You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Make AI writing sound human, in English and 中文. A Claude Code / Codex / any-agent skill that strips templated phrasing, consultant-speak, markdown clutter, em-dashes, and copy-paste model residue while keeping the meaning.
Easywrite - make AI-assisted academic writing read human while staying evidence-true, in EN + 中文. Claim-evidence discipline, detector science, bilingual de-slop, integrity firewall.
De-AI Writing · 中文写作去 AI 味总控|中文写作去 AI 味总控。两大功能:①修改已有文章——先定文体,再把 AI 生成感量化为客观指标(词表密度、句式重复率、模板腔密度、结构指纹),逐处核对后给改写方案,附完整性守卫;②从零生成文案——先逐步与用户确认文体、文风、受众、篇幅等全部要素,严禁擅自推测补料,确认完才动笔。判定标准分层:主矛盾(结论先行、防御性写作、伪排比、细节不服务上下文)优先于次要矛盾(词表句式)。覆盖七大类中文文体(实用说明、专业论证、商务事务、营销转化、叙事创作、社交表达、法规制度)四十余个子类。触发词:去 AI 味、降 AI 率、AI 感、太像 AI 写的、人机味、不像人话、润色、改写、humanize、论文降AI率、公众号文案、帮
Read-only content gate that catches the typographic and phrase tells of AI-generated prose before it ships. No network, no credentials, no auto-run. Exit 1 on a hard tell.
Linter and Claude skill for the text between you and a model. Checks prompts for the ambiguity a model will guess through, and model output for invisible watermark characters, machine rhythm, and AI tells. English and Chinese.
baihua — a Claude Code plugin that strips AI-flavor phrasing from dialogue, commits, PRs, docs, and code comments. Code logic untouched. Auto-injected on session start, always on.
My personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
A VM dedicated to stop outsourcing your ability to think to AI (This is partially vibecoded, because the goal is to create a VM in which Ill do not vibecoded projects and Im no vm specialist)
Chinese text de-AI-ifier: strips the AI flavor from Chinese writing using stylistics, lexicology and rhetoric research instead of banned-word lists. 中文去AI味改写器:九指标体检 + 定点干预 + 语义保真