Comparison
Caveman vs SkillEvaluator
Caveman has more GitHub stars (113,046 vs 570). Caveman was updated more recently (last commit 4d ago). Data comes straight from GitHub and refreshes daily.
Caveman
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
$
/plugin marketplace add JuliusBrussee/caveman
SkillEvaluator
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that…
$
git clone https://github.com/NVIDIA/SkillEvaluator| Metric | Caveman | SkillEvaluator |
|---|---|---|
| Type | Agent skill | Agent skill |
| GitHub stars | 113,046 | 570 |
| Stars, last 7 days | +647 | n/a |
| Forks | 6,541 | 66 |
| Upvotes | 0 | 0 |
| Language | Go | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last commit | 4d ago | 4d ago |
| Created | Apr 2026 | Jun 2026 |
| Categories | AI & LLM tooling | Security, AI & LLM tooling, Frameworks & SDKs |