Skip to content

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

Commits on main

8a851c6
ea147c1
e8f2a1d
fix(ci): use a neutral default validation policy (#334)
Christopher Kevin committed 15 days ago
03a7c22
61ca935
fix(tier3): honor --n-concurrent with --stop-on-pass (#275)
Narendran Raghavan committed 15 days ago
3ad2838
fix(tier2): allow contained directory aliases (#282)
Narendran Raghavan committed 16 days ago
fc900e0
feat(tier1): apply audited SkillSpector baselines (#300)
Narendran Raghavan committed 16 days ago
39d8901
9aa72f9
fix(license): parse SPDX license expressions (#295)
Narendran Raghavan committed 16 days ago
c61fa97
53329d6