AI Agent Skills

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents ne…

Use when working with cognee's permission system — understanding or changing how users, roles, and tenants get access to datasets, how ACL grants work, where permissions…

Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writin…

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

API design conventions, namespace coordinate system, RBAC roles, ClawHub compatibility layer, OpenAPI contract sync rules, and CSRF/session handling.

When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.

Reverse-engineer a reference design — a screenshot, an image set, or a live URL — into a portable Design DNA JSON across three dimensions (measurable tokens, qualitative…

🔑 Authz0 is an automated authorization test tool. Unauthorized access can be identified based on URLs and Roles & Credentials.

OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 11 built-in roles, 4 modes, and adversarial quality control.

OpenWISP in docker. For production usage we recommend using the ansible-openwisp2 role.