ontology-extract

# Extract ontology from prose `/ontology-sync` follows code changes. This skill follows human prose: meeting notes, RFCs, pull-request descriptions, chat logs, or pasted wiki paragraphs. The vault is the Markdown folder whose files and typed frontmatter form the graph. ## Run when - the user explicitly asks to turn supplied prose into ontology; - the user requests extraction from an RFC, meeting note, PR, wiki, or chat that states a codebase concept. Pasted prose alone is not an extraction request; follow the requested task. Skip personal notes without domain/capability/element concepts, summary-only requests, and prose already living inside the target vault node. ## 1. Read prose and the existing vault together ```text list_kinds find_evidence(title) query_ontology({ operation: "similar_nodes", candidateSlug, title }) ``` Extract candidate nouns and verb phrases, then search before proposing. The most common failure is creating “user login” beside an existing `auth-login` node. A similarity score at or above 0.3 is a prompt to consider patching the existing node; lower scores support a new candidate but do not decide it automatically. ## 2. Classify a small candidate set One paragraph normally yields zero to three candidates. More than five means the input is too broad or the extraction is too eager. | Prose shape | Likely kind | Example | |---|---|---| | a new user ability | `capability` | “members can reset a password” → `capabilities/password-reset` | | a lib...