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.
npx skills add kevintsai1202/Humanizer-zh-TW --skill text-watermark-cleaner-zh-twgit clone --depth 1 https://github.com/kevintsai1202/Humanizer-zh-TWWrote 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.
[](https://agentmods.dev/skills/kevintsai1202/humanizer-zh-tw/text-watermark-cleaner-zh-tw)<a href="https://agentmods.dev/skills/kevintsai1202/humanizer-zh-tw/text-watermark-cleaner-zh-tw"><img src="https://agentmods.dev/badge/skills/kevintsai1202/humanizer-zh-tw/text-watermark-cleaner-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.
<a href="https://agentmods.dev/skills/kevintsai1202/humanizer-zh-tw/text-watermark-cleaner-zh-tw"><img src="https://agentmods.dev/badge/skills/kevintsai1202/humanizer-zh-tw/text-watermark-cleaner-zh-tw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00162 | $0.02518 |
| Opus 5 | $0.00081 | $0.01259 |
| Sonnet 5 | $0.00032 | $0.00504 |
| Haiku 4.5 | $0.00016 | $0.00252 |
Grade A, and why
text-watermark-cleaner-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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文字浮水印清理（繁體中文）
工作邊界
只處理使用者擁有或獲授權的內容。把結果描述為「清理可驗證的文字載體」或「降低統計相似度」，不可宣稱內容已證明為人類撰寫、不可偵測或已破解 Claude 的私有演算法。
文字型標記分成兩層：
- Layer A：確定性文字衛生處理。檢查並清理高可信的不可見 Unicode、zero-width、tag characters、異形空白與部分 homoglyph。這一層可用前後統計驗證。
- Layer B：統計式標記降低。透過改變 token、詞序、連接詞、句界與句長來改寫。這不是解碼器；沒有 vendor detector 或相同 key/config 時，不能證明標記已移除。
不要把「去 AI 味」和「去文字浮水印」當成同一個動作。只有使用者明確要求浮水印或 provenance 清理時才執行本 skill；單純要求文字更自然時，使用 humanizer-zh-tw。
模式選擇
- inspect：只檢查並報告，不修改內容。
- layer-a：只做不可見文字清理，預設保守模式。
- layer-b：只做一次統計式改寫；需明確同意可能的語意與語氣漂移。
- full：
inspect → Layer A → Layer B（可選）→ Layer A → after inspect。
如果使用者同時要求去 AI 味與去浮水印，採用：
保護非 prose 區段 → inspect → Layer A → humanizer-zh-tw → 可選 Layer B → Layer A → after inspect
執行流程
1. 先分類與保護內容
先確認輸入是貼上文字、.txt、.md 還是 .html。在任何改寫前，保護下列內容，除非使用者明確要求修改：
- Markdown fenced code、inline code、HTML tag、attribute、script、style。
- URL、檔案路徑、API 名稱、變數名、錯誤碼、版本號與其他技術識別字。
- 數字、日期、專有名詞、引用、參考文獻、法律／學術／平台必要揭露。
- 使用者要求逐字保留的句子。
不要把 DOCX、PDF、圖片、音訊、影片或 ZIP/Office 容器當成純文字讀寫。這些檔案需要另外的容器或 metadata 工具；否則可能破壞二進位內容。
2. Inspect first
本技能優先使用內附的本地 deterministic scripts；它們是從 guillaumemeyer/watermarks-remover 的 service/scripts 擷取，並保留上游 MIT 授權。Windows PowerShell 執行方式：
$skillRoot = (Resolve-Path .\text-watermark-cleaner-zh-tw).Path
& "$skillRoot\scripts\run-text-watermark.ps1" `
-Mode Inspect -InputPath .\article.md -Json
需要較嚴格的檢查時才加上 -Aggressive 或 -StripEmojiGlue。若要同時取得統計式報告，可加 -Stylometry；這是分析訊號，不是 Claude 官方 detector。
若部署環境提供相容的 watermarks-remover HTTP service，也可先檢查：
GET $WATERMARKS_SERVICE_URL/health
GET $WATERMARKS_SERVICE_URL/capabilities
POST $WATERMARKS_SERVICE_URL/inspect
服務不可達時，不要假裝完成服務端清理；可使用本地腳本完成 Layer A，並在報告中分別標示「本地腳本已驗證」與「服務端未驗證」。聊天中的文字沒有可保證的 post-send Unicode filter；只能進行受保護的模型內處理，並在報告中標示限制。
3. 執行 Layer A
使用內附 scripts/run-text-watermark.ps1 -Mode Clean、服務的 /clean 或等效 deterministic cleaner，並保留原檔，預設產生 *.cleaned.*。本地入口範例：
What ships with it
10 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.
- agents/openai.yaml 307 B
- references/chinese-text.md 1.7 KB
- scripts/clean_text.py 3.0 KB runs code
- scripts/common.py 17 KB runs code
- scripts/inspect_text.py 2.6 KB runs code
- scripts/LICENSE-watermarks-remover.txt 1.1 KB
- scripts/run-text-watermark.ps1 2.3 KB runs code
- scripts/score_stylometry.py 16 KB runs code
- scripts/text_unicode.py 25 KB runs code
- scripts/verify-text-watermark.ps1 4.7 KB runs code
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.
- 12d ago First seen · 139 lines · 162 tokens per session scan A 4d7aeec2ac1d
text-watermark-cleaner-zh-tw is a skill published in the GitHub repository kevintsai1202/Humanizer-zh-TW (839 stars, last pushed 17d ago), licensed MIT. It adds 162 tokens to every session and 2,518 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…