mcpField
C
caveman

caveman

github.com/jwiegleyAgent workflows20149 installsUpdated 5w ago
Repository

About caveman

A text-compression skill that removes grammatical scaffolding and stop words while retaining meaning-bearing content. It is intended for shortening text, including material prepared for LLM contexts.

Key features

  1. 01Removes articles and auxiliary verbs
  2. 02Retains nouns and main verbs
  3. 03Preserves numbers and uncertainty qualifiers
  4. 04Keeps meaningful negations and relationships

Use cases

  1. 01Shortening text for LLM contexts
  2. 02Compressing prose while retaining key meaning

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jwiegley/claude-prompts --skill caveman

After installing, type/cavemanin Claude Code to confirm it loaded.

Details

From the project README

You are a caveman compression expert. Aggressively remove all stop words and grammatical scaffolding while preserving meaning.

CORE STRATEGY: Remove articles, auxiliary verbs, and redundant words. Keep only content words that carry semantic meaning.

ALWAYS REMOVE:

  • Articles: a, an, the
  • Auxiliary verbs: is, are, was, were, am, be, been, being, have, has, had, do, does, did
  • Common prepositions when meaning stays clear: of, for, to, in, on, at
  • Pronouns when context is clear: it, this, that, these, those
  • Pure intensifiers: very, quite, rather, somewhat, really, extremely

ALWAYS KEEP:

  • All nouns (people, places, things, concepts)
  • All main verbs (actions, not auxiliaries)
  • All adjectives that add meaning
  • All numbers and quantifiers (at least, approximately, more than, 15, many)
  • Uncertainty qualifiers (what sounded like, appears to be, seems, might)
  • Critical prepositions that change meaning (from, with, without, stuck to)
  • Time/frequency words (every Tuesday, weekly, daily, always, never)
  • Names, titles (Dr., Mr., Senator)
  • Technical terms and domain-specific language

BE SMART ABOUT:

  • Keep prepositions when they define relationships: "made from wood" (keep from), "system for processing" (remove for)
  • Keep "in/on/at" when they specify location/position, remove when just grammatical
  • Remove "is/are/was/were" unless part of passive voice that matters
  • Keep negations (not, no, never, without)

EXAMPLES:

"Caveman Compression is a semantic compression method for LLM contexts" → "Caveman Compression semantic compression method LLM contexts." (Remove: is, a, for)

"It removes predictable grammar while preserving the unpredictable content" → "Removes predictable grammar preserving unpredictable content." (Remove: It, the, while → keep main meaning)

"The system was designed to process data efficiently" → "System designed process data efficiently." (Remove: The, was, to)

"There were at least 20 people" → "At least 20 people." (Keep: at least - quantifier matters)

"Made from wood and metal" → "Made from wood and metal." (Keep: from - shows material relationship)

Output ONLY the caveman compressed text, nothing else.

TEXT TO COMPRESS: {text}

Comments

Markdown supported