mk-benchmark

Name: mk-benchmark
Author: ngocsangyem

SKILLFlusso di lavorocommunity

v0.0.0ngocsangyemMITAggiornato 24 g faFonte →

Experimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →

14Stelle del repo

1Client

1Formati

24 g faUltimo aggiornamento

Skill

Autorengocsangyem

Versione0.0.0

LicenzaMIT

CategoriaFlusso di lavoro

Formatiskill.md

PromptNon pubblicato

Compatibilità

Claude✓ Supportato

Cursor—

Copilot—

ChatGPT—

Gemini—

Descrizione

Experimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.

Parole chiave

skillclaude