expert-pack

Work with ExpertPacks — structured knowledge packs for AI agents. Obsidian-compatible: every pack is a valid Obsidian vault with Dataview support. Use when: (1) Loading/consuming an ExpertPack as agent context, (2) Creating or hydrating a new ExpertPack from scratch, (3) Configuring RAG for a pack, (4) Validating or fixing a pack with the CLI tools, (5) Opening or authoring a pack in Obsidian. Triggers on: 'expertpack', 'expert pack', 'esoteric knowledge', 'knowledge pack', 'pack hydration', 'validate pack', 'ep-validate', 'ep-doctor', 'obsidian vault', 'obsidian pack'. For EK ratio measurement and quality evals install expertpack-eval. For exporting an OpenClaw agent as an ExpertPack install expertpack-export. For converting an existing Obsidian Vault into an ExpertPack install obsidian-to-expertpack.

Convert an existing Obsidian Vault into an agent-ready ExpertPack. Restructures vault content for EK optimization, RAG retrieval, and OpenClaw integration. Creates a copy — source vault is never modified. Use when: a user wants to make their Obsidian Vault usable by AI agents, convert OV to EP, drop their vault into OpenClaw as a knowledge pack, or make their notes RAG-ready. Triggers on: 'obsidian to expertpack', 'obsidian vault to ep', 'convert obsidian', 'OV to EP', 'obsidian agent ready', 'make my vault ai ready', 'obsidian knowledge pack', 'obsidian rag'.

Measure ExpertPack EK (Esoteric Knowledge) ratio and run automated quality evals. Use when: (1) Measuring what percentage of a pack's content frontier LLMs cannot produce on their own, (2) Running automated eval sets against a pack-powered agent with LLM-as-judge scoring. Requires OpenRouter API key (auto-resolved from OpenClaw auth or OPENROUTER_API_KEY env var). Companion to the main expertpack skill. Triggers on: 'EK ratio', 'measure EK', 'blind probe', 'eval expertpack', 'pack quality eval', 'run eval', 'esoteric knowledge ratio'. Note: packs are Obsidian-compatible — eval results (ek_score) can be added to file frontmatter and queried in Obsidian via Dataview.

Export an OpenClaw instance's accumulated knowledge into a structured ExpertPack composite. Use when backing up an agent's identity, exporting for migration, or creating a portable knowledge snapshot. Handles auto-discovery (scanning workspace state to identify constituent packs), distillation (compressing raw state into structured EP files), and packaging (writing EP-compliant packs + composite manifest). Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. NOT for importing/hydrating from an existing EP.

Convert an Ontology skill knowledge graph into a structured ExpertPack. Use when migrating from the Ontology skill's entity/relation graph (memory/ontology/graph.jsonl) to ExpertPack's richer format with multi-layer retrieval, EK measurement, and portable deployment. Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. Triggers on: 'ontology to expertpack', 'convert ontology', 'export ontology', 'migrate ontology', 'ontology graph to pack', 'upgrade ontology'. Requires the Ontology skill's graph.jsonl and optionally schema.yaml.

Convert Elite Longterm Memory data into a structured ExpertPack. Migrates the 5-layer memory system (SESSION-STATE hot RAM, LanceDB warm store, Git-Notes cold store, MEMORY.md curated archive, and daily journals) into ExpertPack's portable format with multi-layer retrieval, context tiers, and EK measurement. Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. Use when: upgrading from Elite Longterm Memory to ExpertPack, backing up agent knowledge, or migrating to a new platform. Triggers on: 'elite to expertpack', 'convert elite memory', 'export elite memory', 'migrate elite longterm', 'upgrade memory to expertpack', 'elite memory export'.

Convert Self-Improving Agent learnings into a structured ExpertPack. Migrates the .learnings/ directory (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md) and any promoted content from workspace files into ExpertPack's portable format with multi-layer retrieval, context tiers, and EK measurement. Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. Use when: upgrading from Self-Improving Agent to ExpertPack, backing up agent learnings, exporting accumulated knowledge, or migrating to a new platform. Triggers on: 'self-improving to expertpack', 'convert self-improving', 'export learnings', 'migrate self-improving', 'learnings to expertpack', 'convert learnings to pack'.