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

f878f99
9e34dd4
fix(tier3): show which Tier 3 source checks failed (#290)
Narendran Raghavan committed 17 days ago
d69c438
55ed08e
Add private MCP execution proof and behavior signals (#321)
Narendran Raghavan committed 17 days ago
d31f1a4
847bdb4
46a8cf2
fix(ci): require Semgrep in scanner subprocesses (#324)
Christopher Kevin committed 18 days ago
e4cda13
Set up Tier 1 scanners on first use and add --skip (#318)
Christopher Kevin committed 18 days ago
a705bb6
chore(release): reconcile published 0.7.0 metadata (#314)
Christopher Kevin committed 18 days ago
f23a6f6
Show per-case Tier 3 results and a "what to fix" list (#316)
Christopher Kevin committed 18 days ago
2951548
Offer to install a missing agent CLI in local mode (#317)
Christopher Kevin committed 18 days ago
58e617c
fix(docs): render README images in PyPI descriptions (#323)
Christopher Kevin committed 18 days ago
7696c71
aba2fa1
6e3c7f4
bfd477b