不合理信念现场验证实验
在咨询中协同求助者设计并实施现场人际反馈实验(如邀请同伴当面评价其社交表现),用真实外部信息直接挑战其核心不合理信念。
npx skills add ECNU-ICALK/AutoSkill --skill 不合理信念现场验证实验 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 不合理信念现场验证实验 在咨询中协同求助者设计并实施现场人际反馈实验(如邀请同伴当面评价其社交表现),用真实外部信息直接挑战其核心不合理信念。 ## Prompt 协同求助者共同选定1–2位可信、友善的同龄同伴(如同班/同宿舍同学);在安全、私密且可控的咨询室内,当着求助者面,向同伴提出结构化问题(如‘她和你们说话时,是否真的像她说的那样脸红发抖、显得怪异?’);引导求助者倾听、记录并即时复述他人反馈;随后与求助者一起对比其原有信念与实际反馈,标注差异,支持其表达认知松动(如‘原来没那么糟’)。 ## Objective 修正核心自动思维 ## Applicable Signals - 求助者使用绝对化、以偏概全、灾难化语言描述他人反应(如‘他们一定会嘲笑我’) - 求助者能识别该想法但无法自我反驳 - 求助者曾提及某位同伴态度友善或中立 ## Contraindications - 求助者当前极度羞耻或拒绝他人接触 - 缺乏可信同伴或环境不支持公开验证 - 信念内容涉及现实危险(如被伤害)而非认知扭曲 ## Intervention Moves - 共构验证问题(聚焦可观察行为,非主观评价) - Third-party live testimony elicitation - Real-time belief–evidence contrast mapping - Cognitive softening reflection ('What felt different hearing that?') ## Workflow Steps - Step 1: Collaboratively identify one concrete, observable belief (e.g., 'I look like a monster when speaking'). - Step 2: Select 1–2 trusted peers; obtain verbal consent for brief, respectful feedback. - Step 3: Conduct in-session, face-to-face peer inquiry using behaviorally anchored questions (e.g., 'When she talks to you, do you notice her face turning red or hands shaking?'). - Step 4: Invite求助者 to paraphrase each response aloud; therapist mirrors and validates emotional impact. - Step 5: Jointly note discr
- Prompt
- Objective
- Applicable Signals
- Contraindications
- Intervention Moves
- Workflow Steps
- Constraints
- Cautions
- Output Contract
- Example Therapist Responses
- Example 1
- Example 2
- Files
- Triggers
What does the 不合理信念现场验证实验 skill do?
在咨询中协同求助者设计并实施现场人际反馈实验(如邀请同伴当面评价其社交表现),用真实外部信息直接挑战其核心不合理信念。
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill 不合理信念现场验证实验 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
