caveman

caveman is a System prompts & personas skill for AI agents, published by DietrichGebert in the ponytail repository on GitHub. Skillspace rates caveman D (55/100) and it passed the safety scan; a judge model has also reviewed it.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Grade
D
Quality
55 / 100
Safety
Passed
GitHub stars
137,112

Placed #2 of 6 in the judged category final for System prompts & personas.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubDietrichGebert/ponytail

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.

Judge review

Placed #2 of 6 in the judged category final for System prompts & personas.

  • Trigger6565
  • Instructions9090
  • Specificity9090
  • Safety8888
  • Disclosure5555
  • Maintenance7070
Rich terseness-persona rules with concrete before/after examples across five intensity levels and a genuine clarity carve-out for warnings and irreversible actions.

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in System prompts & personas

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.