This skill should be used when the Learner Calibrator has produced the gap map and a learning plan needs designing. Applies 4C/ID whole-task instruction, Elaboration Theory epitome design, productive failure placement, and a seven-layer motivation architecture. Produces a sequenced curriculum with task classes, a dual-timeline schedule, assessment criteria, and plateau protocols. Includes a conversational checkpoint for epitome refinement with the learner. Output is structured JSON conforming to learning-plan.schema.json.
This skill should be used when the Skill Researcher has produced a dependency graph and the learner's existing knowledge needs mapping. Walks through the graph conversationally, assessing mastery at key nodes using graph propagation and information-theoretic item selection to minimize questions needed. Produces the knowledge graph overlay (the 'gap map') that drives curriculum design. Output is structured JSON conforming to knowledge-graph.schema.json.
The entry point and router for the meta-learning plugin system. Use this skill whenever a user wants to learn a new skill, continue a learning program, or interact with any part of the meta-learning system. It detects the current pipeline phase, routes to the appropriate component skill, manages state files, handles calibration loops, and ensures smooth handoffs between components. This skill should be triggered by any learning-related request: 'I want to learn X', 'let's do a training session', 'continue my learning', 'show me my progress', 'update my plan', or any reference to an ongoing learning engagement.
This skill should be used when the user's learning goal has been classified by the Domain Assessor and needs deep investigation. Performs skill deconstruction into components, dependency graph construction, frequency/impact analysis, transfer pathway identification, failure point cataloging, and expert panel discovery. Uses web search extensively to ground decomposition in real expert perspectives. Output is a Skill Research Dossier conforming to skill-dossier.schema.json.
This skill should be used when a learner is ready for a training session — they've been through the assessment/research/calibration/curriculum pipeline and have a learning plan, or when the user invokes '/train'. Manages session flow (warm-up, deliberate practice, integration), adaptive teaching using Socratic questioning and the EMT escalation ladder, real-time difficulty calibration, in-session retrieval probes, mastery gate assessments, knowledge graph updates, external data integration (Anki, self-reports), plateau detection, motivation management, instructor persona adoption, and mentor conversation mode. Sessions are scoped to ~150k tokens. State is read at session start and written at session end.
This skill should be used when the Curriculum Architect has produced a learning plan and learning materials need generating, or on-demand when the Training Conductor needs new materials, or when the user invokes '/materials'. Orchestrates dedicated subagents to generate worked examples with fading, visual materials, SRS flashcard decks, assessment instruments, reference one-pagers, dependency graph visualizations, productive failure scenarios, interleaved practice sets, and encoding aids. All outputs conform to the system's JSON schemas and are exportable to Anki (.apkg), PDF, and Markdown.
This skill should be used when the learning plan has been created (initial generation) or after each training session (update), or when the user asks to see their progress or dashboard. Generates and updates a React dashboard artifact that visualizes the learner's knowledge graph, curriculum progress, and key metrics. The dashboard is the learner's visual home base within the Claude Project, rendering an interactive knowledge graph with mastery overlay, curriculum roadmap, progress metrics, session history, and upcoming agenda.
This skill should be used when the user states a learning goal — any phrase like 'I want to learn X', 'teach me X', 'help me get better at X', or 'how do I learn X'. Classifies the skill type (motor/cognitive/perceptual/social), assesses the learning environment (kind vs. wicked), gathers the learner's background for transfer learning, and produces a constructive approach strategy. This is always the first step in the meta-learning pipeline. Output is structured JSON conforming to domain-assessment.schema.json.