tophant-clawvault-mask-project

Mask company names, project amounts, and person names in local documents before AI analysis.

1.1k|38|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/tophant-ai/ClawVault --skill tophant-clawvault-mask-project
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tophant-clawvault-mask-project
Source: https://github.com/tophant-ai/ClawVault/tree/main/skills/tophant-clawvault-mask-project
Command: npx skills add https://github.com/tophant-ai/ClawVault --skill tophant-clawvault-mask-project

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sharing company project documents with AI models risks exposing sensitive business information such as client company names, contract amounts, and contact persons. This Skill desensitizes local documents with non-reversible numbered placeholders before any AI analysis takes place.

Core Features & Use Cases

  • Regex-Based Masking: Detects Chinese and English company names, project amounts, and contextual person names using a configurable JSON policy.
  • Non-Reversible Placeholders: Replaces matched values with numbered placeholders like [mask_1] without creating any restore mapping, and never outputs original matched values.
  • Custom Policies: Generate the default policy with generate-policy, save it as JSON, and load custom policies for mask-file runs.
  • Use Case: Before asking an AI to analyze project.txt containing client names and contract amounts, run the mask-file command and analyze only the returned sanitized_content or the separate output file.

Quick Start

Ask the AI to use ClawVault to check and mask the local file project.txt first, then analyze only the sanitized content it returns.

Frequently Asked Questions about tophant-clawvault-mask-project

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I mask sensitive data in documents before AI analysis?

Run the mask-file command with the document path, for example mask-file project.txt. The skill returns JSON containing sanitized_content where company names, amounts, and person names are replaced with numbered placeholders like [mask_1].

What sensitive content does document masking detect?

The default policy detects Chinese and English company names with business suffixes, project and contract amounts after labels like Budget or 项目金额, and person names after labels like Contact or 项目经理. Label text is preserved while only the value is masked.

Can masked placeholders be restored to original values?

No, the numbered placeholders such as [mask_1] are non-reversible and no restore mapping is created. The original file is never modified, so the original values remain only in your source document.

Does document masking work with Chinese text?

Yes, the default policy includes rules for Chinese company suffixes like 有限公司, Chinese amount expressions like 三百万元, and Chinese role labels like 项目经理 and 联系人. Both Chinese and English documents are supported.

Why does masking return a no-match warning?

The warning appears when no regex rule matches the document, meaning detections is zero and the original content is returned unchanged. It does not guarantee the file is safe, so you should review the output before sharing it.

What are the limitations of regex-based document masking?

Regex-based masking can miss sensitive content that does not match the defined patterns, such as unusual name formats or unlabeled values. It is a cooperative local tool without a hard file sandbox, so run it only on user-approved files.