AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
Use when the user adds, changes, or refactors an LLM agent under src/agents/ — or anything that goes through Foundation Model API or an MLflow-traced LLM call. Mandatory under CNS §3.5 and .cursor/12-ai-feature-lifecycle.mdc. Walks the SPEC → dataset → eval-harness → impl → re-eval sequence.
Use when the user asks for a code review, asks to "review the code", or requests review of a feature/PR/branch. Runs the OntoBricks review checklist defined in .cursorrules.
Use when the user asks to deploy, ship, release, or push OntoBricks to Databricks. Wraps the Databricks Asset Bundle deploy for the FastAPI app and the MCP server, with the bootstrap-perms safety net described in README.md.
This file documents the actual design conventions in the codebase, not aspirations. The two structural rules ("no inline CSS/JS in templates", "shared assets under front/static/") live in 05-code-style-and-structure.mdc § Frontend (HTML/CSS/JS). This file covers visual language, components, naming and asset wiring.
Claude Code instructions for databrickslabs/ontobricks, covering claude.md — operating contract for ontobricks, imported canonical rules, claude-only additions, skills (auto-invoked by description) and databricks-related work.
The assistant MUST proactively avoid the following pitfalls when creating or modifying any ontology. Check each applicable rule before proposing or applying changes, and warn the user if a requested change would introduce one of these pitfalls.
Runs before the agent uses a tool for Bash, Read and Glob tool calls, running /Users/haideri/.local/share/uv/tools/graphifyy/bin/graphify (2 commands). From EBISPOT/ols4.
101 5d agoA
tokens not measured
originalApache-2.0
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Natively ingest Mattermost into the epistemic-graph knowledge graph via the mattermost-mcp MCP server — push teams, channels and users as typed :Team/:Channel/:Person nodes, messages as :Document nodes, and file attachments as :MediaAsset blobs, in one ACID path. Use when the agent must make a Mattermost workspace…
0 5d agoA119 tokens
originalMIT
At most 3 mods per repository are shown here — the rest are on their repository pages: