Skillget

genpark-context-window-chunk-compressor-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Pass
  • Code scan — Scanned 6 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Context window token compressor with semantic sentence saliency scoring and chunk compaction

README.md

genpark-context-window-chunk-compressor-skill

Agent Skill implementing Context Window Pruning & Semantic Saliency Compaction in 100% Python standard library.

Architectural Flow

flowchart TD
    Large["Full Context Window Document"] --> Split["Sentence Boundary Segmentation"]
    Query["Target User Query"] --> Scorer["Saliency Scorer (Term Overlap & Log Length Penalty)"]
    Split & Query --> Scorer
    Scorer --> Sorted["Ranked Sentence Candidates"]
    Sorted --> Knapsack["Budget Greedy Selection (max_chars)"]
    Knapsack --> Chrono["Chronological Re-ordering"]
    Chrono --> Comp["Compacted Context Buffer"]

Reviews (0)

No results found