drawio-skill
Generate .drawio diagrams (flowcharts, UML, cloud/network, ER) from natural language with a vision self-check.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for drawio-skill, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A skill that produces draw.io XML for flowcharts, architecture, UML/sequence/class, ER, network topology, cloud architecture (from Terraform/K8s manifests), and mind maps, then exports PNG/SVG/PDF locally via the native draw.io desktop CLI. It bundles scripts/autolayout.py (needs Graphviz dot) and runs a vision-model self-check on rendered output. Surface: invokes the draw.io CLI binary and an optional Python auto-layout script on the host.
Key features and capabilities
- Rich shape vocabulary, swimlanes, custom styling
- Exports PNG/SVG/PDF/JPG via draw.io desktop CLI
- Optional Graphviz auto-layout script + vision self-check
Use cases
- Turn a Terraform/Kubernetes manifest into an architecture diagram
- Produce exportable UML/ER diagrams from a description