The Agent Skills Directory

[SAFE]: The skill contains instructional content only and does not include any executable scripts, automated tool configurations, or command execution patterns.
[EXTERNAL_DOWNLOADS]: The skill references established testing and documentation resources from trusted services.
Links to Google's Rich Results Test (search.google.com).
Links to the official Schema Markup Validator (validator.schema.org).
References schema definitions from schema.org.
[INDIRECT_PROMPT_INJECTION]: The skill initiates the ingestion of project-specific metadata by instructing the agent to analyze local context files.
Ingestion points: Site structure and hierarchy information is read from .claude/project-context.md or .cursor/project-context.md as specified in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore instructions embedded within the project context files are provided.
Capability inventory: The skill does not define or invoke any sensitive capabilities such as network operations or shell execution.
Sanitization: No sanitization is performed on the content ingested from the project context files.

breadcrumb-generator