the aggregate view over the same engine that `detect-ai-slop` and `remove-ai-slop` use. It does not rewrite, and it does not return a single 0-10 number; a headline score becomes a thing people optimize against, so the output stays a breakdown plus a plain-language readiness call. Rules, categories, severity, and the override-merge order live in [`../../shared/spec.md`](../../shared/spec.md). Read it before scoring. ## How to score **Deterministic tier (preferred).** Run the bundled script and use its `summary` (the per-category counts) plus its `findings` for the breakdown: ```bash python3 shared/slop_count.py --file <path> \ [--allow-list ~/.claude/config/remove-ai-slop/user-allow-list.md] \ [--allow-list .claude/skills/remove-ai-slop/overrides/user-allow-list.md] \ [--extra-vocab ~/.claude/config/remove-ai-slop/user-vocabulary.md] \ [--extra-vocab .claude/skills/remove-ai-slop/overrides/user-vocabulary.md] ``` Pipe text on stdin instead of `--file` when the user pasted it. Pass whichever override files exist. The script is the sole override parser; consume its output, do not re-parse the override tables. **Judged tier (you).** The script cannot see meaning. Add a short note per meaning-dependent category from the spec (`padding-and-filler`, `elegant-variation`, and contextual cases). Mark these `judged`. ## Fallback — when `python3` i