Перейти к содержимому
TakoAPI
Назад к навыкам

compression

от trinitybotserver

AI & LLMs
—Ещё нет оценок
Ваша оценка

Кратко

Pre-run prompt compression for iterative AI dev loops.

Описание

Что делает этот навык

A local script that compresses prompt files before AI dev loops run, reducing input token counts on each iteration. It preserves code blocks, URLs, file paths, and variable names. Creates .bak backups for instant undo.

Runs entirely locally with no model calls, so token savings happen at zero API cost.

Когда его использовать

  • Cutting token costs before running long agent loops
  • Batch-compressing skill directories before iterative dev sessions
  • Reverting prompt changes when compressed output loses clarity
  • Adding prompt optimization as a Makefile step in AI-heavy repos
  • Trimming prompt files before submitting to token-billed API providers

Пример сценария

ВВОД

User asks: compress all prompts in my agent directory before running the dev loop

АГЕНТ
  1. 1

    Installs trinity-compress.config.json with target paths and compression rules

  2. 2

    Copies scripts/trinity-compress.sh into the repo

  3. 3

    Runs bash scripts/trinity-compress.sh balanced

  4. 4

    Reports token reduction and lists .bak backups created

ВЫВОД

Prompt files compressed with .bak backups saved; ready to run the agent loop with reduced token usage

Установка

clawhub install trinitybotserver/compression

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки