The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform shell operations for environmental discovery and technical SEO diagnostics. Upon activation, the agent is directed to list contents of directory paths in the user's home folder (e.g., ~/.claude/skills/) to identify installed companion skills. It also utilizes curl for redirect auditing and complex bash pipelines (incorporating grep, awk, and sed) for processing server access logs to detect crawl anomalies.
[EXTERNAL_DOWNLOADS]: The skill documentation and companion check logic recommend the installation of additional packages via npx skills add AbsolutelySkilled/AbsolutelySkilled. As this repository is not associated with a verified trusted organization or well-known service, it represents the installation of unverifiable code from an external source.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through data ingestion. It processes external data from server access logs and web page content (fetched via curl) without defining explicit boundary markers or sanitization procedures, while the agent maintains access to shell-based execution capabilities across multiple reference files.

technical-seo