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.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "expertpack-eval" with this command: npx skills add brianhearn/expertpack-eval

ExpertPack Eval

Measure and evaluate ExpertPack quality. Companion to the core expertpack skill.

Note: This skill makes external API calls to OpenRouter for blind probing and LLM-as-judge scoring. Requires an API key.

1. Measure EK Ratio

Blind-probe frontier models to measure what percentage of a pack's propositions they cannot answer without the pack loaded:

python3 {skill_dir}/scripts/eval-ek.py <pack-path> [--models model1,model2] [--sample N] [--output FILE]
  • Default models: GPT-4.1-mini, Claude Sonnet 4.6, Gemini 2.0 Flash (via OpenRouter)
  • API key: Auto-resolves from OpenClaw auth profiles or OPENROUTER_API_KEY env var
  • Judge model: Claude Sonnet (GPT-4.1-mini is unreliable as judge — defaults to "partial")
  • Output: YAML with per-proposition scores and aggregate ratio

Interpretation:

EK RatioMeaning
0.80+Exceptional — almost entirely esoteric
0.60–0.79Strong — majority esoteric
0.40–0.59Mixed — significant GK padding
0.20–0.39Weak — most content already in weights
< 0.20Minimal value-add

Add measured ratio to manifest.yaml:

ek_ratio:
  value: 0.72
  measured: "2026-03-12"
  models: ["gpt-4.1-mini", "claude-sonnet-4-6", "gemini-2.0-flash"]
  propositions_tested: 142

2. Run Quality Eval

Automated eval against a pack-powered agent endpoint:

python3 {skill_dir}/scripts/run-eval.py \
  --questions <eval-set.yaml> \
  --endpoint <ws://host:port/path> \
  --output <results.yaml> \
  --label "baseline"
  • Build eval set: 30+ questions (basic, intermediate, advanced, out-of-scope)
  • Fix one dimension at a time: structure → agent training → model
  • Re-run after each change to verify improvement

Learn more: expertpack.ai · GitHub

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Research

Batch Content Factory

Multi-platform content production line. Automates the entire workflow from topic research to content creation. Suitable for self-media operators producing hi...

Registry SourceRecently Updated
Research

Fund Analyzer Pro

[何时使用]当用户需要基金深度分析时;当用户说"分析这个基金""基金对比""基金诊断""基金经理分析"时;当检测到基金代码/基金名称/投顾策略时触发。整合天天基金 API+ 且慢 MCP,提供单一基金分析/基金比较/基金诊断/持仓诊断/基金经理/机会分析/投资方式/报告信号八大模块。新增信号监控提醒功能(sign...

Registry SourceRecently Updated
Research

FN Portrait Toolkit

Financial report footnote extraction and analysis tool for Chinese A-share listed companies. Use when: (1) User wants to extract financial note data from ann...

Registry SourceRecently Updated
Research

流式AI检索问答技能

通用流式AI检索问答技能 — 为任意行业应用提供四步流式分析交互界面。 触发场景:用户输入关键词 → AI自动执行:理解意图 → 检索知识库 → 流式生成 → 来源标记 → 完整回答。 当需要实现以下任意场景时激活: (1) AI搜索框 / 智能咨询组件重构 (2) 知识库问答(医疗/法律/金融/教育等垂直领域)...

Registry SourceRecently Updated