# Semantic Compression

Rewrites verbose prose into dense telegraphic text while keeping its precision.

- Repository: https://github.com/can1357/oh-my-pi (37428 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add can1357/oh-my-pi --skill semantic-compression -g -a claude-code -y`
Codex: `npx skills add can1357/oh-my-pi --skill semantic-compression -g -a codex -y`
Cursor: `npx skills add can1357/oh-my-pi --skill semantic-compression -g -a cursor -y`
Gemini CLI: `npx skills add can1357/oh-my-pi --skill semantic-compression -g -a gemini-cli -y`

## Description

Re-encode verbose prose into a dense telegraphic register, punctuation as connectives, label frames, verbless assertions, without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making documentation token-efficient for LLM input; or rewriting text in compressed notation.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Semantic Compression

Compression is **re-encoding, not word deletion**. Filtering function words out of an English sentence leaves a damaged English sentence (`System design: efficient process incoming data, multiple sources`). Instead re-frame each claim in a register whose grammar is punctuation and layout, then the function words have no work left and drop out on their own.

Target texts are load-bearing: tool descriptions, system prompts, skills. A model executes them cold, with no author present to disambiguate. Compression that forces a guess is a bug, not a saving.

## Procedure

The rest: https://github.com/can1357/oh-my-pi/blob/HEAD/.omp/skills/semantic-compression/SKILL.md