# Bkn Methodology

> Shared OpenBKN modeling methodology. Use when reviewing BKN object boundaries, relation semantics, facts, metrics, actions, governance points, evidence, traceability, or Skill / Agent responsibility boundaries.

- Skill: `openbkn-ai/bkn-methodology` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add openbkn-ai/bkn-methodology`
- Raw SKILL.md: https://api.skillmd.com/api/skills/openbkn-ai/bkn-methodology/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: openbkn-ai (https://skillmd.com/u/openbkn-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/openbkn-ai/bkn-methodology

---


# BKN Methodology

Use this skill as the common modeling rule base for OpenBKN projects.

Read `references/bkn-methodology.md` before making or reviewing BKN modeling decisions.

## Use When

- Deciding whether a concept should be an object, property, fact, state, metric, action, or governance point.
- Reviewing whether a relation expresses a business path rather than a field join.
- Separating stable facts from runtime state and audit records.
- Clarifying the boundary between query, calculation, explanation logic, Skill / Agent work, and side-effecting actions.
- Checking whether evidence, traceability, permissions, approvals, and human confirmation points are represented correctly.

## Output

Return concise modeling guidance with:

1. Recommended classification.
2. Reasoning.
3. Boundary risks.
4. Questions that must be answered before BKN creation.