liuku-xianzei

Score knowledge items by claims, evidence, and application with contamination risk.

10|1|Updated May 4, 2026
One-click install
npx skills add https://github.com/isLinXu/under-one --skill liuku-xianzei
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: liuku-xianzei
Source: https://github.com/isLinXu/under-one/tree/main/underone/skills/liuku-xianzei
Command: npx skills add https://github.com/isLinXu/under-one --skill liuku-xianzei

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Helps transform messy, mixed-credibility information into structured knowledge units while preventing low-quality or potentially contaminated content from polluting long-term memory through risk scoring and quarantine/inheritance queues.

Core Features & Use Cases

  • Gradient knowledge digestion: Scores each item on core claim, evidence, and application using configurable keyword gradients plus semantic signals, then outputs a digestion report.
  • Freshness & review scheduling: Computes category-based freshness windows and generates a review (反刍) schedule to keep knowledge actionable over time.
  • Contamination risk control: Produces a contamination risk score and separates knowledge into inheritance_queue (safe to keep) and quarantine_queue (requires review).
  • Use case: You ingest research notes, blog posts, and forum discussions; this skill digests them into units with freshness days, decides which ones to inherit vs quarantine, and tells you when to review each unit.

Quick Start

Use the liuku-xianzei skill to digest an input file named info.json and produce digest_report.json with knowledge units, freshness windows, and review plans.

Frequently Asked Questions about liuku-xianzei

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

FAQPage Schema
How do I schedule review plans for ingested research notes?▼

To schedule review plans, this skill digests input knowledge items and generates structured units with freshness-days and expiry dates. It then creates a configurable re-review schedule to maintain long-term retention of your research notes.

What is contamination risk scoring in knowledge management?▼

Contamination risk scoring evaluates mixed-credibility information to prevent low-quality content from polluting memory. It calculates a risk score to separate knowledge into an inheritance queue for safe items and a quarantine queue for content requiring review.

How do I digest forum discussions into structured knowledge units?▼

You digest forum discussions by computing a gradient digestion score across core claims, evidence, and application. The skill applies information density and credibility weighting to transform messy inputs into structured knowledge units.

Can I use this skill to manage memory inheritance for blog posts?▼

Yes, you can manage memory inheritance for blog posts. The skill evaluates content credibility and contamination risk, routing safe knowledge units into an inheritance queue to support secure long-term memory inheritance.

What is the best way to prevent knowledge contamination from low-quality sources?▼

The best way to prevent knowledge contamination is applying contamination risk scoring to incoming information. This process identifies potentially polluted content and isolates it into a quarantine queue before it can enter long-term memory.

Why does my knowledge freshness scheduling expire important information?▼

Knowledge freshness scheduling expires information because it computes category-based freshness windows with expiry dates. This ensures outdated content is flagged for a re-review schedule, keeping your actionable knowledge base accurate over time.