Course positioning
面向 Codex Goal 长时运行的课程制作 Agent Skill：课程定位、专家访谈、材料加工、逐字稿、审校与课程海报。
npx -y skills add Ivor-NCUT/course-producer --skill course-positioningAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 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.
- 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
基于课程材料或必要的最少提问，生成可验证的课程定位：课程主题、目标学员、挑战情境、学习成果、使用场景和边界。Use when the user says 课程定位、这门课给谁学、课程解决什么问题、课程承诺、从零设计课程，或 Course Producer 完成材料摄取后进入 positioning 阶段。
SKILL.md
3.4 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it
课程定位
只确定课程方向，不生成课纲或逐字稿。优先读取证据，信息够用就直接推进；不要把访谈流程当成必须经过的仪式。
开始前读取：
.course-producer/materials.jsonl.course-producer/artifacts/material-gap-report.md知识库/方法论/课程定位.md知识库/模板/课程项目模板.md
执行流程
- 从材料提取已经明确的课程主题、受众背景、迫切问题、应用场景、约束、讲师优势和结果承诺。
- 把互相冲突的证据分开列出，不自行选择。向
.course-producer/decisions.jsonl追加决策项，记录来源、影响阶段和建议选项。 - 用“具体的人与环境 + 正在发生的问题 + 时间/资源/能力约束”写挑战情境，拒绝“提升认知”“学会增长”一类空泛表述。
- 把每条课程承诺改写成“成果契约”，逐项回答：
- 完成时能看到哪份产物、动作或状态；
- 出现什么情况说明学员还没有做到；
- 何时或在什么条件下结束本次学习任务；
- 谁在什么场景完成什么任务，达到什么判定标准；
- 该成果是否与学员当前资源、权限和时间约束兼容。 删除不改变验收含义的修饰词；“系统掌握”“深入理解”“全面提升”不能单独成为学习成果。
- 判断信息是否足够：
- 缺口不会改变目标学员、课程承诺或边界时，标为待确认并继续；
- 缺口会让课程变成另一门课时，只问一个当前最关键的问题；
- 用户已经授权长时执行时，不重复要求确认已有事实。
- 生成
.course-producer/artifacts/positioning.md，每个重要判断附source_id；用户口头新增信息用source_id: user-decision-*登记到 decisions。 - 运行定位质量检查，写入检查结果并登记阶段完成。
输出结构
# 课程定位
## 一句话主题
## 目标学员
- 已有背景
- 当前场景
- 排除人群
## 核心挑战
- 场景
- 问题
- 约束
## 学习成果
- 成果 / 使用场景 / 验收标准 / 未完成信号 / 完成条件
## 课程使用场景
## 课程边界与不承诺
## 证据与待确认项
决策记录
decisions.jsonl 每项至少包含 decision_id、question、options、evidence、impact、status 和 resolution。status 使用 open 或 resolved。不要把普通材料缺口升级成用户决策。
完成检查
- 主题、目标学员、挑战、学习成果、使用场景和边界齐全。
- 挑战同时包含场景、问题和约束。
- 学习成果可观察、可验收，没有编造量化承诺。
- 每条学习成果都有未完成信号与完成条件，学员能够判断下一步和什么时候算完成。
- 每个关键判断有来源或明确标为用户决定/待确认。
- 材料矛盾已进入
decisions.jsonl，没有被静默抹平。 - 文档没有提前设计课程模块、章节或完整正文。
完成后把定位交给 course-interview-design 或 course-knowledge-extraction。
What ships with it: 1 file
276 B alongside SKILL.md
agents/
- openai.yaml276 B
Gives 0 of the 12 instructions most product growth skills give in ~1.1k tokens
Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07
- Read product marketing context before asking questionsin 24 of 728, across 18 files
- Define the ideal customer profilein 21 of 728, across 3 files
- Document a rollback plan before deploymentin 21 of 728, across 12 files
- Analyze the codebase to understand the productin 19 of 728, across 1 file
- Ask clarifying questions about the value propositionin 19 of 728, across 1 file
- Search for companies matching the criteriain 19 of 728, across 1 file
- Look for signals of immediate needin 19 of 728, across 1 file
- Assign a fit score from one to tenin 19 of 728, across 1 file
- Identify the target decision-maker rolein 19 of 728, across 1 file
- Suggest a personalized contact strategyin 19 of 728, across 1 file
- Provide conversation starters for outreachin 19 of 728, across 1 file
- Format results in a scannable markdown templatein 19 of 728, across 1 file
Said here and by no other author read
- 读取课程材料证据与方法论文档
- 提取课程主题、受众、问题、场景、约束和承诺
- 将互相冲突的证据分开列出
- 追加决策项到 decisions 日志
- 用具体环境、问题和约束写挑战情境
- 将课程承诺改写为成果契约
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.