The Agent Skills Directory

[SAFE]: The skill implements a methodology for defining workflows through a conversational interview process. Its primary function is the creation and management of documentation within the workspace.- [SAFE]: The skill interacts with local workspace files NOTES.md and workflows/*.md. While reading user-controlled content from these files constitutes a surface for indirect prompt injection, the risk is negligible as the skill does not possess capabilities for network access, subprocess execution, or dynamic code evaluation. Ingestion points: NOTES.md and workflows/*.md in the local workspace. Boundary markers: Absent. Capability inventory: Restricted to local file manipulation (create, edit, delete) of markdown files and conversational responses. Sanitization: None identified.

loop-me