distil-pii-redactor

Redacts personally identifiable information from user text via a local model.

126|11|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/HybridAIOne/hybridclaw --skill distil-pii-redactor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: distil-pii-redactor
Source: https://github.com/HybridAIOne/hybridclaw/tree/main/skills/distil-pii-redactor
Command: npx skills add https://github.com/HybridAIOne/hybridclaw --skill distil-pii-redactor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, bash, curl, llama-server, and includes scripts (resource) components.

What problem does it solve?

This Skill prevents sensitive personal data from being exposed by redacting personally identifiable information before it reaches logs, chat, or any downstream processing.

Core Features & Use Cases

  • Local Distil-PII redaction: Uses a local Distil-PII GGUF model served via llama-server to produce a sanitized version of user-provided text.
  • Entity-aware replacement: Replaces common PII types with standardized tokens (for example, [PERSON], [EMAIL], [PHONE], [SSN], [ADDRESS]).
  • Privacy-first workflow: Rejects non-loopback server URLs by default and supports “redacted output only” behavior to minimize sensitive exposure.

Quick Start

Ask HybridClaw to redact the PII in the provided text using the distil-pii-redactor skill.

Frequently Asked Questions about distil-pii-redactor

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

FAQPage Schema
How do I redact PII from text locally before sending it to external systems?

To redact PII locally, you can use a local Distil-PII model served via llama-server to sanitize text and replace sensitive data with standardized tokens before routing it to external systems or storage.

What is the best way to sanitize personally identifiable information in chat logs and document snippets?

The best way to sanitize PII in chat logs and document snippets is using entity-aware replacement, which substitutes personal data with standardized tokens like [PERSON], [EMAIL], and [PHONE] to prevent sensitive data exposure.

Does local PII redaction with llama-server require an internet connection?

Local PII redaction with llama-server does not require an internet connection because it runs the Distil-PII model locally and rejects non-loopback server URLs by default to maintain a privacy-first workflow.

Can I use Distil-PII to redact text before processing it with an external LLM?

Yes, you can use Distil-PII as a pre-processing step to redact text before interacting with external LLMs, ensuring that sensitive personally identifiable information is replaced with tokens and never exposed.

What types of personally identifiable information can a local redaction model detect and replace?

A local redaction model can detect and replace common PII types such as names, emails, phone numbers, SSNs, and addresses, substituting them with standardized entity tokens like [ADDRESS] and [SSN].

Why does my local PII redaction model refuse to connect to my custom server URL?

Your local PII redaction model refuses custom server URLs because it enforces a privacy-first workflow that rejects non-loopback server URLs by default unless they are explicitly allowed by the user.