The Agent Skills Directory

[SAFE]: The skill is entirely instructional and serves as a reference guide for software architecture best practices. It does not contain executable code that could perform malicious actions.
[EXTERNAL_DOWNLOADS]: The documentation mentions standard industry tools such as openapi-typescript, datamodel-code-generator, and graphql-codegen within code examples. These are well-known development utilities and are listed purely for educational purposes in the context of API-first design.
[DATA_EXFILTRATION]: No evidence of unauthorized data access or external transmission. Network-related examples (like fetch or Stripe API integration) are provided as architectural templates and are not invoked by the skill itself.
[PROMPT_INJECTION]: The skill's instructions are consistent with its stated purpose. There are no attempts to override agent safety guidelines, bypass filters, or hide malicious instructions in metadata.

modern-architecture