Teach one replacement
Skill beckpioo/tongban/plugins/tongban/skills/teach-one-replacement
面向4—6岁儿童照护者的事件记录、审慎分析、周复盘与医生客观导出 Skills(仅限非商业使用)
npx -y skills add beckpioo/tongban --skill teach-one-replacementAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- 20 days oldThe repository was created 20 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
当4—6岁儿童的事件已经安全、成人知道要替换哪个可观察行为,并需要把“不要抢、别打人、要礼貌、专心”等抽象要求改成一个可排练动作时使用。触发词包括“教他说什么/做什么、replacement behavior、知道规则但做不到、怎么练”。不用于情绪高峰、即时危险、一次训练多个目标或强迫道歉。
SKILL.md
6.0 KB, ~1.9k tokens by cl100k_base, as published. Nobody here has run it
一个替代行为教学
R — 方法来源(Reading)
本 Skill 综合了把禁止性语言转换成可观察替代动作、低压力排练、现场最小提示和跨机会记录等方法。内容为独立转述,不保留原书摘录。
I — 方法论骨架(Interpretation)
“不能做什么”不是技能。先把问题行为限定在一个可观察情境,再选择一句话或一个动作作为替代。动作必须符合 4—6 岁能力,能被成人示范、孩子低压力排练,并能在真实机会中用最少提示唤起。
评估的是替代动作是否出现、需要多少提示、出现后是否帮助安全或参与,而不是孩子是否立刻完美。高唤醒时做不到不代表没有学会,也不证明故意违抗。
A1 — 合成应用示例(Past Application)
示例:低压力时会说,现场仍冻结
- 问题:一个虚构儿童在玩偶排练中会说“请停下”,真实冲突中仍没有说出。
- 方法论的使用:区分低压力下知道动作和高唤醒现场能执行,保留现有提示而不增加第二个目标。
- 结论:少量练习不足以证明技能已经形成,也不能证明儿童故意不用。
- 结果:继续记录真实机会和提示等级,不从一次未迁移下结论。
示例:把多个修复步骤缩成一个动作
- 问题:一个合成冲突方案同时要求停止、解释、想办法和道歉。
- 方法论的使用:学龄前版本当前只练“听到停后退开一步”。
- 结论:平静时排练和现场提示都要围绕同一个替代动作。
- 结果:安全稳定后,其他能力在新的训练周期另行选择。
A2 — 触发场景(Future Trigger)
- 孩子知道“不能抢”,真实场景仍直接拿。
- 成人反复说“专心、礼貌、别打人”,但没有教可见动作。
- 周复盘要判断一个替代行为是否开始出现。
语言信号:
- “应该教他怎么说?” / “what should she say instead?”
- “知道规则还是做不到” / “knows the rule but cannot do it”
- “想练一个替代动作” / “teach a replacement behavior”
相邻区分:正在升级先用 co-regulate-and-rejoin;任务步骤问题用 scaffold-routines-and-transitions;加入/拒绝等社交脚本从 social-boundary-and-repair 选择内容,但仍由本 Skill维持单一教学闭环。
E — 可执行步骤(Execution)
-
定义一个情境和一个行为
- 写成“当 X 发生,孩子目前做 Y”,不用人格词。
- 完成标准:成人能看见行为是否发生。
-
选择一个替代动作
- 句式:“当 X 时,先说/做 Z。”只允许一句话或一个动作。
- 完成标准:4—6 岁儿童能在低压力环境中模仿。
-
示范并短时排练
- 成人先演,孩子可用玩偶、手势或语言练 1—3 次;允许拒绝。
- 判停条件:孩子升级、疲劳或拒绝时停止,不把排练变成服从测试。
-
在真实机会提示并记录
- 只提示目标动作,记录
prompt_level和是否出现。 - 完成标准:获得至少一次真实机会的数据,不要求一次独立成功。
- 只提示目标动作,记录
🔴 CHECKPOINT — 更换目标或减少提示前
先完整给出当前唯一替代动作的低压力练习方案。初次选择一个动作、恢复更多提示或响应儿童停止信号,不触发本检查点。
仅当下一步会更换当前替代动作、加入第二个目标、减少提示,或把一个场景的结果推广到新场景:
- 列出已记录的真实机会、替代动作是否出现、
prompt_level和仍未知的信息;不同场景不得合并。 - 只提出一个待改变项,并请用户确认或纠正记录、确认是否在下一次相似机会试行。
- 🛑 STOP:确认前保持当前唯一目标和支持量,不新增目标、不减少提示,也不因一次未迁移宣布失败。
即时危险、情绪升级、疲劳或儿童拒绝时不等待确认:立即停止教学,恢复安全与关系。
B — 边界(Boundary)
- 不在即时危险或情绪高峰中教学。
- 不同时教请求、等待、轮流、道歉和情绪表达。
- 不把口头道歉、持续眼神或外向表现当成默认替代行为。
- 不因一次未迁移就提高压力、撤回关系或宣布孩子故意。
- 不用奖励交易或羞辱代替技能教学。
相关 Skills
composes-withevent:主 Skill 确认资料足够且选择“替代行为”后,本 Skill 闭合一次教学循环。composes-withco-regulate-and-rejoin:若事件曾升级,先恢复安全和可学习状态,再在平静时排练。composes-withsocial-boundary-and-repair:社交 Skill 选择“加入、拒绝、求助、修复”中的内容,本 Skill 保证一次只教一个动作。composes-withplay-for-connection:孩子自愿时,可用玩偶或角色游戏承载同一个目标动作。contrasts-withscaffold-routines-and-transitions:本 Skill 替换一个行为;脚手架 Skill 拆解多步骤任务与环境负荷。
审计信息
- 验证:V1 ✓ / V2 ✓ / V3 ✓
- 主要来源:《情商》《社交》《用孩子的逻辑》《孩子:挑战》
What ships with it: 2 files
2.9 KB alongside SKILL.md
agents/
- openai.yaml251 B
- test-prompts.json2.7 KB
Gives 0 of the 12 instructions most learn study skills give in ~1.9k tokens
Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07
- Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
- Produce self-contained HTML lessonsin 24 of 546, across 8 files
- Record user preferences in a notes filein 23 of 546, across 5 files
- Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
- Find high-quality resources before writing lessonsin 19 of 546, across 5 files
- Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
- Create reusable components for lessonsin 19 of 546, across 5 files
- Create compressed reference documents for quick lookupin 19 of 546, across 3 files
- Update the mission file and records upon mission changesin 16 of 546, across 2 files
- Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
- Populate the mission file before teachingin 15 of 546, across 1 file
- Include interactive feedback loops in lessonsin 15 of 546, across 1 file
Said here and by no other author read
- define one observable situation and target behavior
- choose one age-appropriate replacement action
- demonstrate and briefly rehearse the action
- prompt only the target action in real situations
- record prompt level and occurrence at every opportunity
- stop if the child escalates, fatigues, or refuses
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.