Knowledge Forge
Forge raw experience into transferable cognitive assets using a 4-step conversion engine.
Core Concept
Experience is abundant. Answers are scarce.
Most experts are strong inside their own world. But when they open a document or step on stage, others can't follow. The problem is not lack of experience -- it's that experience has not been modeled.
A modeled experience is one that has been abstracted into a structure that transfers across contexts. This skill performs that transformation.
Conversion Engine
When the user provides raw material (a case study, personal summary, business document, draft speech, or any form of experience narrative), execute these 4 steps sequentially:
Step 1: Perspective Flip -- "My experience" -> "Your challenge"
Identify what the user accomplished, then reframe it as a universal challenge the audience faces.
- - Extract the core problem the user solved
- Abstract it away from domain-specific details
- Restate it as a challenge the target audience recognizes in their own work
- The audience should think "yes, I face this too" -- not "interesting, but that's your job"
Key question to answer: "What struggle does the audience already have that this experience speaks to?"
For modeling patterns and examples, see modeling-patterns.md.
Step 2: Experience Modeling -- Specific story -> Transferable structure
The raw experience is a story. Transform it into a model -- an abstraction that works across scenarios.
- - Find the structural pattern hidden in the specific case
- Name it with a memorable, compact label (e.g., "The 100->10->1 Funnel")
- Validate: does the model apply to at least 2-3 other domains the audience cares about?
Key question to answer: "What is the underlying structure that makes this experience work -- independent of the specific domain?"
For modeling archetypes and before/after examples, see modeling-patterns.md.
Step 3: Narrative Reconstruction
Rebuild the narrative using this sequence:
- 1. Challenge alignment -- Present the universal challenge so the audience enters the tension. Spend substantial space here. Make old/obvious answers visibly insufficient.
- Model reveal -- Introduce the abstracted model as the new lens. Emphasize the shift in thinking (role change, mental model upgrade), NOT tool details or step-by-step procedures.
- Evidence from experience -- Use the original story as proof that the model works, not as the centerpiece.
Principle: Present the "Dao" (the judgment behind decisions), not the "Shu" (the operational steps). Tools and procedures are forgettable; the cognitive shift is what transfers.
For techniques on designing cognitive gaps, see challenge-design.md.
Step 4: Anchor Design -- The one sentence they carry away
Design a single, specific, portable judgment -- the anchor.
Requirements for a good anchor:
- - Specific -- not a vague platitude ("work smarter") but a concrete reframing ("AI doesn't save you time -- it changes which game you're playing")
- Sticky -- compact enough to remember and repeat
- Generative -- triggers new thinking when applied to the audience's own context
Key question to answer: "If the audience forgets everything else, what is the ONE sentence that, by itself, changes how they think?"
Place the anchor at the structural climax of the output. It must feel earned -- a culmination of the challenge and model, not a disconnected slogan.
Output
After completing the 4 steps internally, produce the final output.
Determining Output Format
If the user specifies a format, use it. Otherwise, infer from context:
| Signal | Format |
|---|
| "presentation", "talk", "speech", "share" | Presentation Script |
| "course", "training", "teach", "workshop" |
Course Outline |
| "article", "post", "essay", "document" | Article / Document |
| "summary", "card", "one-pager", "memo" | Knowledge Card |
| Ambiguous or unspecified | Knowledge Card (default) |
For output templates and structural guidance, see output-formats.md.
Output Structure
Every output, regardless of format, must contain these elements:
- 1. The Challenge -- The universal problem, stated in the audience's language
- The Model -- The transferable structure, with a memorable label
- The Evidence -- The original experience, reframed as proof of the model
- The Anchor -- The one sentence to carry away
Transformation Log
After the main output, append a brief ## Transformation Log showing the key decisions made during conversion:
CODEBLOCK0
This log helps the user understand and iterate on the transformation.
