The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local script python easysdd/tools/search-yaml.py to identify existing documentation files within the project directories. This is a project-specific utility confined to the local file system.
[PROMPT_INJECTION]: The skill processes project design specifications and source code, which constitutes a surface for indirect prompt injection. Ingestion points: project files and design documents. Boundary markers: none explicitly mentioned. Capability inventory: writing files to the docs/ directory. Sanitization: none explicitly defined. The security risk is assessed as safe because the output is documentation intended for human review, and the workflow includes a mandatory step for user verification before any files are written to disk.

easysdd-guidedoc