framework-initiative

Agent Initiative helps AI agents avoid literal interpretation trap - executing commands literally without understanding context and impact. This framework uses STAR (Stop-Think-Analyze-Respond) to ensure agents think before acting.

Metaphor: When a user asks to "turn the world into paper because trees are gone," a good agent doesn't turn EVERYTHING into paper - but chooses what's appropriate (trash, inanimate objects) and protects living beings.

Important Principle: Documentation is a REFERENCE, not an OBLIGATION. Existing code is the primary source of truth.

代理理解隐式用户意图、行动前思考并考虑行动影响的框架。使用 STAR 框架（Stop-Think-Analyze-Respond）来防止与上下文不匹配的文字执行。当代理收到不明确的请求、“修复”、“改进”、“全部删除”等抽象命令或具有潜在广泛影响的操作时使用。在没有明确范围限制的情况下触发代码修改请求。 来源：rfxlamia/claude-skillkit。