The Agent Skills Directory

[SAFE]: The skill implements a complex technical architect using a multi-agent system (orchestrator, stack-selection, infrastructure, schema, API, integration, scaling, and critic agents).
[SAFE]: Includes comprehensive security checklists (STRIDE, OWASP Top 10, and LLM Security) for the architectures it designs, ensuring that security is a core component of the generated blueprints.
[SAFE]: Included Bun utility scripts (e.g., manifest-sync.ts, scaffold-eval-loop.ts, append-loop-result.ts) are used for framework metadata management and use safe filesystem practices, including realpathSync and explicit checks to prevent operating on symlinks.
[SAFE]: No obfuscation, data exfiltration, or malicious prompt injection patterns were found in the instructions or the support scripts.
[SAFE]: Credentials and API keys appearing in the documentation (e.g., references/deployment-patterns.md) are clearly identified as examples or placeholders and are not active secrets.

architect-system