The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (init_agentic_os.py, init_flywheel_files.py) and shell commands to automate project initialization and create the directory structure. These scripts are part of the skill's own package distribution.
[EXTERNAL_DOWNLOADS]: The skill includes instructions to install additional components using npx skills add from the author's repository. These are documented as part of the intended setup process for the environment and originate from a source associated with the skill author.
[DATA_EXFILTRATION]: While the skill reads existing project files like CLAUDE.md to tailor the initialization process, it does not contain instructions or code to transmit this information to any external or remote destinations.
[PROMPT_INJECTION]: The skill uses detailed instructional blocks to guide the agent through a user interview process. These instructions focus on functional bootstrapping and do not attempt to override the agent's underlying safety or operational constraints.

os-init