You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Loop-based deep reasoning skill for ...Loop-based deep reasoning skill for complex multi-step problems. Triggers when: the user says "think deeper", "deep think", "think through this", "analyze this thoroughly", "reason through", "think step by step", or any task that requires more than surface-level analysis. Also triggers automatically when a task involves: architectural decisions, security analysis, multi-step reasoning chains, comparing competing approaches, risk assessment, or any problem where a quick answer would miss important nuances. Use this BEFORE giving a final answer on any non-trivial task.
1
# DeepThink -- Loop-Based Reasoning Skill
2
3
## Core Concept
4
5
DeepThink turns complex reasoning into a repeatable loop. Instead of trusting the first plausible answer, the agent revisits the original problem through several passes: surface, explore, challenge, synthesize, and converge.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page
or contact support.