Pii Guard — AI skill for Claude Code
繁體中文(台灣)個人資料去識別化工具,讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local.
How to install Pii Guard
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open danyuchn/pii-guard and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Pii Guard does
繁體中文(台灣)個人資料去識別化工具,讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local.
Alternatives in AI
- Memmy Agent — 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memor 1k ★
- DontFeedTheAI — Transparent anonymization proxy for AI-assisted pentesting 654 ★
- Hol Guard — Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, M 485 ★
README
pii-guard
繁體中文(台灣)個人資料去識別化工具。把文件裡的個資換成可還原的代號,讓你能用雲端 AI 處理機敏文件,處理完再換回來。**偵測與還原全程在你自己的機器上跑。**
**English summary** — Reversible PII de-identification for Traditional Chinese (Taiwan) documents.
Most tools that strip PII before an LLM call are network gateways ([LiteLLM + Presidio](https://www.litellm.ai/), [PrivAiTe](https://github.com/crp4222/PrivAiTe), [AI Security Gateway](https://github.com/aisecuritygateway/aisecuritygateway)) and they work well. None of them handle Taiwanese PII: national ID and ARC numbers, 統一編號 business IDs, local phone formats, or Traditional Chinese personal and organisation names — which need CKIP's Chinese NER rather than an English model with the locale switched.
This fills that gap, and differs in one more way: it produces a **redacted file you can keep and hand to someone**, not a per-request proxy. Detection is Presidio + CKIP BERT + Taiwan regex; substitution and restoration are plain code, so restoration is exact. A bundled Claude Code skill runs the whole thing without letting the cloud agent read the original.
Everything below is in Traditional Chinese. Start at [安裝](#安裝).
為什麼還要一個?
處理「送進 LLM 之前先遮個資」的工具已經很多,而且做得好——但它們幾乎都是**網路層的 gateway**,攔在你的程式和模型供應商之間。
它們沒有處理的是**台灣的個資**:身分證與居留證字號、統一編號、本地電話格式,以及繁體中文的人名與組織名——後者需要中研院的 CKIP 中文 NER,不是英文模型換個語系就行。
這個專案補的是那一塊。另外還差一件事:**它產出的是一份你可以留存、可以交給別人的檔案**,不是逐次請求、用完即逝的代理。
實際輸出
下面是真的跑出來的,不是示意圖。輸入:
客戶:王小明
聯絡電話:0912345678
電子郵件:wang@example.com
身分證字號:A123456789
所屬公司:範例科技股份有限公司(統一編號 10000009)
通訊地址:臺北市中正區忠孝東路一段
案由:本季顧問合約續約,金額新臺幣 30 萬元,付款分兩期。
`uv run python -m pii_guard anonymize input.txt -o out.txt -m map.json` 之後:
客戶:
聯絡電話:
電子郵件:
身分證字號:
所屬公司:(統一編號 )
通訊地址:
案由:本季顧問合約續約,金額新臺幣 30 萬元,付款分兩期。
七項個資全部換成代號,**而金額、合約條款、日期原封不動**。這是刻意的——把那些也拿掉,文件就沒有送進 AI 的意義了。
對照表另存一份,AI 回答完之後用它換回真名,逐字精確。
人工補標介面
偵測層是機率性的,會有漏網,也會把不該遮的機構名遮掉。skill 因此提供一個在**你自己的瀏覽器**開的頁面:選取任何仍然裸露的文字就補遮(全文所有出現位置
Related Skills
Zh Tw Humanizer
繁體中文(台灣)去 AI 味 agent skill:59 種中文 AI 寫作特徵、兩岸用語在地化、簡轉繁修正、隱形字元清除,附機械檢查腳本與 eval 測試集。Traditional Chinese (Taiwan)
Bu Ketao
不客套 — Strip Chinese AI verbosity. 繁體中文 LLM 輸出壓縮規則集。~72% token compression, zero semantic loss.
Plain Language Skill
Rewrites convoluted AI output into plain language — separate rule sets for English and Traditional Chinese 把繞口
Humanizer Hk
去 AI 味 · Strip the AI tells out of written Chinese. Hong Kong Traditional. Claude Code skill + paste-anywhere
Datafog Python
Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM
Localvoxtral
Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and
Related Agents
Self Containment Reviewer
Read-only reviewer that verifies every committed-facing artifact in the diff is self-contained — fully underst
Lemonade Specialist
Lemonade Server and SDK specialist for local LLM on AMD hardware. Use PROACTIVELY for Lemonade setup, model ma
Delegate
Expert LLM delegation specialist that seamlessly connects to external language models including GPT-4, GPT-3.5