World Model Diagnostic
Twenty-minute conversational diagnostic for assessing a company's world-model readiness.
Install
npx skills add NateBJones-Projects/OB1 --skill world-model-diagnostic -g -a claude-code -y- Repository
- NateBJones-Projects/OB14.8k
- Category
- Engineering
- Updated
- 3d ago
- License
- See repository
- Context cost
- Mediumabout 2,344 tokens
- Runs scripts
- No, instructions only
What it does
Twenty-minute conversational diagnostic for assessing a company's world-model readiness. Use when the user wants to map their company to the right world-model paradigm, identify where the highest-fidelity signal lives, audit the boundary layer between facts and interpretation, flag simulated-judgment exposure, and leave with a first/second/third build sequence. Works in plain chat and compounds when Open Brain search/capture tools are present.
World Model Diagnostic
Purpose
Your job is not to hand back a polished readiness score. Your job is to expose where information routing ends and editorial judgment begins, then recommend the smallest credible starting sequence.
This diagnostic exists to answer five questions:
- Where does reality leave the clearest fingerprint in this business?
- Which world-model paradigm fits the company right now?
- Does the company have an explicit boundary layer?
- Where is it most exposed to simulated judgment?
- What should it build first, second, and third?
Modes
Run in one of two modes:
OB1-connected mode: if Open Brain search/capture tools are available, use them to look for prior context and persist the intake, boundary audit, and final assessment.Direct-chat mode: if those tools are missing, run the exact same diagnostic and clearly say that the output is not being persisted.
Preferred Tools
Before starting, identify whether the current client exposes:
- a base Open Brain search tool, usually
search_thoughts - a base Open Brain capture tool, usually
capture_thought
Do not assume exact prefixes. Use the tool names visible in the client.
If search is available:
- run 2-4 narrow queries such as
world model,boundary layer, the company name, or obvious strategic context - treat every result as a hint, not as a confirmed fact
If capture is available:
- tell the user you will persist three lean artifacts unless they ask you not to:
- intake summary
- boundary audit summary
- final assessment
