knowledge-forge

Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others can understand, remember, and apply. Use this skill when users want to turn experience or case studies into teachable content, redesign presentations for maximum retention, create course outlines from domain expertise, crystallize knowledge into shareable documents or knowledge cards, convert know-how into teachable answers, or any scenario where experience must become portable and transferable.

3,891 stars

Best use case

knowledge-forge is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others can understand, remember, and apply. Use this skill when users want to turn experience or case studies into teachable content, redesign presentations for maximum retention, create course outlines from domain expertise, crystallize knowledge into shareable documents or knowledge cards, convert know-how into teachable answers, or any scenario where experience must become portable and transferable.

Teams using knowledge-forge should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/knowledge-forge/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/angjustinl/knowledge-forge/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/knowledge-forge/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How knowledge-forge Compares

Feature / Agentknowledge-forgeStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others can understand, remember, and apply. Use this skill when users want to turn experience or case studies into teachable content, redesign presentations for maximum retention, create course outlines from domain expertise, crystallize knowledge into shareable documents or knowledge cards, convert know-how into teachable answers, or any scenario where experience must become portable and transferable.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 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](references/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](references/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.
2. **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.
3. **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](references/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](references/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
2. **The Model** -- The transferable structure, with a memorable label
3. **The Evidence** -- The original experience, reframed as proof of the model
4. **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:

```
## Transformation Log

- **Perspective Flip**: [Original framing] -> [Audience-facing challenge]
- **Model Extracted**: [Model name and one-line description]
- **Narrative Shift**: [What was de-emphasized vs. elevated]
- **Anchor**: "[The one sentence]"
```

This log helps the user understand and iterate on the transformation.

Related Skills

Knowledge Management System

3891
from openclaw/skills

> Turn tribal knowledge into searchable, maintained organizational intelligence. Stop losing expertise when people leave.

rag-knowledge-assistant

3891
from openclaw/skills

基于向量数据库的 RAG(检索增强生成) 知识库助手。支持语义检索、多格式文档 (PDF/Word/Excel/Markdown) 处理、智能问答。使用 Chroma 向量库 + BGE-M3 Embedding 模型。适用于从 knowledge 目录快速检索信息、回答基于文档的问题。触发词:"从知识库查"、"检索文档"、"RAG 查询"、"向量搜索"、"语义检索"等。

benchmark-lobster-forge

3891
from openclaw/skills

用元认知引导发现值得被做成小龙虾的机会点,并将其收敛为可开箱即用的基准 Agent 小龙虾。

marketing-copy-knowledge

3891
from openclaw/skills

小黑老師 邱煜庭設計。Meta 廣告文案、Google 廣告文案、社群貼文:用 FABE x SPIN 產出更能轉換的廣告文案。支援 freemium/付費(X-Api-Key credits)。

knowledge-gaps

3891
from openclaw/skills

Track questions Hans failed to answer and flag missing knowledge

SkillForge - GitHub Automation Skill

3891
from openclaw/skills

> OpenClaw Skill for GitHub Automation

knowledge-answer

3891
from openclaw/skills

Current Date: $DATE$. Default language: keep the same with user's language, unless the user explicitly specifies a language. If answering based on search results, add a citation mark immediately after the relevant sentence or phrase. 2. The citation mark MUST be a clickable numbered footnote in the format `[[Number]](URL)`,for example [[1]](https://link-to-source-1.com). At the end, there shoul...

careerforge-cv-generator

3891
from openclaw/skills

AI-powered CV generator for job applications. Sets up automated job search with CareerForge CLI, manages master resume creation, configures filtering criteria (location, keywords, remote/in-person, schedule), and generates tailored CVs on demand. Use when user wants to automate job search, create/update a master resume, configure job filters, or generate CVs for specific job postings.

professional-agent-forge

3891
from openclaw/skills

Build a complete OpenClaw agent package for a real profession or job role. Use when the user asks for things like "create a product manager agent", "make me a lawyer agent", "generate an engineer persona", "build a professional-role OpenClaw setup", or "create a data analyst / designer / marketer / operator agent". Produce a role-specific package centered on `soul.md`, `identity.md`, `memory.md`, `agents.md`, and `tools.md`, plus a recommended supporting-skill stack.

fictional-companion-forge

3891
from openclaw/skills

Turn a fictional character from games, films, TV, novels, comics, or anime into a deployable OpenClaw companion agent. Use when the user names a character such as Ghost, König, Keegan, Hermione, Tony Stark, Cloud, or any other fictional persona, or asks for things like "turn this character into an AI companion", "let me talk to this character", "restore this character's personality", or "generate an agent based on this fictional role". Produce a character-faithful package centered on `soul.md`, `identity.md`, `memory.md`, and `agents.md`.

knowledge-sync

3891
from openclaw/skills

Real-time knowledge base synchronization for AI assistants. Supports inotifywait file monitoring, Git auto-push/pull, Nutstore sync, and multi-device consistency. Use for maintaining knowledge continuity across servers and local devices.

lexiang-knowledge-base

3891
from openclaw/skills

用于访问乐享知识库平台的专用 skill。当用户明确提到「乐享」「lexiang」「知识库」「知识」「文档」等关键词,或用户提供的链接 host 为 lexiangla.com,应优先调用本 skill。本 skill 支持:获取文档内容与元数据、搜索文档内容、查询知识库与目录结构、创建/编辑/移动文档、管理标签与评论、上传文件及维护附件等知识库操作能力。