Agent skill

逐级暴露与反应阻止训练

在强迫症干预中,系统性地引导来访者接触诱发焦虑的刺激(如‘脏东西’),同时阻止其执行习惯性缓解行为(如清洁),以降低焦虑耐受阈值并削弱强迫循环。

ECNU-ICALKgithub.com/ECNU-ICALKGitHub ↗
claude-code
Install
npx skills add ECNU-ICALK/AutoSkill --skill 逐级暴露与反应阻止训练 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 3
SKILL.md size: 3 KB
Bundled scripts: none
Version: 0.1.1
Path: SkillBank/DocSkill/心理咨询/Family技能/认知行为疗法/二级技能/逐级暴露与反应阻止训练/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 539
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 逐级暴露与反应阻止训练 在强迫症干预中,系统性地引导来访者接触诱发焦虑的刺激(如‘脏东西’),同时阻止其执行习惯性缓解行为(如清洁),以降低焦虑耐受阈值并削弱强迫循环。 ## Prompt 在来访者已完成认知重建、具备基本情绪耐受能力且无高风险共病的前提下,引导其进入结构化暴露:先从低强度想象暴露开始(如回忆‘未封口的字’情境),同步监测主观焦虑评分(SUDS);当焦虑达峰值后,明确要求其抑制对应强迫行为(如不补封口、不刻意弄响右脚鞋)至少90秒;全程陪伴性支持,不代偿、不强化仪式行为;结束后共同评估焦虑下降幅度与自我效能感变化。 ## Objective exposure_and_response_prevention ## Applicable Signals - 报告特定情境下出现可预测的焦虑上升与仪式冲动 - 能自主命名1–3个典型强迫诱因 - 在认知作业中已初步接受‘焦虑会自然下降’这一原理 ## Contraindications - 存在活跃自杀意念或计划 - 强迫行为涉及现实安全风险(如反复检查电器、自伤性清洗) - 当前处于重度抑郁发作期(PHQ-9 ≥15)或有精神病性症状 ## Intervention Moves - 引导想象暴露或实景暴露 - 设定明确的反应抑制时限(≥90秒) - 实时SUDS锚定与反馈 - 归因重构:将焦虑下降归因为‘耐受而非仪式’ ## Workflow Steps - 确认来访者理解ERP原理及合作意愿,回顾前期认知重建成果 - 共同选择一个低至中度诱发强度的强迫情境(优先想象暴露) - 引导沉浸式暴露(时长≤2分钟),同步用0–10分标尺记录SUDS变化 - 在焦虑峰值出现后,明确指令:‘请暂停所有仪式行为,静观感受,坚持至少90秒’ - 全程不提示转移注意、不提供安抚性替代行为,仅作存在性陪伴 - 暴露结束后立即评估:SUDS下降值、主观控制感、是否观察到焦虑自然回落 ## Constraints - 单次暴露总时长不超过5分钟(含准备与复盘) - 首次暴露必须为想象形式,禁用实景触发 - 若SUDS峰值>8且无法在90秒内下降≥20%,即刻中止并切换至接地技术 ## Cautions - 避免使用‘你必须忍住’等命令式语言,改用‘我们试试看你能观察到什么’ - 警惕来访者以‘分心’‘找借口’等方式隐性执行仪式,需温和指认 - 若连续两次无法完成90秒抑制,需回溯认知模块或评估动机水平 ## Output Contract - 来访者完成一次结构化暴露(想象或实景)且全程抑制仪式行为≥90秒,报告焦虑峰值下降≥20%。 ## Example Therapist Responses ### Example 1 - Client/Input: 来访者说:‘想到字没封口,心跳很快,手心出汗,马上想拿笔补上。

What's inside
Steps it walks through
  1. Prompt
  2. Objective
  3. Applicable Signals
  4. Contraindications
  5. Intervention Moves
  6. Workflow Steps
  7. Constraints
  8. Cautions
  9. Output Contract
  10. Example Therapist Responses
  11. Example 1
  12. Example 2
  13. Files
  14. Triggers
Ships with 2 files
  • references/evidence.md
  • references/evidence_manifest.json
More from AutoSkill
All skills →
About this skill
What does the 逐级暴露与反应阻止训练 skill do?

在强迫症干预中,系统性地引导来访者接触诱发焦虑的刺激(如‘脏东西’),同时阻止其执行习惯性缓解行为(如清洁),以降低焦虑耐受阈值并削弱强迫循环。

How do I install it?

Run `npx skills add ECNU-ICALK/AutoSkill --skill 逐级暴露与反应阻止训练 --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.

Keep going