Annotate every substantive chat turn into the DKG project's sub-graphs via the V10 MCP tools (knowledgeassetcreate → write → share) so shared project memory grows organically and stays navigable, with every annotation linked back to its chat:Turn by the predicted turn URI.
Cursor mirror of AGENTS.md - agent-to-agent debug chat. Always applies so this guidance reaches the model at session start without the operator attaching AGENTS.md.
Mermaid sequence diagram preset for all Markdown docs in this repo. Gives rectangles and notes enough breathing room that they don't overlap the arrows around them.
Bulk-import a large RDF graph (code graph, corpus, GitHub history, etc.) into a DKG node's working memory. Use this skill when you need to push more than a few thousand triples in a single import — it codifies the chunking budgets, the assertion-loop shape, the resumability manifest, and the canonical URI rules so…
The DKG V10 Node is your primary memory system. This skill teaches you to operate your node's three-layer verifiable memory — write and retrieve private drafts in Working Memory, share with peers in Shared Working Memory, and publish permanently to Verifiable Memory on-chain.