using-superpowers

To ensure AI agents invoke tools before responding, implement a strict workflow protocol that mandates checking for and executing relevant skills prior to generating any response, preventing premature or incorrect answers.

AI agents provide canned responses instead of checking available skills due to common rationalizations for skipping tool invocation. Enforcing a structured decision flow with red flag identification prevents these errors and mandates skill use.

The protocol for mandatory skill invocation requires AI agents to check for applicable external knowledge or functionality during all conversational turns and task executions, invoking skills even with a low probability of applicability to ensure comprehensive information gathering.

An AI agent should invoke a skill even with a low probability of applicability whenever external knowledge or functionality might be required, adhering to a strict protocol to prevent errors and ensure comprehensive information gathering across all task executions.

Yes, this skill invocation protocol applies to all conversational turns and task executions where external knowledge or functionality might be required, ensuring agents consistently check for and use applicable tools before taking any action.