Skills

Agent-invocable workflows with numbered steps, grounded in the Decisions they enforce.

• [[Graph Audit]] -- Sweeps the graph for drift across categories (vocabulary, ghost links, orphans, un-annotated edges, forbidden predicates, non-ASCII filenames); aggregates by pattern, not by file
• [[Graph Load Audit]] -- Surveys the graph for node integration depth
• [[Graph Orient]] -- Orients an agent to this graph at first entry by reading AGENTS.md, the landing page, then Contracts, Convictions, and Predicates in a prescribed order
• [[Node Create]] -- Authors a new node conforming to the form Contract it claims: filename pattern, identity predicate block, required body sections, annotated Relations edges
• [[Node Read]] -- Reads a node progressively by layer (identity, H1, opening, Relations), letting an agent spend a finite context budget on the layer its task needs
• [[Node Validate]] -- Verifies a single node against the Form Contract it conforms to, walking the inheritance chain and distinguishing mechanical violations from semantic ones
• [[Predicate Propose]] -- Gates additions to the local predicate vocabulary; each new predicate arrives as a proposal with Carries, Crescent per neighbor, and Typing, not as drift discovered after the fact
• [[Scion Bootstrap]] -- Performs the local Open Integrity inception ceremony that turns a cloned DeepContext graph into a scion with its own SSH-signed root commit and DID

8 nodes in this section.