The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command using find to dynamically locate its reference file geo-techniques.md within local plugin and skill directories.- [EXTERNAL_DOWNLOADS]: The documentation references and recommends two external GitHub repositories (AI2HU/gego and jonradoff/llmopt) for monitoring and measuring optimization results. These are third-party tools provided for the user to install.- [PROMPT_INJECTION]: The skill processes untrusted content from external URLs and local files to perform audits and rewrites, creating a surface for indirect prompt injection.
Ingestion points: Data enters the context via WebFetch or local file paths as described in Step 3 of SKILL.md.
Boundary markers: The skill contains specific instructions to refuse requests for data fabrication and includes a "Quality Gate" for verification.
Capability inventory: The skill performs file discovery via shell commands, uses web search/fetch tools, and references a CMS integration workflow.
Sanitization: The skill implements validation steps to check for fabricated quotes, statistics, and expert names before outputting results.

geo-optimizer