claude-config

Convene a dialectic expert-panel review (the Linked Data Council Hive) on an ontology/ADR/ODR proposition or a set of outstanding questions, then produce a session record. Use when a modelling decision has a credible split, a contested mapping or identity-criterion question needs adjudicating, or a precedent needs recording. Spawns a SCOPED panel via the Agent tool (Queen + Devil's Advocate + only the relevant experts), collects per-question verdicts, writes the synthesis, and routes dispositions to the ODRs/ADRs.

Create professional diagrams using Mermaid or DOT/Graphviz. Mermaid for flowcharts, sequences, classes, ER, Gantt, architecture with semantic coloring and WCAG AA accessibility. DOT/Graphviz for pure network graphs, semantic webs, and maximum layout control.

Lint ODR frontmatter, section structure, and references against the DCAP profile

Create a new Ontology Decision Record (ODR) with sequential numbering and AgentDB registration

Build or rebuild the ODR index and dependency graph in AgentDB (strict mode — unified MADR DCAP: 6 required + 3 optional frontmatter keys, MADR body spine, matching odr-create / odr-review)

Create a new Architecture Decision Record with sequential numbering (ADR- prefixed filename) and AgentDB registration

Build or rebuild the ADR index and dependency graph in AgentDB (strict mode — Phase 3 corpus, ADR- prefix filenames, no legacy fallbacks)

Export Mermaid diagrams from documents to PNG images. MUST be run immediately after creating or editing any Mermaid diagram, BEFORE committing. Processes .md, .html, .mdx, .rst, .adoc files.

Export DOT/Graphviz diagrams from documents to PNG images (default) or SVG. Use after creating documents with DOT code blocks when you need to render them as static images for distribution, GitHub, wikis, or static sites. Supports multiple layout engines (dot, neato, circo, fdp, twopi, osage, patchwork). Processes .md, .html, .mdx, .rst, .adoc files.

Markdown formatting rules and validation. Use when editing or creating .md files to ensure correct blank line placement around blocks, lists, and headings.

Create professional Jupyter notebooks with zero-execution styling using markdown-based CSS and HTML components following Airbnb DLS principles.

Design and implement OWL 2 ontologies for knowledge representation. Covers RDFS foundations, OWL profiles (EL, QL, RL), class expressions, property characteristics, reasoning patterns, SKOS taxonomies, and the evolving shift toward SHACL. Informed by Kurt Cagle's ontologist perspective.

Query, configure, and optimize QLever—the high-performance open-source RDF triplestore. Covers SPARQL queries, GeoSPARQL, text search, CLI operations, and public endpoints. Informed by Kurt Cagle's semantic web expertise.

Design, implement, and validate RDF data with SHACL (Shapes Constraint Language). Covers node shapes, property shapes, constraint components, validation reports, SHACL-SPARQL integration, AI/LLM patterns, UI generation, and taxonomy integration. Informed by Kurt Cagle's ontologist perspective and W3C specifications.

Design, implement, and manage knowledge organization systems with SKOS (Simple Knowledge Organization System). Covers concept schemes, taxonomies, thesauri, controlled vocabularies, semantic relations, mapping, SKOS-XL labels, AI/LLM integration patterns, and SHACL validation. Informed by Kurt Cagle's ontologist perspective and W3C specifications.

Write, analyze, and optimize SPARQL 1.1 queries for knowledge graphs. Covers RDF, OWL, SHACL, Turtle serialization, and AI/LLM integration patterns. Informed by Kurt Cagle's ontologist perspective.