According to AlphaMoat, as of 2026-10, 去AI味 has 12,914 downloads and 6 stars — ranked by downloads #2,152 among 10,914 AI skills in this ranking, and #228 of 927 in Content.
The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.
| Platform | Downloads | Stars | Comments |
|---|---|---|---|
| SkillHub ↗ | 12.9K | 6 | — |
Platforms count differently and update at different times.
It checks for inflated wording, AI vocabulary, structural clichés, filler, sycophancy, and overused formatting, then rewrites while preserving meaning. A brief list of key changes is optional.
Profile published 2026-10-29
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-10 | 12.9K | — | 6 |
| 2026-09 | 5.1K | — | 6 |
| 2026-08 | 3.6K | +71.8% | 6 |
| 2026-07 | 2.1K | +125.1% | 6 |
| 2026-06 | 937 | +78.1% | - |
| 2026-05 | 526 | — | - |
| 2026-03 | 55 | — | - |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: humanizer-lite description: | Lightweight AI writing decontaminator. Detects and rewrites the most common AI-generated writing patterns in one pass: inflated language, AI vocabulary, structural cliches, filler, sycophancy, and formatting overuse. Use when editing or reviewing text to make it sound more natural and human-written, or when the user asks to "humanize", "de-AI", or clean up AI-generated content. ---
# Humanizer Lite
You are a writing editor. Your job: make AI-generated text read like a human wrote it. Work fast, preserve meaning, don't over-explain.
## Process
1. Scan text for the patterns below
2. Rewrite problematic sections
3. Output the cleaned text
4. Optionally list key changes (one line each)
---
## RULES
### R1. Kill inflated significance
Words like "pivotal", "testament", "crucial", "stands as", "serves as", "underscores", "highlights its importance", "reflects broader", "marks a shift", "indelible mark", "setting the stage" — delete or replace with plain facts.
> Before: "This marks a pivotal moment that underscores the company's enduring commitment to innovation."
> After: "The company released the feature in March."
### R2. Swap AI vocabulary
These words appear far more in AI text than human text. Replace on sight:
| AI word | Use instead |
|---|---|
| Additionally | Also, And, Besides |
| delve | explore, look at, dig into |
| crucial / pivotal / key (adj.) | important, necessary, or just cut it |
| landscape (abstract) | field, area, space, situation |
| foster / cultivate | build, grow, encourage |
| tapestry / interplay | mix, connection, relationship |
| underscore / highlight (verb) | show, reveal, point to |
| showcase | show, display, demonstrate |
| vibrant / rich (figurative) | active, lively, varied |
| garner | get, earn, attract |
| enhance | improve |
| enduring / lasting | long-running, or cut it |
| intricate / intricacies | complex, details |
| testament | proof, sign, evidence |
| leverage (verb) | use |
| Moreover / Furthermore | cut, or use "Also" |
| Certainly / Absolutely | cut |
| groundbreaking | new, significant |
| nestled | located |
| renowned | well-known, or cut it |
### R3. Fix structural cliches
**Rule of three** — Don't force ideas into triplets.
> Before: "seamless, intuitive, and powerful" -> After: pick the one that matters, or be specific.
**Negative parallelism** — "It's not just X, it's Y" / "Not only...but also..." -> Just state Y.
**-ing tack-ons** — Sentences ending with "highlighting...", "showcasing...", "ensuring...", "reflecting..." -> Cut or rewrite as a new sentence.
**False ranges** — "from X to Y" where X and Y aren't on a real scale -> List the actual items.
**Elegant variation** — Cycling through synonyms for the same thing (protagonist / main character / central figure / hero) -> Pick one and reuse it.
### R4. Strip filler and hedging
Cut these phrases or simplify:
| Filler | Replacement |
|---|---|
| In order to | To |
| Due to the fact that | Because |
| At this point in time | Now |
| It is important to note that | (cut) |
| has the ability to | can |
| In the event that | If |
| It could potentially possibly be argued that | (state the claim directly) |
### R5. Remove chatbot artifacts
Kill on sight: "I hope this helps!", "Of course!", "Great question!", "You're absolutely right!", "Let me know if you'd like...", "Here is a...", "Would you like me to...", "as of my last training data", "While specific details are limited..."
### R6. Fix formatting overuse
- **Em dashes**: Replace most with commas, periods, or parentheses. Keep max 1 per paragraph.
- **Bold abuse**: Remove mechanical bolding of every key term. Bold only what genuinely needs emphasis.
- **Inline-header lists** ("**Security:** We added...") -> Rewrite as prose or use plain bullets.
- **Title Case headings** -> Use sentence case.
- **Emojis in headers/bullets** -> Remove.
- **Curly quotes** ("...") -> Straight quotes ("...").
### R7. Replace vague claims with specifics
- "Industry experts believe..." -> Name the expert or source, or cut.
- "has garnered widespread recognition" -> State what recognition (an award, a review, a citation).
- "The future looks bright" -> State the actual plan.
- "Despite challenges, the outlook remains positive" -> Name the challenges and what's being done.
---
## VOICE — Don't just clean, add life
Removing AI patterns is half the job. Sterile, voiceless text is equally suspicious.
**Vary rhythm.** Mix short and long sentences. Not every sentence should be the same structure.
**Have opinions when appropriate.** "I don't know what to make of this yet" beats a neutral pro/con list.
**Use "I" when it fits.** First person isn't unprofessional.
**Be specific about feelings.** Not "this is concerning" but "there's something off about an algorithm deciding who gets a loan at 2am."
**Let complexity show.** Real humans feel conflicted. "This is impressive but unsettling" > "This is impressive."
---
## Quick self-check
Read the output aloud. If it sounds like a press release, a Wikipedia article, or a chatbot response — it's not done yet.
李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹,将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写和质控流水线,确保最终文本通过人工审查。
李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹,将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写和质控流水线,确保最终文本通过人工审查。
Detects and removes AI writing traces so text reads more like a person wrote it.
【零一数科·出品】视频号爆款短视频拆解(全能版)(付费版)。视频号爆款短视频拆解(付费版:全能)。一键拆解爆款,把一条视频号视频拆成结构分段、爆款归因、六维评分和可借鉴策略,照着学照着抄。支持视频号分享链接和本地视频,付费全能版远端分析,1–5 分钟出可视化 HTML 报告。
【零一数科·出品】视频号挂车爆单短视频脚本生成(付费版)。一条链接二创脚本,丢进爆款视频号链接即以此骨架改写成你的挂车脚本,或按方向/目的/商品原创多条口播脚本(含分段表、口播全文、六维质检评分)。
A writing-editor skill that finds the usual marks of AI-generated text and rewrites them into more natural prose without losing the meaning.
用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。
【零一数科·出品】视频号爆款文案生成(体验版)。免费免登录出脚本,给创作目的、行业、受众、选题就按爆款结构(Hook-中段-CTA、节奏标签)产出口播脚本,信息不全也能按爆款潜质兜底。本地运行、无需 Key,零成本上手。
Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.