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

54fff6b
5adf3d1
chore(deps): pin SkillSpector to v2.13.3 (#292)
Narendran Raghavan committed 18 days ago
765ab5e
feat: support Python 3.14 (#311)
Christopher Kevin committed 19 days ago
3633954
6d5d57f
1e147a8
ffbbd6b
Revert "chore(release): prepare v0.7.0" (#302)
Christopher Kevin committed 21 days ago
a61e1f3
c8e26ce
chore(release): prepare v0.7.0 (#262)
Christopher Kevin committed 22 days ago
c8ccd9e
fix: address review findings from #249 and #250 (#260)
Narendran Raghavan committed 21 days ago
63d2b31
ci: run main test jobs in parallel (-n auto) (#261)
Narendran Raghavan committed 22 days ago
d581884
fad61ed
239e321
74cb19b
b63288c
34d84cd
Compose private inventory, audits and catalog checks (#257)
Narendran Raghavan committed 22 days ago
aca88a9
Add opt-in Unicode character facts for Tier 3 judges (#242)
Narendran Raghavan committed 22 days ago
58953e9
abdf333
d229da7
b3a1706