The Agent Skills Directory

[SAFE]: The skill provides a structured framework for decision-making by maintaining project state in markdown files. While it loads these files as context (an indirect prompt injection surface), this is the primary intended functionality of the tool and is managed within the user's project environment.
Ingestion points: The 'resume' workflow loads an existing markdown file from a local file path into the agent's context.
Boundary markers: The skill does not specify explicit delimiters or 'ignore' warnings for content within the decision map tickets.
Capability inventory: The skill can invoke other internal functional skills such as '/prototype', '/grilling', and '/domain-modelling' based on the map's contents.
Sanitization: No sanitization or validation is performed on the markdown file content before it is used to guide agent behavior. No high-risk behaviors or security violations were detected.

decision-mapping