ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

expertpack

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) Opening or authoring a pack in Obsidian. Triggers on: 'expertpack', 'expert pack', 'esoteric knowledge', 'knowledge pack', 'pack hydration', 'obsidian vault', 'obsidian pack'. For CLI tools (ep-validate, ep-doctor, ep-graph-export, ep-strip-frontmatter) install expertpack-cli. 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. For serving any ExpertPack as an MCP endpoint (expertise-as-a-service), see EP MCP at github.com/brianhearn/ep-mcp.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/brianhearn/expertpack
Or

What This Skill Does

The expertpack skill is a specialized framework for managing structured knowledge packs within the OpenClaw ecosystem. It allows AI agents to consume, create, and optimize high-value information packages designed to minimize hallucinations and maximize relevance. By leveraging schema-aware structures, expertpack bridges the gap between generic RAG deployments and bespoke, high-fidelity knowledge retrieval, enabling agents to operate with domain-specific accuracy through optimized content hydration and retrieval layers.

Installation

To integrate this skill, use the OpenClaw command-line interface: clawhub install openclaw/skills/skills/brianhearn/expertpack Ensure that you have your workspace directory configured correctly, typically under ~/expertpacks/, to allow the agent to index your content effectively.

Use Cases

  • Agent Context Loading: Instantly provide an agent with core, searchable knowledge regarding proprietary processes or products.
  • Knowledge Scaffolding: Create new ExpertPacks for complex domains, using EK-aware (Esoteric Knowledge) hydration to ensure the model focuses on rare, non-generative information.
  • RAG Optimization: Deploy schema-aware chunking to improve retrieval correctness by over 9% while significantly reducing token overhead.
  • Workspace Archiving: Backup agent memory and learned insights into a portable, versioned ExpertPack format for cross-agent migration.

Example Prompts

  1. "Load the project-alpha ExpertPack from my workspace and summarize the Tier 1 documentation for today's briefing."
  2. "Hydrate a new product ExpertPack for our internal API using the files in /docs/v2, focusing on the specialized authentication process."
  3. "Run the schema-aware chunker on my 'client-onboarding' pack and update the .chunks directory for my RAG config."

Tips & Limitations

To maximize the utility of ExpertPacks, prioritize Tier 2 (searchable) documentation for core data and keep Tier 3 (on-demand) content for exhaustive transcripts. Always use the companion expertpack-eval skill if you are measuring the Esoteric Knowledge (EK) ratio, as this provides critical insights into your agent's knowledge depth. Note that improper schema adherence in manifest.yaml will result in failed indexing; ensure you follow the structure provided in the documentation schemas.

Metadata

Stars4190
Views0
Updated2026-04-18
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-brianhearn-expertpack": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#knowledge-management#rag#agent-context#data-structuring#productivity
Safety Score: 4/5

Flags: file-write, file-read, code-execution

Related Skills

elite-to-expertpack

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'.

brianhearn 4190

expertpack-cli

Run ExpertPack CLI tools for validating, fixing, graphing, and deploying packs. Use when: running ep-validate, ep-doctor, ep-graph-export, ep-strip-frontmatter, or ep-fix-broken-wikilinks on a local pack. Triggers on: 'validate pack', 'ep-validate', 'ep-doctor', 'fix pack errors', 'graph export', 'ep-graph-export', 'strip frontmatter', 'deploy pack', 'ep-strip-frontmatter'. Requires the ExpertPack repo cloned locally (github.com/brianhearn/ExpertPack) — tools live in tools/validator/.

brianhearn 4190

expertpack-eval

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.

brianhearn 4190

self-improving-to-expertpack

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'.

brianhearn 4190

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'.

brianhearn 4190