The Agent Skills Directory

[SAFE]: The skill provides structured instructions for managing project state via a local Markdown file. It does not contain any obfuscated code, unauthorized network requests, or credential exposure.
[COMMAND_EXECUTION]: The skill references a /prototype tool intended for generating and testing logic as part of the planning process. This is a primary function of the skill and is triggered through user-authorized tickets.
[INDIRECT_PROMPT_INJECTION]: The skill reads from a Markdown-based decision map that can be updated by other agents or processes in a collaborative environment.
Ingestion points: Project-resident Markdown decision map files.
Boundary markers: None specified in the instructions.
Capability inventory: File system writes for ticket creation and invocation of the /prototype skill for code execution.
Sanitization: No specific sanitization of the decision map content is implemented; the skill relies on the structured Markdown format for parsing.

decision-mapping