The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx -y godpowers@7 to download and execute code from the NPM registry during project status checks, initialization, and migration tasks. This is a primary function of the skill to manage the environment.
[COMMAND_EXECUTION]: The skill performs multiple shell executions via npx, including status, migrate, init, verify, and doctor. It also allows for the inclusion of a user-defined verification command via the --verify "<command>" argument during initialization.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input by capturing project goals and custom verification commands, which are then stored in local configuration files or executed.
Ingestion points: User-provided goal description for STATE.md and user-supplied verification commands for the init step.
Boundary markers: No specific boundary markers or sanitization logic are defined for the goal content written to STATE.md.
Capability inventory: The skill possesses file system write capabilities (STATE.md, AGENTS.md, CLAUDE.md, .godpowers/) and the ability to execute shell commands via npx.
Sanitization: The instructions do not specify any sanitization or validation of the user-provided goal text or command strings before they are persisted or executed.

god-init