agentsclimarketplace

Seven day family plan

Skill githubume/chengxing-os-skills/plugins/parent-learning/skills/seven-day-family-plan

为作业启动、家庭提醒或手机边界设计七天家庭学习实验。用户说“给我们一周计划”“家长和孩子分别做什么”“试七天再复盘”“不要只要求孩子改变”时使用;每轮只验证一个关键变量,明确孩子、家长和环境各一个动作,并设置恢复与第3/7天检查。From its SKILL.md

Install
npx -y skills add githubume/chengxing-os-skills --skill seven-day-family-plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 26 days oldThe repository was created 26 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.
  • 1 stars1 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.

SKILL.md

2.5 KB, 842 tokens by cl100k_base, as published. Nobody here has run it

七天家庭学习实验

必须先读

读取 ../../references/chengxing-shared/safety/routing.md../../references/chengxing-shared/core-models/behavior-method.md../../references/chengxing-shared/quality-gates/output-quality.md。先做 B3 筛查;出现儿童自伤、暴力、虐待、剥削、无法保持安全或其他 B3 信号时,不生成普通七天计划。

前置条件

至少确认一个具体学习行为、最近场景、大致基线、一个优先瓶颈和过去尝试。信息不足时每轮只问 1–3 个高价值问题。多因素、反复失败或家庭成员相互影响时标记 B2,但首轮仍只验证一个竞争假设。

设计

  1. 把目标改写为可观察动作,不以“听话、自觉、爱学习、提高成绩”作为行为定义。
  2. 选择一个最小充分干预;七天共同规则保持稳定,不每天更换整套方法。
  3. 同时明确孩子、家长和环境各一个动作:孩子动作应可独立尝试,家长动作应可观察,环境动作应能在开始前完成。
  4. 孩子最低版本应在困难日也可能完成;不得通过增加家长盯守、讲道理或处罚来伪装“最低版本”。
  5. 记录最多 3 个指标,从启动延迟、提醒次数、中断/恢复、独立比例、家长执行度或冲突强度中选择;分数只能作为背景结果,不能作为唯一指标。
  6. 写出漏做一次、家长未执行和冲突升级后的恢复脚本,不追补、不归零、不追加惩罚。
  7. 设置第 3 天轻调整和第 7 天保留/简化/替换/暂停决策。

输出

  • B1/B2 路由、目标行为、基线与本轮假设;
  • 七天共同规则;
  • “触发—孩子动作—家长动作—环境动作—反馈—记录”表;
  • 最低版本、标准版本和不强制的可选加码;
  • 最多 3 个指标及记录责任人;
  • 一次中断和冲突升级的恢复脚本;
  • 第 3/7 天复盘问题;
  • 停止和专业升级条件。

不得把服从、安静、分数、排名或连续打卡作为唯一成功标准;不得比较、羞辱、代做、秘密监控,或剥夺睡眠、饮食、教育和必要联系。

What ships with it: 1 file

255 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,782. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.