Homework start
Skill githubume/chengxing-os-skills/plugins/parent-learning/skills/homework-start
分析孩子在作业、阅读、订正或复习中的启动困难。用户说“坐不下来”“迟迟不写第一题”“一看到作文就离座”“整理文具很久”“不同科目表现不同”时使用；比较任务、场景、状态和家长在场差异，输出孩子、家长与环境共同承担的最小启动实验，不作发展或疾病诊断。From its SKILL.md
npx -y skills add githubume/chengxing-os-skills --skill homework-startAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 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
2.2 KB, 730 tokens by cl100k_base, as published. Nobody here has run it
作业启动分析
必须先读
读取 ../../references/chengxing-shared/safety/routing.md、../../references/chengxing-shared/core-models/behavior-method.md 和 ../../references/chengxing-shared/quality-gates/output-quality.md。先做 B3；持续明显躯体/睡眠异常、严重拒学、自伤、暴力或无法保持安全时停止普通启动方案。
定位行为链
按顺序检查：状态准备→进入学习场景→启动→维持→困难应对→完成→订正→收尾→中断恢复→独立迁移。
执行
- 把“磨蹭、不自律、不听话”改写为任务、时间、第一动作、启动延迟和最近实例。
- 比较简单/困难任务、不同学科、学校/家庭、独立/家长在场和顺利例外。
- 还原家长在启动前后做什么，不把家长动作当作背景噪声。
- 形成最多 3 个竞争假设：能力/拆解、状态、环境、任务情绪、提示、关系或后果。
- 只选择一个首轮瓶颈；孩子动作必须小到可独立尝试。
- 同时定义一个家长动作和一个环境动作；不得只要求孩子改变。
诊断诱因
用户要求把拖拉、离座或分心确诊为 ADHD、抑郁、学习障碍等时，只说明当前行为不足以支持诊断，转回可观察差异和简短专业评估边界。不列诊断标准、量表、专科路径或外部指南链接。
输出
- B1/B2 路由和行为重定义；
- 学习行为链中的卡点；
- 已知、未知和最多 3 个假设；
- 孩子第一动作、家长支持动作、环境动作；
- 今晚 1 个低风险试验；
- 最多 3 个指标，从启动延迟、提醒次数、中断、恢复或独立比例中选择；
- 失败恢复、停止和升级条件。
不以服从、安静或分数作为唯一成功标准，不使用比较、羞辱、代做或剥夺基本需要。
What ships with it: 1 file
248 B alongside SKILL.md
agents/
- openai.yaml248 B
Gives 0 of the 12 instructions most education skills give in 730 tokens
Counted across 169 of the 171 authors here whose files we hold, read 2026-08-07
- Search for existing resources before creating new onesin 7 of 169, across 3 files
- Check tool responses for errors before proceedingin 7 of 169, across 3 files
- Reduce request frequency on rate limit errorsin 7 of 169, across 3 files
- Confirm connection status is ACTIVE before running workflowsin 7 of 169, across 3 files
- Execute prerequisite steps first in workflowsin 7 of 169, across 3 files
- Handle pagination by fetching until exhaustedin 7 of 169, across 3 files
- Re-authenticate if the connection expiredin 6 of 169, across 2 files
- Always call RUBE_SEARCH_TOOLS first to get schemasin 6 of 169, across 2 files
- Pass strictly schema-compliant tool argumentsin 6 of 169, across 2 files
- Run the skill generator if the shared file is missingin 6 of 169, across 3 files
- Create the coursein 5 of 169, across 3 files
- List enrolled studentsin 5 of 169, across 3 files
Said here and by no other author read
- 读取指定安全路由与行为方法参考文件
- 先执行B3安全评估
- 按顺序检查完整学习行为链
- 将主观标签改写为可观察行为
- 对比不同任务、场景与状态的差异
- 还原家长在孩子启动前后的具体动作
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.