Skillget

genpark-prompt-compression-token-pruning-skill

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Gecti
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

GenPark AI Agent Skill - Task-aware prompt token pruning using information density scoring and semantic stop-phrase elimination to compress long context prompts up to 60%.

README.md

GenPark AI Agent Skill - Prompt Compression Token Pruner

A pure Python standard library skill implementing task-aware prompt token compression (LLMLingua style). Prunes linguistic stop-phrases and syntactic boilerplate while preserving critical entities, numerical constraints, and imperative instructions.

Architecture

graph TD
    A[Verbose Context / Prompt] --> B[Token Information Density Scorer]
    B --> C[Entities, Numbers, Content Tokens vs Stopwords]
    C --> D[Top-K Information Retainer]
    D --> E[Chronological Sequence Reassembly]
    E --> F[Dense Compressed Prompt: ~50% Token Reduction]

Features

  • Preserves Key Information: Retains entities, numbers, and core intent.
  • Up to 60% Token Savings: Dramatically cuts token costs and latency.
  • Zero Pip Dependencies: Standard Library Only.

Citations & Ecosystem

Yorumlar (0)

Sonuc bulunamadi