Identifies when task outputs require iteration based on quality signals, unmet requirements, or explicit feedback. Triggers appropriate re-execution strategies. Activate on 'needs iteration', 'retry needed', 'not good enough', 'try again', 'refine output'. NOT for feedback generation (use dag-feedback-synthesizer) or convergence tracking (use dag-convergence-monitor).
Identifies when task outputs require iteration based on quality signals, unmet requirements, or explicit feedback. Triggers appropriate re-execution strategies. Activate on 'needs iteration', 'retry needed', 'not good enough', 'try again', 'refine output'. NOT for feedback generation (use dag-feedback-synthesizer) or convergence tracking (use dag-convergence-monitor).
根据质量信号、未满足的要求或明确反馈，识别任务输出何时需要迭代。触发适当的重新执行策略。在以下情况激活：'需要迭代'、'需要重试'、'不够好'、'再试一次'、'优化输出'。不用于生成反馈（请使用有向无环图反馈合成器）或收敛跟踪（请使用有向无环图收敛监控器）。
Category: other · Author: curiositech · Version: @main · License: MIT
Tags: dag, feedback, iteration, refinement, quality
该 Skill 暂无文档文件。