lab-toolsresearch
calibrate
Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs targets against them, and measures recall, precision, and confidence calibration — revealing whether self-reported confidence scores track actual quality.
maintainer
Borda
Atualizado 4/10/2026
Estrelas
8
Forks
1
quick start
Installation and usage
Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs targets against them, and measures recall, precision, and confidence calibration — revealing whether self-reported confidence scores track actual quality.
Instalação
$ install --globalskills.sh
Uso
Depois de instalar, você pode usar esta skill executando o seguinte comando no terminal:
skills use calibrate