Minimizes token usage in files while preserving their complete semantic meaning for AI consumption.
Provides expert guidance for compacting files to reduce AI token consumption without losing semantic meaning. This skill is useful when you need to minimize, compact, or reduce the token count of text or code files. It follows a clear workflow to analyze the file, apply specific compaction guidelines that prioritize information density over human readability, and report on the resulting token savings.
Key Features
01Preserves critical information like frontmatter, links, key facts, and code logic.
02Aggressively removes redundancy, filler words, and verbose explanations.
03Includes a workflow to measure and report token savings after compaction.
04Simplifies markdown and code blocks, removing decorative formatting and redundant examples.
05Employs a concise, information-dense writing style optimized for AI consumption.
060 GitHub stars
Use Cases
01Reducing the size of documentation before including it in a prompt for an AI model.
02Minimizing the token count of context files to fit within an AI's context window.
03Preparing large text files for analysis or summarization by language models to lower costs.
