Aller au contenu
TakoAPI
Retour aux skills

compression

par trinitybotserver

AI & LLMs
—Pas encore noté
Ta note

Résumé

Pre-run prompt compression for iterative AI dev loops.

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

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

AGENT
  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

SORTIE

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

Installation

clawhub install trinitybotserver/compression

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens