dunk

Internal agent — dispatched by the DLN orchestrator when a new domain has no syllabus. Not user-facing. Researches the domain using web search, context7, and available MCP services, generates a comprehensive flat topic list, writes it to the Notion page body, and returns the list to the orchestrator for user review. All research context stays in the subagent — only the topic list returns to the main session.

Internal agent — dispatched programmatically by DLN phase skills (dln-dot, dln-linear, dln-network) at teaching boundaries. Not user-facing. Handles all Notion MCP calls for the DLN running ledger: replacing Knowledge State blocks, appending progress notes, reading back page content, and updating column properties. Compresses raw read-back into a re-anchor payload using the preloaded dln-compress skill format.

Internal format specification for the DLN system. Only relevant when preloaded by the dln-sync agent via the skills frontmatter field. Never activated by user prompts. Defines the re-anchor payload compression template that dln-sync uses to convert raw Notion page-body read-backs into compact structured summaries for DLN teaching skills.

This skill should be used when the DLN orchestrator routes a learner whose Phase is Dot, or when a user wants to learn a domain from scratch with no prior knowledge. Covers foundational concept delivery (70% teaching / 30% elicitation), causal chain building, worked examples, and phase gate assessment. Triggers: DLN orchestrator determines Phase = Dot, or user says "I know nothing about [domain]", "start from zero", "teach me the basics of [domain]".

This skill should be used when the DLN orchestrator routes a learner whose Phase is Linear, or when a user explicitly requests a Linear session. Guides factor discovery (50% delivery / 50% elicitation) — finding shared structures across procedural chains and transforming them into transferable principles. Triggers: DLN orchestrator determines Phase = Linear, or explicit requests like "run a Linear session on [topic]", "help me find factors across my chains", "find patterns across my [domain] chains", "what do my [domain] chains have in common".

This skill should be used when the DLN orchestrator routes a learner whose Phase is Network, or when a user explicitly requests a Network session. Stress-tests and compresses the learner's mental model (20% delivery / 80% elicitation) against edge cases, counterexamples, and cross-domain analogies. Triggers: DLN orchestrator determines Phase = Network, or explicit requests like "run a Network session on [topic]", "stress-test my model of [domain]", "compress my understanding of [domain]".

This skill should be used when the user wants to learn a new domain from scratch using structured cognitive phases, or when they say "dln", "dln list", "dln reset [domain]", "learn [domain]", "teach me [domain] from zero", "cold-start [domain]", "start learning [domain]", "continue learning [domain]", "resume [domain]", "pick up [domain]", "review [domain]", or reference the Dot-Linear-Network framework. It orchestrates three phase skills (dln-dot, dln-linear, dln-network) based on the learner's current phase stored in a Notion database, routing them to the appropriate learning protocol for their level of understanding.

1 hook across 1 event