知识锻造
运用四步转换引擎,将原始经验锻造为可迁移的认知资产。
核心理念
经验丰富,答案稀缺。
大多数专家在自己的领域内游刃有余。但一旦他们打开文档或站上讲台,他人便难以跟上。问题不在于缺乏经验——而在于经验未被模型化。
模型化的经验,是指已被抽象为可跨情境迁移的结构。本技能即执行这一转化。
转换引擎
当用户提供原始素材(案例研究、个人总结、商业文档、演讲稿或任何形式的经验叙述)时,按顺序执行以下4个步骤:
步骤1:视角翻转——我的经验 → 你的挑战
识别用户所取得的成就,然后将其重构为受众面临的普遍性挑战。
- - 提取用户解决的核心问题
- 将其从领域特定细节中抽象出来
- 重新表述为受众能在自身工作中识别出的挑战
- 受众应产生是的,我也面临这个问题的共鸣——而非有意思,但那是你的工作
需回答的关键问题: 受众已经存在的、与这段经验相关的挣扎是什么?
关于建模模式与示例,请参阅建模模式.md。
步骤2:经验建模——具体故事 → 可迁移结构
原始经验是一个故事。将其转化为模型——一种适用于多种场景的抽象结构。
- - 发现隐藏在具体案例中的结构模式
- 用令人难忘的简洁标签命名(例如:100→10→1漏斗)
- 验证:该模型是否至少适用于受众关心的2-3个其他领域?
需回答的关键问题: 使这段经验奏效的底层结构是什么——独立于具体领域之外?
关于建模原型及前后对比示例,请参阅建模模式.md。
步骤3:叙事重构
按以下顺序重建叙事:
- 1. 挑战对齐——呈现普遍性挑战,让受众进入紧张状态。在此处投入大量篇幅。让旧有/显而易见的答案明显不足。
- 模型揭示——引入抽象后的模型作为新视角。强调思维转变(角色转换、心智模型升级),而非工具细节或分步流程。
- 经验佐证——将原始故事作为模型有效的证据,而非核心内容。
原则: 呈现道(决策背后的判断),而非术(操作步骤)。工具和流程会被遗忘;认知转变才是可迁移的。
关于设计认知缺口的技术,请参阅挑战设计.md。
步骤4:锚点设计——他们带走的一句话
设计一个单一、具体、可携带的判断——即锚点。
优秀锚点的要求:
- - 具体——不是模糊的陈词滥调(更聪明地工作),而是具体的重构(AI不会为你节省时间——它改变了你参与的游戏)
- 易记——足够简洁,便于记忆和复述
- 具有生成性——应用于受众自身情境时能触发新思考
需回答的关键问题: 如果受众忘记了其他所有内容,哪一句话本身就能改变他们的思维方式?
将锚点置于输出的结构高潮处。它必须让人感觉是应得的——是挑战与模型的升华,而非一句孤立的标语。
输出
在内部完成4个步骤后,生成最终输出。
确定输出格式
如果用户指定了格式,则使用该格式。否则,根据上下文推断:
| 信号 | 格式 |
|---|
| 演示、演讲、讲话、分享 | 演示脚本 |
| 课程、培训、教学、工作坊 |
课程大纲 |
| 文章、帖子、论文、文档 | 文章/文档 |
| 总结、卡片、一页纸、备忘录 | 知识卡片 |
| 模糊或未指定 | 知识卡片(默认) |
关于输出模板和结构指导,请参阅输出格式.md。
输出结构
无论何种格式,每个输出必须包含以下要素:
- 1. 挑战——用受众的语言表述的普遍性问题
- 模型——可迁移的结构,带有令人难忘的标签
- 证据——原始经验,重构为模型的证明
- 锚点——带走的一句话
转换日志
在主输出之后,附加一个简短的## 转换日志,展示转换过程中的关键决策:
转换日志
- - 视角翻转:[原始框架] → [面向受众的挑战]
- 提取的模型:[模型名称及一行描述]
- 叙事转变:[被弱化的内容 vs. 被提升的内容]
- 锚点:[那一句话]
此日志有助于用户理解并迭代转换过程。