skills.rest
kochetkov-ma
kochetkov-maCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

text-optimizer

Apply 41 research-backed rules to compress text for LLM token efficiency.

30|2|Updated Jan 24, 2026
Search Tags:#documentation#prompt engineering#llm#token efficiency#compression#text optimization
One-click install
npx skills add https://github.com/kochetkov-ma/claude-brewcode --skill text-optimizer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-optimizer
Source: https://github.com/kochetkov-ma/claude-brewcode/tree/main/skills/text-optimizer
Command: npx skills add https://github.com/kochetkov-ma/claude-brewcode --skill text-optimizer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill optimizes text, prompts, and documentation to significantly reduce token count, leading to lower costs and faster responses from LLMs.

Core Features & Use Cases

  • Token Efficiency: Applies 41 research-backed rules to compress text by 20-40% without losing meaning.
  • Prompt Optimization: Improves the clarity and effectiveness of instructions for LLMs.
  • Documentation Compression: Reduces the size of documentation files for better handling by LLMs.
  • Use Case: Optimize your system prompt for a customer service agent to reduce API costs while maintaining or improving response quality.

Quick Start

Use the text-optimizer skill to optimize the file 'my-prompt.md'.

Frequently Asked Questions about text-optimizer

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

FAQPage Schema
How do I reduce token count in LLM prompts without losing meaning?▼

You can reduce LLM token counts by applying research-backed compression rules that remove redundancies and restructure text, cutting tokens by 20-40% without losing meaning.

What is the best way to compress documentation for LLM token efficiency?▼

The best way to compress documentation for LLM token efficiency is applying 41 optimization rules across six categories, using light, medium, or deep compression modes to reduce file size and API costs.

How does text optimization improve prompt engineering results?▼

Text optimization improves prompt engineering by applying compression rules that increase instruction clarity and reduce token waste, leading to better LLM response quality and lower API costs.

Can I use different compression levels for various prompt optimization use cases?▼

Yes, you can use light, medium, and deep compression modes for different use cases, ranging from simple text cleanup to aggressive restructuring of complex documentation for token efficiency.

Why does my LLM documentation consume so many tokens and cost so much in API calls?▼

Your documentation likely contains redundancies and verbose structures that inflate token counts. Applying 41 research-backed compression rules reduces tokens by 20-40%, directly lowering API costs.

When should I avoid deep compression mode for prompt optimization?▼

You should avoid deep compression mode when your text requires strict structural preservation, as it aggressively restructures content; use light or medium modes for simpler cleanup instead.

Related Skills

Explore More Content & Communication Skills→
sergicalsergical
1

semantic-compression

Compress text by removing grammatical scaffolding while preserving meaning for LLM inputs.

Community
Intermediate
thavirak-svaythavirak-svay
1

bmad-distillator

Convert source documents into lossless, token-efficient distillates for LLM consumption.

Community
Advanced
JaiminVadadoriyaJaiminVadadoriya
1

ai-system-testing

Test AI features including LLM prompts, tool calls, and nondeterministic outputs.

Community
Advanced
Kushal9889Kushal9889

context-compression

Compress AI agent session context to reduce token usage.

Community
Advanced