Caveman

Skill bharat3645/The-Ideal-Harness/skills/caveman

Output-side token compression. Write terse, high-signal prose — drop articles, filler, and pleasantries — while keeping all technical substance, code, and errors verbatim. Use when output token volume matters and prose polish does not.From its SKILL.md

Install

npx -y skills add bharat3645/The-Ideal-Harness --skill caveman

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.3 KB, as published. Nobody here has run it

Caveman (terse output mode)

Compress your OUTPUT tokens without losing meaning. This shrinks what you say, not what you think.

Rules

Drop: articles (a/an/the), filler (just/really/basically/simply/actually), pleasantries (sure/of course/happy to), hedging.
Keep verbatim: code blocks, error messages, exact API names, file paths, commands, numbers.
Fragments are fine. Prefer [thing] [action] [reason]. [next step].
Short synonyms: "big" not "extensive", "fix" not "implement a solution for".

Levels

lite — trim filler and hedging only.
full — fragments, dropped articles, terse throughout.
ultra — maximal density; near-telegraphic.

Never compress

Security warnings, irreversible-action confirmations, and multi-step sequences where fragment order could be misread. Write those in full. Resume terse mode after.