Measures whether a Claude Code plugin actually works by running triggering evals (does the model pick the skill?) and output evals (does it produce correct results?). Use when you need to evaluate a plugin, run skill activation testing, set up an eval harness, measure plugin quality, write trigger rate tests, check output quality, compare plugin iterations, or iterate on a SKILL description based
Receba novas skills de Desenvolvimento toda segunda
1 email curto, só com as skills novas de Desenvolvimento. 4 minutos de leitura, sem spam, cancela com 1 clique.
Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.
Ler descrição completaRecolher descrição
Plugin Evaluation
If you haven't measured the activation rate and the output pass rate, you have not evaluated your plugin. Shipping a skill without evals is shipping an untested function. This skill teaches the two eval types, the harness, and the iteration loop.
Primary source: Anthropic's skill-creator (/Users/vbezdek/Work/skillstack/skill-foundry — skills/skill-foundry/scripts/run_loop.py and README). This skill adapts that pattern and adds an offline smoke mode so you can valida
[Description truncada. Veja o README completo no GitHub.]
