world-model-diagnostic

Runs a structured diagnostic to assess your company's BigQuery usage and needs.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/Greyborne/OB1-Canobi --skill world-model-diagnostic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: world-model-diagnostic
Source: https://github.com/Greyborne/OB1-Canobi/tree/main/skills/world-model-diagnostic
Command: npx skills add https://github.com/Greyborne/OB1-Canobi --skill world-model-diagnostic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you determine whether your company is ready for a world model by exposing where reality becomes interpretation, where signal fidelity lives, and what you should build first without relying on misleading numeric readiness scores.

Core Features & Use Cases

  • 20-minute company interview: Runs a lightweight diagnostic to gather company context, signal sources, decision ownership, and outcome recording.
  • Paradigm mapping: Maps the company to the right world-model paradigm (vector database, structured ontology, or signal-fidelity) using signal fidelity and boundary complexity cues.
  • Boundary-layer audit: Audits 5–10 concrete information flows and labels each as act on this versus interpret this first, including where human editors are missing and the exposure level to simulated judgment.
  • Labeled conclusions: Labels every conclusion as Firm finding, Inference, or Open question to keep evidence and synthesis separate.
  • Optional OB1 persistence: When Open Brain tools exist, persists exactly three lean artifacts (intake, boundary audit, assessment) for compounding diagnostics over time.
  • Starting sequence: Produces a first/second/third build sequence focused on boundary clarity, outcome encoding, and paradigm-specific retrieval/structure.

Quick Start

Ask your AI client to run the World Model Diagnostic on your company and insist it returns paradigm fit, boundary-layer status, top simulated-judgment exposures, and a first/second/third build sequence without any numeric readiness score.

Frequently Asked Questions about world-model-diagnostic

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit my company's readiness for a world model without misleading numeric scores?

To audit world model readiness without numeric scores, run a diagnostic interview exposing where reality becomes interpretation, mapping signal fidelity and the boundary layer between facts and interpretation to determine paradigm fit.

What is the boundary layer in world model planning and when do I need to audit it?

The boundary layer is where facts transition into interpretation during information flow. You need to audit it when planning a world model to identify missing human editors and exposure to simulated judgment before building.

How do I select the right world model paradigm for my company?

To select a world model paradigm like vector database, structured ontology, or signal-fidelity, map your company using signal fidelity cues and boundary complexity gathered during a lightweight diagnostic interview.

Can I use this world model diagnostic for enterprise planning or is it only for startups?

You can use this diagnostic for both startup and enterprise planning. It applies to any organization needing paradigm selection, information-flow audits, and a build-first sequence based on evidence rather than readiness scores.

How do I plan a build sequence for a world model based on evidence?

To plan an evidence-based build sequence, complete a boundary-layer audit and signal ranking first. This produces a first, second, and third build step focused on boundary clarity, outcome encoding, and paradigm-specific retrieval.

Why do information flow audits label conclusions as firm findings, inferences, or open questions?

Information flow audits label conclusions as firm findings, inferences, or open questions to keep evidence and synthesis strictly separate, ensuring your world model planning relies on high-fidelity signal rather than mixed interpretation.