MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It is grounded in a controlled blind experiment (4 rewriting strategies × 4 judges) that showed adding traceable personal material dramatically outperformed purely deletion-based methods (8.6 vs 5.9 on a 10-point 'reads human' scale).
Who it is for
- Writers and content creators who want their AI-assisted text to sound human
- Editors and reviewers who detect AI writing
- Developers using AI coding agents (Claude Code, Codex, Cursor, etc.)
- Researchers studying AI text humanization
Use cases
- Diagnose whether a draft sounds AI-generated with a four-layer report
- Rewrite a piece by first asking for real experiences then injecting them
- Validate rewritten text with optional blind test
- Install as a skill for any Agent Skills‑compatible runtime
Strengths
- Evidence‑based methodology from a controlled experiment with measurable scores
- Four‑layer model (vocabulary, syntax, structure, lived experience) addressing the deepest layer AI cannot fake
- Dual modes: diagnosis and rewriting with a hard rule never to fabricate user experiences
- Multi‑runtime compatibility (Claude Code, Codex, Cursor, OpenClaw)
Considerations
- Relies on the user providing genuine personal material – without it, rewriting is limited
- May not suit all writing styles or genres that require strict anonymity or pure fiction
- Adoption requires understanding the skill's philosophy and prompting correctly
README quick start
电车站.skill · Tramstop Skill
人味不是删出来的。 De-slop your writing with evidence, not word blacklists.
AI编细节是为论点服务的， 不会把细节浪费在用不上的电车站上。
为什么叫电车站 · 它凭什么不一样 · 两种用法 · 安装 · English
为什么叫电车站
一次四版本盲测：同一篇文章的四个版本，匿名乱序，交给一位审过上千篇AI投稿、患有重度「AI疑心病」的编辑，让他赌哪版是真人手笔。
他赌中了。理由不是文笔，是一个对论证毫无用处的细节——作者在维也纳除了弗洛伊德博物馆，还去看了阿德勒的电车站。
那个电车站是作者两年前真实发过的动态。这个skill帮你的文字找回它的电车站。
它凭什么不一样
市面上的去AI味工具几乎都是「删」派：禁词表、句式黑名单、破折号计数。这个skill的方法论来自一次真实的对照实验（四版本改写×四评委盲测，数据在 references/evidence.md）：
| 方法 | 盲测得分（像真人，1-10） |
|---|---|
| 原稿 | 5.5 |
| 纯删法（结构手术） | 5.9 —— 评委：「干净得像消过毒」 |
| 删法 + 真实素材注入 | 8.6，四票全胜 |
结论写在名字里：人味不是删出来的。AI味分四层（词汇
许可证
MIT — 随便用，随便改，随便造。
作者的其他项目 · also by 花叔
女娲.skill — 蒸馏任何人的思维方式 · 弗洛伊德.skill — 给AI做心理分析 · 达尔文.skill — 让 Skill 无限进化
English
Tramstop Skill is an evidence-based de-slop skill for AI-assisted writing. Its method comes from a controlled experiment (4 rewrite strategies × 4 blind judges): word blacklists and structure surgery alone barely moved the needle (5.5 → 5.9 on a 10-point "reads human" scale), while injecting traceable personal material scored 8.6 with a unanimous vote.
The name: a judge with severe "AI suspicion" correctly identified the human-sounding version by one detail useless to the argument — the author had visited Adler's tram stop in Vienna. AI invents details that serve the point; humans remember details that serve nothing.
What it does differently:
- Four-layer model: vocabulary < syntax < structure < lived experience. Deleting AI-isms is table stakes; the deepest layer is the only one AI can't fake (consistent with Russell 2025: expert raters still catch humanized AI text at 100% via originality and structure).
- Two modes: diagnose (layered report) or rewrite (mine real material from you → structure surgery → experience injection).
- Hard rule: never fabricates your experiences — it asks, or leaves
[TODO]placeholders.
Install: `git clone https://github.com/alchaincyf/tramstop-skill.git ~/.claude/skil
Description
电车站.skill — 人味不是删出来的。Evidence-based de-slop skill: 四层AI味模型+真实素材注入，来自四版本盲测实验
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.