Le descrizioni degli strumenti sono in inglese.

SkillEvaluator — scheda e storico dello strumento

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

Attivo

Fonte canonica ↗

Linguaggio
Python
Licenza
Apache-2.0
Creazione
Ultima attività
Argomenti
  • agent-evaluation
  • agent-security
  • agent-skills
  • agentic-ai
  • benchmark
  • claude-code
  • codex
  • evaluate
  • evaluation
  • security-scanner
  • skill-eval
  • skill-evals
  • skill-evaluation
  • skill-evaluator
  • skills

Installa git clone https://github.com/NVIDIA/SkillEvaluator ~/.claude/skills/SkillEvaluator

Misurazione attuale

363stelle GitHub+70 (+23.9 %)
crescita misurata

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Storico delle rilevazioni

90 giorni · 90 rilevazioni massime
DataValoreMetrica
363stelle GitHub
351stelle GitHub
348stelle GitHub
332stelle GitHub
326stelle GitHub
305stelle GitHub
293stelle GitHub
266stelle GitHub
245stelle GitHub
209stelle GitHub
168stelle GitHub
94stelle GitHub

Classificazioni

Ambiti
Tipo
Skill per agenti
Utilizzi