Results for “self-evaluation”

当个人希望提升自身在职业或社会中的不可替代性，以应对环境变化和不确定性时

LLaVA-Critic: Learning to Evaluate Multimodal Models

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

当意识到当前行为模式可能导致不理想的未来，需要一种具体方法来激发改变动力时

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

当意识到自己处于被动、重复、缺乏意义的生活状态，想要主动设计人生时

当面对新任务或挑战，内心产生“缺乏经验”、“不擅长”等自我否定想法时

Autonomous error recovery — detect failures, diagnose root cause, apply fixes, and resume without stopping

Improve existing content and close the learning loop without cannibalizing new-content work.

当设定个人或工作目标，希望目标本身能带来持续的内在动力和满足感时

当需要设定人生方向或进行重大行为改变时

Autonomous evolutionary code improvement engine with tournament selection

当需要将个人学习、成长与价值创造整合为一个持续发展的系统时

当意识到自己处于长期迷茫、缺乏动力阶段，需要系统性方法走出困境时

Pauses mid-conversation to reassess direction, assumptions, and bias, then recommends whether to continue, pivot, or pause.

当感到生活迷茫、停滞不前，需要理解当前所处阶段并规划下一步行动时

Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.

Analyzes evaluation patterns across completed plans and evolves the superpowers checklists accordingly.

当遭遇挫折、失败或结果不如预期时，用于将负面经验转化为成长燃料

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:review or asks what has been learned and what should be promoted or pruned.