The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands such as find, ls, and ln -s to locate skill files within the project and manage documentation symlinks.\n- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill requires the agent to read content from locally discovered skill files to populate documentation templates.\n
Ingestion points: SKILL.md files located in project-specific directories like .claude/skills/ or plugins/*/skills/ (SKILL.md).\n
Boundary markers: Not present; the agent is directed to read discovered files directly to understand their purpose.\n
Capability inventory: File discovery (find, ls) and document creation/writing (AGENTS.md) in SKILL.md.\n
Sanitization: None; content is parsed as natural language instructions for documentation generation.

agents-md