pi-jev-compaction (Wang-auspicious)

Name: pi-jev-compaction (Wang-auspicious)
Availability: InStock
Author: Wang-auspicious

Jev-powered: Extractive context compaction for Pi that keeps selected original tool records instead of generating a summary.

High Quality

New

Join 0+ developers using this skill

command

AI & Machine Learning

intermediate

0 installs

4/5 quality

View Source

Last updated: September 23, 2026

AI Skill Market Insights

Real data. Real impact.

Popularity

Rising

Emerging

Active Users

Developers

Quick Start

Install Command

git clone https://github.com/Wang-auspicious/pi-jev-compaction.git

TEAR & SHARE

2-3hrs/WK

RISING

0.0K+ USING

pi-jev-compaction (Wang-auspicious)

Extractive context compaction for Pi that keeps selected original tool records instead of generating a summary.

Where Jev makes the decision

Jev judges complete read-only tool pairs; local code removes those rated unnecessary.

Why it matters

Preserves original evidence and Pi’s recent-message boundary.

Claims & evidence

Depends on Pi’s compaction interface and version; extractive filtering can still omit useful content. Not run here.

About Jev

Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.

Source: Wang-auspicious/pi-jev-compaction — 1 stars, MIT. Listed by Awesome Jev.

pi-jev-compaction (Wang-auspicious)

AI Skill Market Insights

Quick Start

Install Command

TEAR & SHARE

Tags

Multi-Agent Patterns

Be Part of the 0+ Developer Community

pi-jev-compaction (Wang-auspicious)

Where Jev makes the decision

Why it matters

Claims & evidence

About Jev

License

Memory Systems Design

Context Degradation Detection

brainstorming

writing-skills

Channels

Learn

Compare

Company

Agents