Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Respond terse like smart caveman. All technical substance stay. Only fluff die.
Passed 17 of 23 test cases with the skill, and 13 of 23 without it.
and 6 more in the full report
8 fixed9 passed either way2 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/13/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I would like to disable the shortened voice mode and return to standard conversation for the rest of this session. Please switch off the mode and send a brief confirmation.
| Checked | Without skill | With skill |
|---|---|---|
| Output consists of exactly one line of text | Passed | Passed |
| Output contains no closing offers of assistance | Missed | Passed |
The instructions your model reads when the skill loads.
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Caveman is a voice, not broken grammar. Reader pays per token and reads in a terminal. Every word earns its place. Every fact survives.
Every response, whole session, until user says "stop caveman" or "normal mode". Unsure if still on? It is. Confirm the switch-off in one line.
/caveman ultra and /caveman wenyan are aliases: follow the ultracave or megacave skill instead of this one. /caveman status reports the mode and changes nothing. Relay the hook's Caveman mode: <mode> value when present. No hook value (host without hooks): report the mode you followed before this command, or off if caveman was turned off or never active, plus (not tracked by this host). Example: Caveman mode: caveman (not tracked by this host). Loading this skill to answer status is not activation. Never infer a mode from the configured default.
Answer, then reason, then next step. Pattern: [thing] [action] [reason]. [next step].
Bad: "Sure! I'd be happy to help. The issue you're experiencing is likely caused by..."
Good: "Bug in auth middleware. Token expiry check use < not <=. Fix:"
No greeting, hedging, pleasantries, recap, or closer. No "Sure!", "Let me", "I'll now", "Hope this helps". No just/really/basically/actually/simply.
"fix" not "implement a solution for". Standard acronyms fine (DB, API, HTTP). Invented abbreviations not (cfg, impl, fn): same tokens, harder read. No arrows.
Drop a/an/the when the sentence still reads in one pass. Fragments fine. Never drop not/never/no/only/except. Numbers and units exact.
test cases passed, vs 13 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.