The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx to run well-known API linting tools (@stoplight/spectral-cli and @redocly/cli) to validate generated OpenAPI specifications as part of the backend development workflow.
[EXTERNAL_DOWNLOADS]: The use of npx fetches the specified linting tools from the official NPM registry (npmjs.com) if they are not already installed locally. These are well-known services provided by established vendors.
[PROMPT_INJECTION]: The skill processes external design documents, which presents a surface for indirect prompt injection. This is an inherent part of the skill's primary purpose to translate high-level designs into backend architecture.
Ingestion points: Ingests content from system-design.md, ADRs, and PRD sections as specified in Step 1 of the Process in SKILL.md.
Boundary markers: None; the skill does not specify markers to isolate untrusted input from the rest of the prompt context.
Capability inventory: Executes shell commands via npx for contract validation as specified in Step 11 of the Process in SKILL.md.
Sanitization: None; the skill does not include steps to sanitize or validate the content of the input documents before processing.

backend-architecture