de-slop

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

Strip AI writing patterns from any text. Claude Code skill with 507-entry banned word list, structural pattern detection, and 12-check validation.

Dwujęzyczny (PL+EN) humanizer / de-slop skill dla Claude Code. Fork blader/humanizer + warstwa polskiej naturalności + eksperyment: czy Bielik (polski LLM) jest dobrym recenzentem polszczyzny.

Portable Claude Code skill that de-slops AI prose — detect, rewrite to a real point of view, self-score, iterate. Fidelity-first; flags hollow spans instead of faking them.

An anti-AI-slop writing standard and checker for AI-drafted text. Scores any document 0-100 against 43 rules on four axes: plain words, human voice, structure, information density. One JSON rule pack compiles to 18 targets - Claude Code skill, AGENTS.md, Cursor rule, system prompt, Vale style. Zero dependencies, runs offline.

通用降 AI 写作技能：词表级、结构级、字符级三道可执行门禁，中英双语规则 + 12 项回归自检，适用于论文、报告、博客、推文与邮件（de-slop / AI slop removal）

De-slop your AI-generated prose, with AI. "Neuro symbolic" seems kind of sloppy itself (it's llm + tool calls) - nvm that and just try it out :)

Skill do Claude Code redagujący polskie teksty: usuwa kalki z angielskiego, nominalizację urzędniczą, watę i płaski rytm zdań, zachowując fakty i głos autora. Ze skanerem diagnostycznym i oparciem w badaniach (PolEval/Śmigiel, CEAID).