菜单
User correction, thumbs up/down, inline editing, and reinforcement signals.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Proactively identifying failure modes, misuse, and unintended consequences.
Managing shared context, memory, and state across multiple agents.
Coordinating text, image, voice, and tool-use modalities in a single interaction.
Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.
Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.
Designing review workflows to surface and mitigate bias in AI outputs.
| name | feedback-loops |
| description | User correction, thumbs up/down, inline editing, and reinforcement signals. |
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.
The most valuable feedback is correction — but it's also the hardest to design for:
When to ask for feedback matters:
Feedback is only valuable if it changes something. The user needs to see that their feedback matters:
