AI Pm Atom Lesson

输入一个"原子知识点"(AI 产品经理知识体系里的最小单元概念,如「文本切分」「演绎推理」「思维链 CoT」「向量化」「LLM-as-Judge」),自动展开成一份讲解思路并产出一个单文件、离线可用的交互式 HTML 原子课件——含权威定义+真实出处、通俗解释、贯穿项目案例、实操判断题、以及一个可视交互 Demo。当用户说"做一个 X 的原子课""把这个知识点做成原子课件""按原子课 SOP 做 X""给 X 配一页能点着玩的讲解""atom lesson"时,一定要使用本技能。也适用于:把知识体系/能力地图里的某个词条单点成课、要一系列同构的知识点小课件、批量把能力地图节点做成课。即使用户只说"把 X 讲清楚、做成能上手玩的一页",也要触发。本技能是 ai-pm-interactive-lesson 的"单原子特化版":那个处理一整节多知识点的课,本技能处理单个原子,粒度更细、结构更固定。

5 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add uimarch123-arch/ai-pm-atom-lesson --skill ai-pm-atom-lesson

Manual install

git clone --depth 1 https://github.com/uimarch123-arch/ai-pm-atom-lesson.git /tmp/ai-pm-atom-lesson
mkdir -p ~/.claude/skills
cp -r /tmp/ai-pm-atom-lesson/. ~/.claude/skills/ai-pm-atom-lesson

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI PM 原子课件生成技能

把**一个原子知识点**升级为**一个单文件交互式 HTML 课件**。核心信条:**一个原子 = 一页课 = 一个可点着玩的直觉。** 抽象概念之所以难,不是因为定义难背,而是因为学员脑子里缺一个"能亲手拨一下、看它怎么变"的模型。这个技能的全部工作,就是把每个原子变成那样一页。

## 输入与产物

- **输入**:一个原子概念(一个词 / 一个短语)。可能来自《AI 产品经理知识体系》里的任意叶子节点,也可能是用户临时给的。
- **产物**:一个 `原子课-NN-名称.html`——单文件、零外部依赖、双击即开、断网可用。

## 全流程四步 SOP

```
① 定位与研课 → ② 靶点与交互选型 → ③ 出稿 → ④ 自检交付
```

每一步都不要跳。**先想清楚这个原子难在哪、该拿什么交互打它,再动手写 HTML。** 写代码前必读两份参考文件:`references/visual-spec.md`(视觉规范)与 `references/html-scaffold.html`(可直接填的骨架);选 Demo 形式时读 `references/interaction-catalog.md`。

---

## 第 ① 步:定位与研课(先把这一个原子想透)

拿到原子后,先产出一张**研课卡**(不落文件,想清楚即可),回答六个问题:

1. **它在知识体系哪一层?** 属于哪个能力域、是"懂原理 / 会设计 / 能落地"哪一层。→ 决定 Hero 的层级标签和整页语气(懂原理偏认知直觉,能落地偏操作判断)。
2. **权威定义 + 真实出处是什么?** 找到这个概念**可查的正源**(原始论文 / 权威教材 / 官方文档 / 经典著作 / 权威百科)。→ 见下方【出处硬约束】。
3. **一句话本质是什么?** 用大白话把它压成一句,作为通俗解释的锚。避免用定义解释定义。
4. **放进贯穿项目长什么样?** 用**母婴电商客评回复助手**造一个具体场景(见【硬约束】)。场景要具体到能看见数据/话术,不能是空泛的"某个功能"。
5. **学员最容易误解 / 最反直觉的那个点是什么?** 这是全课的靶心——它直接决定第②步 Demo 打哪儿。每个原子几乎都有一个"口头认同、内心不信"或"总是搞错"的点,把它揪出来。
6. **和相邻原子怎么勾连?** 上一个原子回指、下一个原子埋伏笔(前向伏笔)。→ 落到正文的 🔗 提示句和页面底部的原子互链卡。

**出处硬约束**:定义必须**转述,不照抄**(尊重版权,也更好懂);出处必须**真实存在、可顺藤查证**,标注到"著作/文档 + 大致年代/条目名"这一级(例:亚里士多德《前分析篇》约公元前 350 年;休谟《人类理解研究》1748;某模型的官方文档条目)。**宁可给一个稳妥的经典正源,也不要编一个看起来专业的假引用。** 拿不准时用 web 检索核实,不要凭印象编造作者、书名、年份。

---

## 第 ② 步:靶点与交互选型(本技能的灵魂)

**一个原子课固定放 2 个「动手实验室」,不多不少:**

- **实验室 1 = 实操判断题**(每课必有)。用刚讲完的定义**反向出题**——给场景让学员判概念/判对错,不出记忆题。2 道题为宜:一道考"是不是这个概念",一道考"这个概念最容易踩的坑"。
- **实验室 2 = 可视交互 Demo**(每课必有,放在最后当压轴)。它只打第①步揪出的那个**靶心**,不贪多。

Read the full skill on GitHub

Details

Skill name: ai-pm-atom-lesson
Repository: uimarch123-arch/ai-pm-atom-lesson
License: MIT
Repo updated: 8 July 2026

FAQ

What does the AI Pm Atom Lesson skill do?

How do I install the AI Pm Atom Lesson skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add uimarch123-arch/ai-pm-atom-lesson --skill ai-pm-atom-lesson. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Pm Atom Lesson popular?

It lives in uimarch123-arch/ai-pm-atom-lesson, which has 5 GitHub stars and 0 forks.

Related skills

AI Prompt Optimizer

banzr519/ai-prompt-optimizer

AI prompt optimizer for prompt improvement, requirements clarification, reusable templates and feedback-driven prompt repair. Turn vague requests into faithful, actionable instructions; audit prompts, preserve variables and output contracts, or compare supplied results. Use for text, coding, design, research, image/video briefs and agent instructions. 中文：AI 提示词优化、需求澄清、语义转译、失败反馈修订、模板复用。 Do not interrupt clear simple tasks, casual conversation or literal translation. Execute the underlying task only when requested.

AI, LLMs & Agents

AI Fluency Assessment

n-pillai/ai-fluency-assessment-skill

Run /assess-fluency to score AI fluency against Anthropic's 4D Framework (Delegation, Description, Discernment, Diligence) and Yegge's 8-Stage Developer-Agent Evolution Model. Generates dated reports, tracks progress across quarterly assessments, and produces .docx output. Use when asked to assess AI fluency, run a fluency check, compare to a past assessment, generate an AI skills report, or check Yegge stage.

AI, LLMs & Agents

AI Resume Generator

haorenhao58-sketch/ai-resume-generator

一键生成互联网AI方向简历的通用工具。当用户提到'生成简历''写简历''AI简历''求职简历''更新简历'，或提到想投递AI产品经理、AI运营、AI工程师、AI商业化、Prompt Engineer、LLM应用、AIGC等AI相关岗位时触发。也适用于用户说'帮我整理项目经历''优化简历表述''简历润色'等场景。该skill通过深度引导候选人输入个人信息与项目细节，运用'问题→方案→量化结果'三段式写作范式，生成突出AI思维与产品化能力的高质量简历，支持Markdown和Word两种输出格式。

AI, LLMs & Agents

Agent Teacher

JackyYang258/agent-teacher

Teach a concept through a runnable code example plus a structured walkthrough, instead of a wall of definitions. Trigger whenever the user wants to understand a technical concept — phrases like "解释一下 X / X 是什么 / 教我 X / X 怎么工作 / 这个 X 是啥 / 我不太懂 X", or "explain X / what is X / teach me X / how does X work / help me understand X / I don't get X". Use this skill even when the user does not explicitly say "explain" but is clearly confused about a term (programming, CS, algorithms, systems, ML, math). Default mode is in-conversation lesson; only write a file when the user asks to save notes.

AI, LLMs & Agents

AI Slop Detector

MahmoudHalat/slop-cop

Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post, social post, doc, or chat message — before delivering it, even when nobody asked for an audit. Also use whenever the user wants to audit, critique, score, rewrite, or humanize prose: "audit this", "review this", "is this AI", "does this sound like AI", "humanize this", "make this le

AI, LLMs & Agents

Agent Guard

elliottwaves-20/agent-guard

This is a multi-file skill: individual entry points intentionally implement only their documented role while the package provides the workflow as a whole. Scan AI agent skills, plugins, and MCP servers for malicious code BEFORE installation — catches prompt injection, credential theft, data exfiltration, and backdoors. Skills and the static MCP source scan use NVIDIA SkillSpector (static patterns + taint tracking + YARA + live OSV.dev CVE lookup + LLM semantic analysis, which runs by default through the user's own claude / opencode CLI login — no API key — or any hosted provider with a key; co

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.