Caveman
v1.0.2Ultra-compressed communication mode. Slash token usage ~75% by speaking like smart caveman while keeping technical accuracy. Use when user says "caveman mode...
⭐ 3· 800·3 current·3 all-time
byS K Aravind@skaravind
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (compress responses into 'caveman' style) align with SKILL.md and the repo content. The only mismatch: a benchmark script (benchmarks/run.py) uses the anthropic client and will consume API credentials if run, but the registry metadata lists no required environment variables or credentials. This is reasonable for an optional benchmark tool but is a minor documentation/metadata omission.
Instruction Scope
SKILL.md content limits scope to changing assistant output style (drop articles/fillers, preserve code and technical accuracy) and defines clear stop phrases. It does not instruct reading system files, harvesting credentials, or sending arbitrary data to external endpoints.
Install Mechanism
There is no install spec in the registry package (instruction-only skill). README suggests npx/marketplace install commands consistent with a user-installed skill. No downloads from untrusted URLs or archive extraction are present in the package data.
Credentials
The skill metadata declares no required environment variables, but benchmarks/run.py loads a .env.local (if present) and uses the anthropic client (which typically requires an API key in environment). This is expected for a local benchmark script but the metadata doesn't document it — verify before running the benchmark script locally if you have sensitive env vars in repo parent directories.
Persistence & Privilege
Skill does not request always:true and is user-invocable only. It does not modify other skills or system-wide agent settings. The benchmark script can write local result files only if executed by the user (no automatic persistence or elevated privileges requested).
Assessment
This skill is primarily an instruction prompt that makes the assistant answer tersely ('caveman' style). It's coherent and low-risk for general use. Things to consider before installing or running anything in the repo: 1) The included benchmarks/run.py calls the Anthropic client and will load .env.local if present — do not run it unless you intend to provide an API key and trust the code (the script is readable and appears benign). 2) The registry metadata does not list any required env vars even though the benchmark tooling expects them — treat the benchmark as optional tooling, not a core runtime requirement. 3) There is no network exfiltration or secret-access behavior in SKILL.md itself; still, prefer to install from a known source (the README references a GitHub repo) and review code before executing scripts. 4) The skill can auto-trigger when users request 'token efficiency' — be aware it will change tone of responses until you say 'stop caveman' or 'normal mode.'Like a lobster shell, security has layers — review code before you run it.
latestvk977b73y3f9bzx040hpg8jcd4d8487ck
License
MIT-0
Free to use, modify, and redistribute. No attribution required.