Idea Darwin 中文版

This skill is internally consistent and appears to do what it advertises, but before installing or running it: 1) run it (or initialize) in a dedicated project directory or backup your repository — it will create and modify files (cards/, rounds/, config.yaml, stimuli.md, graph/). 2) Review generated stimuli.md and any new card files for content you don't want persisted. 3) Because it can be invoked autonomously by the agent, consider when/how triggers will be used (it will only run when invoked or when matching trigger phrases). 4) There are no network calls or secret access declared, but absence of code files means there is nothing to scan — if you need stronger assurance, request the author/source code or run it in an isolated environment first.