The Agent Skills Directory

[SAFE]: The skill implements a strict 'Collaborative Protocol' that requires explicit user confirmation via the AskUserQuestion tool before any file is written or modified.
[SAFE]: Tool usage is limited to standard local file operations (Read, Write, Edit, Glob, Grep) within the project's documentation and state directories.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected in the instructions.
[SAFE]: While the skill processes external documentation (game-concept.md), the risk of indirect prompt injection is mitigated by the multi-stage human review process required for system enumeration, dependency mapping, and priority assignment.

map-systems