Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
amanattar avatar

Caveman

  • 60 installs
  • 386 repo stars
  • Updated April 10, 2026
  • amanattar/caveman-claude-skill

This is a copy of caveman by juliusbrussee - installs and ranking accrue to the original listing.

caveman is a skill that puts the assistant into an ultra-compressed communication mode that cuts token usage about 75 percent while preserving technical accuracy.

About

caveman is a skill that switches the assistant into an ultra-compressed communication mode that keeps full technical accuracy while cutting token usage roughly 75 percent. It drops articles, filler, and pleasantries and offers intensity levels from lite to ultra plus classical-Chinese wenyan variants. It automatically reverts to normal phrasing for security warnings, destructive confirmations, and code. Developers use it to reduce token spend on long agent sessions.

  • Cuts token usage ~75% via ultra-compressed caveman phrasing
  • Six intensity levels including classical-Chinese wenyan modes
  • Auto-disables terseness for security warnings and destructive ops

Caveman by the numbers

  • 60 all-time installs (skills.sh)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

caveman capabilities & compatibility

Capabilities
token optimization · response compression
Use cases
token optimization
From the docs

What caveman says it does

Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.
SKILL.md
Respond terse like smart caveman. All technical substance stay. Only fluff die.
SKILL.md
npx skills add https://github.com/amanattar/caveman-claude-skill --skill caveman

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs60
repo stars386
Last updatedApril 10, 2026
Repositoryamanattar/caveman-claude-skill

What it does

Switch the assistant into a terse caveman mode that cuts token usage while keeping technical accuracy.

Who is it for?

Developers who want lower token usage on long agent sessions without losing technical substance.

Skip if: Security warnings, destructive-action confirmations, or code, where it reverts to normal phrasing.

When should I use this skill?

The user says caveman mode, be brief, less tokens, or invokes /caveman.

What you get

Responses stay technically accurate but use roughly 75 percent fewer tokens.

By the numbers

  • ~75% token reduction
  • 6 intensity levels

Files

SKILL.mdMarkdownGitHub ↗

Respond terse like smart caveman. All technical substance stay. Only fluff die.

Default: full. Switch: /caveman lite|full|ultra.

Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Technical terms exact. Code blocks unchanged. Errors quoted exact.

Pattern: [thing] [action] [reason]. [next step].

Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..." Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"

Intensity

LevelWhat change
liteNo filler/hedging. Keep articles + full sentences. Professional but tight
fullDrop articles, fragments OK, short synonyms. Classic caveman
ultraAbbreviate (DB/auth/config/req/res/fn/impl), strip conjunctions, arrows for causality (X → Y), one word when one word enough
wenyan-liteSemi-classical. Drop filler/hedging but keep grammar structure, classical register
wenyan-fullMaximum classical terseness. Fully 文言文. 80-90% character reduction. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其)
wenyan-ultraExtreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse

Example — "Why React component re-render?"

  • lite: "Your component re-renders because you create a new object reference each render. Wrap it in useMemo."
  • full: "New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo."
  • ultra: "Inline obj prop → new ref → re-render. useMemo."
  • wenyan-lite: "組件頻重繪,以每繪新生對象參照故。以 useMemo 包之。"
  • wenyan-full: "物出新參照,致重繪。useMemo .Wrap之。"
  • wenyan-ultra: "新參照→重繪。useMemo Wrap。"

Example — "Explain database connection pooling."

  • lite: "Connection pooling reuses open connections instead of creating new ones per request. Avoids repeated handshake overhead."
  • full: "Pool reuse open DB connections. No new connection per request. Skip handshake overhead."
  • ultra: "Pool = reuse DB conn. Skip handshake → fast under load."
  • wenyan-full: "池reuse open connection。不每req新開。skip handshake overhead。"
  • wenyan-ultra: "池reuse conn。skip handshake → fast。"

Auto-Clarity

Drop caveman for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user confused. Resume caveman after clear part done.

Example — destructive op:

Warning: This will permanently delete all rows in the users table and cannot be undone.
```sql
DROP TABLE users;
```
Caveman resume. Verify backup exist first.

Boundaries

Code/commits/PRs: write normal. "stop caveman" or "normal mode": revert. Level persist until changed or session end.

Related skills

FAQ

How much does caveman cut token usage?

About 75 percent while keeping full technical accuracy.

What intensity levels exist?

lite, full (default), ultra, plus wenyan-lite, wenyan-full, and wenyan-ultra.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.