‹ 首页

feedback-loops

@owl-listener · 收录于 5 天前 · 上游提交 1 个月前

User correction, thumbs up/down, inline editing, and reinforcement signals.

场景用户反馈收集模型调优

适合你，如果你需要根据用户操作来优化AI输出

/ 下载安装
https://github.com/owl-listener/ai-design-skills/tree/main/claude-plugin/model-interaction-design/skills/feedback-loops ↗
/ 通过 npx 安装 校验哈希
npx oh-my-skill add owl-listener/ai-design-skills/feedback-loops
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- owl-listener/ai-design-skills/feedback-loops
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify owl-listener/ai-design-skills/feedback-loops
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
144GitHub stars
~485上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 f41b650 · 表述以原文为准
它做什么

安装反馈循环技能后，Claude会根据你的点赞、点踩、直接编辑输出或提供纠正等反馈，在对话中即时调整回答，并记住你的偏好。

什么时候触发

当你对Claude的输出做出评价（如点赞/点踩）、修改其回复内容、提供正确答案，或要求它重试并给出指导时。

装好后可以这样说
Claude会记住这个纠正，类似情况用正确年份。
Claude会优先考虑你的偏好。
Claude会根据你的指导重新生成。
技能原文 SKILL.md作者撰写 · MIT · f41b650

Feedback Loops

Feedback loops are how users tell the AI what's working and what isn't. Designing these loops well is the difference between an AI that improves over time and one that repeats the same mistakes.

Types of Feedback
  • Explicit feedback: Thumbs up/down, star ratings, "this was helpful/not helpful" buttons
  • Implicit feedback: Regeneration (user asks again), editing (user modifies the output), abandonment (user leaves)
  • Corrective feedback: User provides the right answer ("No, I meant X not Y")
  • Preference feedback: User chooses between alternatives ("I prefer option B")
  • Contextual feedback: Feedback tied to a specific part of the output, not the whole response
Designing for Correction

The most valuable feedback is correction — but it's also the hardest to design for:

  • Inline editing: Let users edit AI output directly. Track what they change.
  • Partial acceptance: Let users keep some parts and reject others.
  • Explanation requests: "Why did you do it this way?" — the user's question reveals what went wrong.
  • Redo with guidance: "Try again but make it more formal" — correction through re-prompting.
Feedback Timing

When to ask for feedback matters:

  • Too early: User hasn't evaluated the output yet. Feedback is premature.
  • Too late: User has moved on. The moment for feedback has passed.
  • Interruptive: Modal dialogs or required ratings break flow.
  • Ambient: Passive signals (edits, regeneration) collected without asking.

Design for ambient feedback first. Add explicit feedback sparingly.

Closing the Loop

Feedback is only valuable if it changes something. The user needs to see that their feedback matters:

  • Immediate adaptation: The AI adjusts in the current conversation
  • Persistent learning: The AI remembers preferences across sessions
  • Acknowledgment: "I'll keep that in mind" — even if adaptation is delayed
Design Artefacts
  • Feedback mechanism inventory per feature
  • Implicit signal definitions (what counts as positive/negative)
  • Feedback-to-adaptation mapping (what changes based on what feedback)
  • Correction flow specifications
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…