The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external links and user-provided files, which creates a surface for instructions embedded in that data to influence agent behavior.
Ingestion points: The agent reads from RESOURCES.md (which contains links to external documentation, books, and videos) and MISSION.md (user-provided goals and constraints) to ground its teaching.
Boundary markers: No explicit delimiter or 'ignore' instructions are defined in the file templates to separate ingested content from system instructions.
Capability inventory: The agent has the capability to write multiple file types to the local workspace (.md, .html) and utilize domain-specific tools like vg for asset generation and deployment.
Sanitization: The skill instructions emphasize a manual vetting process by instructing the agent to 'populate RESOURCES.md first' from 'high-trust' and 'primary sources'.

teach-me