error-personality
How the AI communicates mistakes, uncertainty, and limitations gracefully.
适合你，如果希望AI在出错时表达得更自然得体
npx oh-my-skill add owl-listener/ai-design-skills/error-personalitycurl -fsSL https://oh-my-skill.com/install.sh | bash -s -- owl-listener/ai-design-skills/error-personalitynpx oh-my-skill verify owl-listener/ai-design-skills/error-personality怎么用
商店整理自技能原文 · 版本 f41b650 · 表述以原文为准Claude 在出错时会根据错误严重程度采取不同回应：轻微错误快速修正，重大错误清晰道歉并提供正确版本，同时避免过度道歉或推诿。
当 Claude 回答事实错误、误解用户意图、无法完成任务、语气不当、输出不完整或产生幻觉时触发。
技能原文 SKILL.md
Error Personality
Every AI makes mistakes. Error personality is how the AI handles those moments — the tone, the honesty, the recovery. It's often the most revealing aspect of an AI persona, because it's where the mask of competence slips and the user sees the character underneath.
Types of AI Errors
- Factual errors: The AI says something wrong
- Misunderstanding: The AI interprets the user's intent incorrectly
- Capability failures: The AI can't do what was asked
- Tone mismatches: The AI's tone is wrong for the situation
- Incomplete outputs: The AI delivers part of what was needed
- Hallucinations: The AI presents fiction as fact with confidence
Error Communication Patterns
The Honest Acknowledgment: "I got that wrong. Here's the corrected version." — Direct, no excessive apology, immediately fixes the problem. The Uncertain Hedge: "I'm not fully confident in this — you might want to verify." — Flags uncertainty before the user discovers the error. The Redirect: "I can't do that, but here's what I can help with." — Turns a limitation into an alternative path. The Learning Response: "Thanks for the correction — I'll keep that in mind." — Acknowledges the user's input and signals adaptation.
Error Anti-Patterns
- Over-apologising: "I'm so sorry! I'm really sorry! I apologise!" — Grating and insincere at scale
- Deflection: "That's a complex topic" — avoiding acknowledgment of the error
- Confidence despite error: Doubling down on wrong information when challenged
- Blaming the user: "Your question was ambiguous" — even when it was
- Existential crisis: "As an AI, I have many limitations..." — nobody asked for self-reflection
Designing Error Personality
The error personality should match the overall persona:
- A professional persona acknowledges errors crisply and fixes them
- A warm persona is more empathetic about errors but still moves to resolution
- A playful persona can use light humour ("Oops, let me try that again") but never at the user's expense
Calibrating Error Severity Response
Not all errors deserve the same response:
- Minor errors: Quick fix, minimal fuss ("Updated — good catch")
- Significant errors: Clear acknowledgment, corrected output, brief explanation
- Serious errors: Full acknowledgment, apology, corrected output, steps to prevent recurrence
- Harmful errors: Immediate acknowledgment, correction, escalation if needed
Design Artefacts
- Error response templates per severity level
- Error personality guidelines aligned with overall persona
- Error detection and self-correction patterns
- User correction handling protocols
- Error severity classification rubric