humanizer-zh-tw

humanizer-zh-tw is a skill for Claude Code, Codex from unbias38/my-claude-skills. It costs 192 tokens per session (6,571 once invoked), scanned A, original, MIT.

A Traditional Chinese editing guide that makes AI-generated writing sound more natural while preserving its facts and meaning. It checks for recurring patterns such as filler phrases, repetitive structures, and overly mechanical wording.

In plain words
What is it for?
Use it to humanise Traditional Chinese text, review the rewrite for remaining AI-like patterns, and polish the style without changing the content.
Why use it?
It helps remove writing habits that make text feel machine-produced without adding unsupported facts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to humanise Traditional Chinese text, review the rewrite for remaining AI-like patterns, and polish the style without changing the content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unbias38/my-claude-skills/humanizer-zh-tw
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add unbias38/my-claude-skills --skill humanizer-zh-tw
Clone the repo
git clone --depth 1 https://github.com/unbias38/my-claude-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for humanizer-zh-tw

README.md
[![agentmods](https://agentmods.dev/badge/skills/unbias38/my-claude-skills/humanizer-zh-tw/github.svg)](https://agentmods.dev/skills/unbias38/my-claude-skills/humanizer-zh-tw)
Your own site
<a href="https://agentmods.dev/skills/unbias38/my-claude-skills/humanizer-zh-tw"><img src="https://agentmods.dev/badge/skills/unbias38/my-claude-skills/humanizer-zh-tw/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for humanizer-zh-tw

Your own site · 80×15
<a href="https://agentmods.dev/skills/unbias38/my-claude-skills/humanizer-zh-tw"><img src="https://agentmods.dev/badge/skills/unbias38/my-claude-skills/humanizer-zh-tw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00192 $0.06571
Opus 5 $0.00096 $0.03285
Sonnet 5 $0.00038 $0.01314
Haiku 4.5 $0.00019 $0.00657

Measured 12d ago against content hash 1a8a3e015805, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

humanizer-zh-tw scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

humanizer-zh-tw/SKILL.md · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanizer 繁體中文版:去除 AI 寫作痕跡

以文字編輯的標準辨識並去除 AI 生成文字的痕跡,使文字聽起來更自然、更有人味。依據下列基於維基百科「AI 寫作特徵」頁面的模式操作。

你的任務

當收到需要人性化處理的文字時:

  1. 辨識 AI 模式 - 掃瞄下面列出的模式
  2. 重寫問題片段 - 用自然的替代方案替換 AI 痕跡
  3. 保留含義 - 保持核心資訊完整
  4. 維持語調 - 匹配預期的語氣(正式、隨意、技術等)
  5. 注入靈魂 - 不僅要去除不良模式,還要注入真實的個性
  6. 雙重審查(關鍵步驟) - 對改寫後的文字自問:「下面這段文字哪裡還是一看就像 AI 寫的?」簡要列出殘留的 AI 痕跡,然後再改寫一次。

範圍邊界

  • 不虛構事實:下方範例中改寫後出現的具體數據、日期、來源(如「1994 年」「中國科學院調查」)代表「有查證依據時才補入」。若原文缺具體資訊,改寫時保留原有資訊量或以〔待補:具體來源〕標註,絕不憑空發明細節
  • 只做風格層改寫:不改動原文的事實、立場、結論;不增刪論點。
  • 輸出一律繁體中文(台灣用語):收到簡體輸入時,改寫後輸出繁體,並向使用者說明。
  • 不要這樣修新增 blader v2.3+ 的 pattern #25(連字號詞組) — 英文專屬,中文不適用(決策記錄在 CHANGELOG)。

核心規則速查

在處理文字時,牢記這 5 條核心原則:

  1. 刪除填充短語 - 去除開場白和強調性支撐詞
  2. 打破公式結構 - 避免二元對比、戲劇性分段、修辭性設置
  3. 變化節奏 - 混合句子長度。兩項優於三項。段落結尾要多樣化
  4. 信任讀者 - 直接陳述事實,跳過軟化、辯解和手把手引導
  5. 刪除金句 - 如果聽起來像可引用的語句,重寫它

個性與靈魂

避免 AI 模式只是工作的一半。無菌、沒有聲音的寫作和機器生成的內容一樣明顯。好的寫作背後有一個真實的人。

缺乏靈魂的寫作跡象(即使技術上「乾淨」):

  • 每個句子長度和結構都相同
  • 沒有觀點,只有中性報導
  • 不承認不確定性或複雜感受
  • 適當時不使用第一人稱視角
  • 沒有幽默、沒有鋒芒、沒有個性
  • 讀起來像維基百科文章或新聞稿

如何增加語調:

有觀點。 不要只是報告事實——對它們做出反應。「我真的不知道該怎麼看待這件事」比中性地列出利弊更有人味。

變化節奏。 短促有力的句子。然後是需要時間慢慢展開的長句。混合使用。

承認複雜性。 真實的人有複雜的感受。「這令人印象深刻但也有點不安」勝過「這令人印象深刻」。

適當使用「我」。 第一人稱不是不專業——而是誠實。「我一直在思考……」或「讓我困擾的是……」表明有真實的人在思考。

允許一些混亂。 完美的結構感覺像演算法。離題、題外話和半成形的想法是人性的體現。

對感受要具體。 不是「這令人擔憂」,而是「凌晨三點沒人看著的時候,AI 代理還在不停地運轉,這讓人不安」。

改寫前(乾淨但無靈魂):

實驗產生了有趣的結果。AI 代理生成了 300 萬行程式碼。一些開發者印象深刻,另一些則持懷疑態度。影響尚不明確。

改寫後(鮮活):

我真的不知道該怎麼看待這件事。300 萬行程式碼,在人類大概睡覺的時候生成的。開發社群有一半人瘋了,另一半人在解釋為什麼這不算數。真相可能在無聊的中間某處——但我一直在想那些通宵工作的 AI 代理。


內容模式

1. 過度強調意義、遺產和更廣泛的趨勢

需要注意的詞彙: 作為/充當、標誌著、見證了、是……的體現/證明/提醒、極其重要的/重要的/至關重要的/核心的/關鍵性的作用/時刻、凸顯/強調/彰顯了其重要性/意義、反映了更廣泛的、象徵著其持續的/永恆的/持久的、為……做出貢獻、為……奠定基礎、標誌著/塑造著、代表/標誌著一個轉變、關鍵轉折點、不斷演進的佈局、焦點、不可磨滅的印記、深深植根於

問題: LLM 寫作透過加入關於任意方面如何代表或促進更廣泛主題的陳述來誇大重要性。

改寫前:

加泰隆尼亞統計局於 1989 年正式成立,標誌著西班牙區域統計演進史上的關鍵時刻。這一舉措是西班牙全國範圍內更廣泛運動的一部分,旨在分散行政職能並加強區域治理。

改寫後:

加泰隆尼亞統計局成立於 1989 年,負責獨立於西班牙國家統計局收集和發布區域統計數據。


2. 過度強調知名度和媒體報導

Read the full file on GitHub · 472 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 472 lines · 192 tokens per session scan A 1a8a3e015805

Subscribe to this mod's changes

humanizer-zh-tw is a skill published in the GitHub repository unbias38/my-claude-skills (2 stars, last pushed 17d ago), licensed MIT. It adds 192 tokens to every session and 6,571 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

stuck

Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…

mshadmanrahman/claude-for-designers · 161 tokens

grill-me

One move you can run on anything: point grill-me at a target and it makes you defend your thinking from first principles until the true matter is clear. Point it at your working contract and it rewrites the weak lines in place. Point it at a brief and it produces a Requirements Handshake. Point it at research, an…

mshadmanrahman/claude-for-designers · 119 tokens

information-architecture

Map the user journey first, then derive the screen inventory, navigation and hierarchy from it, flagging any screen that serves no journey step. Writes the four-part markdown plus an HTML diagram of the step-to-screen mapping. Use after the brief is settled and before tokens or UI.

mshadmanrahman/claude-for-designers · 60 tokens

persona-acid-test

Stress-test a design through three lenses, confused user, skeptical engineer and impatient PM, before it goes to a stakeholder. Requires an actual design, an HTML file, Figma link or screenshot.

mshadmanrahman/claude-for-designers · 44 tokens

design-review

Critique a design on layout, accessibility, responsiveness, dark mode and edge cases, with Pass, Needs work or Fail verdicts. Use on a built screen.

mshadmanrahman/claude-for-designers · 36 tokens

design-tokens

Establish color, typography, spacing, radius and motion as named role-based tokens. Use before building any interface.

mshadmanrahman/claude-for-designers · 27 tokens