The Agent Skills Directory

[SAFE]: The skill is a documentation utility that guides the agent through a series of steps to capture the rationale behind design choices. It does not interact with the operating system, execute shell commands, or perform network requests.
[NO_CODE]: The skill contains no scripts (Python, JavaScript, shell) or external binary dependencies. All operations are confined to generating text based on user-provided context.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied information about decisions, it lacks the capability to execute commands, write to the filesystem, or send data over a network. This lack of sensitive capabilities eliminates the risk of harmful outcomes from indirect prompt injection.

decision-record