The Agent Skills Directory

[SAFE]: The skill implements a structured workflow for document generation without any malicious patterns. It correctly uses local file operations and platform-native sub-agents for its primary tasks.
[COMMAND_EXECUTION]: The skill uses file system tools (Read, Write, Grep, Glob) and specialized agent capabilities (worldmodel, analyze, research) to investigate the product space. These operations are limited to project files and standard web search APIs, serving the skill's documented purpose.
[PROMPT_INJECTION]: No attempts to override agent safety guidelines or bypass behavioral constraints were detected. The instructions focus on maintaining product rigor and technical accuracy.

stories