The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute multiple Python scripts (manage_markdown_site.py, manage_markdown_work.py, and validate_seo_findings.py) to handle SEO auditing and markdown site management tasks.
[DYNAMIC_EXECUTION]: Executable paths are constructed at runtime using the <suite-root> variable. This variable is resolved from platform environment variables like ${CLAUDE_PLUGIN_ROOT} or from local configuration files such as .seo-suite-runtime.json. Dynamic loading from computed paths allows the execution of scripts from variable locations.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including URL inventories, sitemaps, and SEO evidence retrieved from public websites.
Ingestion points: The skill reads URL-to-locale inventories, sitemaps, and site-wide inventories from external sources as specified in SKILL.md and references/markdown-delivery-contract.md.
Boundary markers: There are no explicit instructions or delimiters used to isolate external data from the agent's instructions, nor are there warnings to ignore instructions embedded in the data.
Capability inventory: The agent has the capability to execute shell commands (Python scripts) and perform file system operations to generate reports and site structures.
Sanitization: The instructions do not specify any sanitization or validation protocols for the ingested SEO data before it is passed to the execution scripts or processed by the agent.

seo-hreflang