The Agent Skills Directory

[SAFE]: The skill instructions promote secure API design principles, such as adopting RFC 9457 for standardized error envelopes, using cursor-based pagination to avoid performance degradation, and implementing strict HTTP status code mapping. No patterns of prompt injection, data exfiltration, or obfuscation were detected.\n- [COMMAND_EXECUTION]: The skill includes a utility script scripts/verify.sh that performs read-only structural checks on OpenAPI documents. It utilizes standard command-line tools including grep, jq, and python3 to lint specifications for design anti-patterns. The script uses yaml.safe_load for parsing YAML content, ensuring secure handling of local specification files without risk of code injection or execution.

api-design