browse-work-chat

Masks customer names and HR info in DingTalk workgroup chats and replies.

13|3|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/Theodora-Y/MaskClaw --skill browse-work-chat
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse-work-chat
Source: https://github.com/Theodora-Y/MaskClaw/tree/main/user_skills/demo_UserC/browse-work-chat/v1.0.0
Command: npx skills add https://github.com/Theodora-Y/MaskClaw --skill browse-work-chat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Masking sensitive fields such as customer names and internal HR details when browsing and replying in DingTalk workgroups.

Core Features & Use Cases

  • Mask customer names and internal personnel information in chat messages during live conversations.
  • Apply a policy-driven rule to automatically replace sensitive data with a placeholder.
  • Use cases include corporate team chats where privacy must be preserved without compromising workflow.

Quick Start

Tell the AI to apply masking to customer names and internal HR information while browsing and replying in a DingTalk workgroup.

Frequently Asked Questions about browse-work-chat

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

FAQPage Schema
How do I mask sensitive data in DingTalk workgroup chats?

You can mask customer names and HR information in DingTalk chats by applying a rule-based policy that automatically replaces sensitive fields with a configurable placeholder during live conversations.

What is rule-based data masking for enterprise messaging?

Rule-based data masking is a policy-driven approach that replaces sensitive personnel fields with a placeholder in workgroup messages, preventing data leakage while preserving team communication workflows.

Can I configure custom rules to mask specific personnel information in DingTalk?

Yes, you can configure custom rules to mask specific personnel information in DingTalk by defining a mask-based policy that replaces targeted sensitive fields with a designated placeholder.

Does this masking approach work when replying to mentions in DingTalk discussions?

Yes, the masking approach works when replying to mentions in DingTalk discussions by applying the placeholder policy to messages containing sensitive personnel data, preserving privacy across workgroup interactions.

What are the limitations of using a placeholder policy for chat data privacy?

A limitation of using a placeholder policy for chat data privacy is that it operates strictly on configured rules, masking only explicitly defined sensitive fields rather than detecting contextually sensitive information.