Ai Tool Compliance

Automated compliance gatekeeper for internal AI tools that checks 11 P0 rules across auth, security, cost tracking, and logging before you ship. Runs three ways: quick grep scans, full verification with evidence collection, or guided fix mode with improvement loops. The scoring is quantitative (Security 40pts, Auth 25pts, Cost 20pts, Logging 15pts) and any P0 failure blocks deployment regardless of total score. It generates RBAC matrices, gateway boilerplate, and log schemas on init, which saves setup time but locks you into their five-role model. The role-based approval workflow with 20 checkpoints feels heavy for small teams, though the CI/CD bash integration is straightforward. Best for orgs that need formal compliance guardrails and can absorb the initial scaffolding overhead.

Install to Claude Code

npx -y skills add supercent-io/skills-template --skill ai-tool-compliance --agent claude-code