← Back to Skills Marketplace
angjustinl

knowledge-forge

by ANGJustinl · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
384
Downloads
1
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install knowledge-forge
Description
Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others...
README (SKILL.md)

\r \r

Knowledge Forge\r

\r Forge raw experience into transferable cognitive assets using a 4-step conversion engine.\r \r

Core Concept\r

\r Experience is abundant. Answers are scarce.\r \r 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.\r \r A modeled experience is one that has been abstracted into a structure that transfers across contexts. This skill performs that transformation.\r \r

Conversion Engine\r

\r 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:\r \r

Step 1: Perspective Flip -- "My experience" -> "Your challenge"\r

\r Identify what the user accomplished, then reframe it as a universal challenge the audience faces.\r \r

  • Extract the core problem the user solved\r
  • Abstract it away from domain-specific details\r
  • Restate it as a challenge the target audience recognizes in their own work\r
  • The audience should think "yes, I face this too" -- not "interesting, but that's your job"\r \r Key question to answer: "What struggle does the audience already have that this experience speaks to?"\r \r For modeling patterns and examples, see modeling-patterns.md.\r \r

Step 2: Experience Modeling -- Specific story -> Transferable structure\r

\r The raw experience is a story. Transform it into a model -- an abstraction that works across scenarios.\r \r

  • Find the structural pattern hidden in the specific case\r
  • Name it with a memorable, compact label (e.g., "The 100->10->1 Funnel")\r
  • Validate: does the model apply to at least 2-3 other domains the audience cares about?\r \r Key question to answer: "What is the underlying structure that makes this experience work -- independent of the specific domain?"\r \r For modeling archetypes and before/after examples, see modeling-patterns.md.\r \r

Step 3: Narrative Reconstruction\r

\r Rebuild the narrative using this sequence:\r \r

  1. Challenge alignment -- Present the universal challenge so the audience enters the tension. Spend substantial space here. Make old/obvious answers visibly insufficient.\r
  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.\r
  3. Evidence from experience -- Use the original story as proof that the model works, not as the centerpiece.\r \r 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.\r \r For techniques on designing cognitive gaps, see challenge-design.md.\r \r

Step 4: Anchor Design -- The one sentence they carry away\r

\r Design a single, specific, portable judgment -- the anchor.\r \r Requirements for a good anchor:\r

  • Specific -- not a vague platitude ("work smarter") but a concrete reframing ("AI doesn't save you time -- it changes which game you're playing")\r
  • Sticky -- compact enough to remember and repeat\r
  • Generative -- triggers new thinking when applied to the audience's own context\r \r Key question to answer: "If the audience forgets everything else, what is the ONE sentence that, by itself, changes how they think?"\r \r 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.\r \r

Output\r

\r After completing the 4 steps internally, produce the final output.\r \r

Determining Output Format\r

\r If the user specifies a format, use it. Otherwise, infer from context:\r \r | Signal | Format |\r |--------|--------|\r | "presentation", "talk", "speech", "share" | Presentation Script |\r | "course", "training", "teach", "workshop" | Course Outline |\r | "article", "post", "essay", "document" | Article / Document |\r | "summary", "card", "one-pager", "memo" | Knowledge Card |\r | Ambiguous or unspecified | Knowledge Card (default) |\r \r For output templates and structural guidance, see output-formats.md.\r \r

Output Structure\r

\r Every output, regardless of format, must contain these elements:\r \r

  1. The Challenge -- The universal problem, stated in the audience's language\r
  2. The Model -- The transferable structure, with a memorable label\r
  3. The Evidence -- The original experience, reframed as proof of the model\r
  4. The Anchor -- The one sentence to carry away\r \r

Transformation Log\r

\r After the main output, append a brief ## Transformation Log showing the key decisions made during conversion:\r \r

## Transformation Log\r
\r
- **Perspective Flip**: [Original framing] -> [Audience-facing challenge]\r
- **Model Extracted**: [Model name and one-line description]\r
- **Narrative Shift**: [What was de-emphasized vs. elevated]\r
- **Anchor**: "[The one sentence]"\r
```\r
\r
This log helps the user understand and iterate on the transformation.\r
Usage Guidance
This skill appears internally consistent and safe in terms of system access. Before using it, avoid pasting secrets, personal identifiers, or confidential attachments into the input (the skill transforms whatever you supply). Note the skill's source/homepage are not provided — if provenance matters, ask the publisher for more information. Also remember that, like any skill that sends user content to the model, transformed outputs may be stored in conversation logs depending on your platform's data retention policies; confirm privacy/retention settings if you need strict confidentiality.
Capability Analysis
Type: OpenClaw Skill Name: knowledge-forge Version: 1.0.0 The 'knowledge-forge' skill bundle is a purely instructional set of markdown files designed to guide an AI agent through a structured content transformation process (turning personal experience into educational material). It contains no executable code, no network requests, no requests for sensitive data, and no prompt-injection attempts to bypass safety filters or exfiltrate information. The logic is entirely focused on linguistic reframing and structural modeling as described in SKILL.md and its supporting reference files.
Capability Assessment
Purpose & Capability
The name and description (turning experience into teachable assets) match the SKILL.md and reference materials. The skill requests no binaries, env vars, or config paths and contains only instruction and reference docs — nothing extraneous or unrelated is required.
Instruction Scope
SKILL.md contains a self-contained 4-step conversion engine and output templates. It does not instruct the agent to read system files, environment variables, or external endpoints, nor to exfiltrate data. All actions are textual transformations of the user's supplied material.
Install Mechanism
No install spec or code files beyond documentation; nothing will be downloaded or written to disk by the skill itself. This is low-risk from an installation perspective.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate to the described functionality (pure content transformation).
Persistence & Privilege
always is false and the skill does not request or modify agent/system-wide settings. It can be invoked by the model (normal default), but there is no indication of privileged or persistent behavior.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install knowledge-forge
  3. After installation, invoke the skill by name or use /knowledge-forge
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of knowledge-forge skill. - Enables conversion of personal experience, case studies, and business documents into structured, transferable knowledge assets. - Introduces a 4-step conversion engine: Perspective Flip, Experience Modeling, Narrative Reconstruction, and Anchor Design. - Supports multiple output formats (e.g., presentations, course outlines, knowledge cards) based on user input or context. - Final outputs include The Challenge, The Model, The Evidence, and The Anchor, plus a concise Transformation Log for transparency and refinement.
Metadata
Slug knowledge-forge
Version 1.0.0
License
All-time Installs 5
Active Installs 5
Total Versions 1
Frequently Asked Questions

What is knowledge-forge?

Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others... It is an AI Agent Skill for Claude Code / OpenClaw, with 384 downloads so far.

How do I install knowledge-forge?

Run "/install knowledge-forge" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is knowledge-forge free?

Yes, knowledge-forge is completely free (open-source). You can download, install and use it at no cost.

Which platforms does knowledge-forge support?

knowledge-forge is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created knowledge-forge?

It is built and maintained by ANGJustinl (@angjustinl); the current version is v1.0.0.

💬 Comments