expertpack-evalMeasure ExpertPack EK (Esoteric Knowledge) ratio and run automated quality evals. Use when: (1) Measuring what percentage of a pack's content frontier LLMs c...
Install via ClawdBot CLI:
clawdbot install brianhearn/expertpack-evalGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://expertpack.aiAI Analysis
The skill's external API calls to OpenRouter and its own documented domain (expertpack.ai) are consistent with its stated purpose of evaluating AI knowledge packs. While it processes user-provided pack data and sends it to external LLM APIs, this is an explicit, intended function with no evidence of hidden instructions, credential harvesting, or obfuscation.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 22, 2026
An AI research lab uses the skill to evaluate proprietary knowledge packs before integrating them into their agents, ensuring the packs contain novel insights not already present in frontier models. They measure EK ratio to quantify esoteric content and run quality evals to verify agent performance improvements, optimizing research efficiency and intellectual property validation.
A large corporation employs the skill to assess internal knowledge packs built from confidential data, such as proprietary processes or market analyses. By measuring EK ratio, they determine the uniqueness of their knowledge assets and run evals to ensure AI agents deliver accurate, secure responses, enhancing decision-making and compliance.
An educational technology company uses the skill to validate custom learning packs designed for specialized courses, like advanced mathematics or niche sciences. They measure EK ratio to ensure content is not redundant with general knowledge and run evals to test AI tutor agents, improving educational outcomes and content quality.
A healthcare provider leverages the skill to evaluate medical knowledge packs containing up-to-date clinical guidelines or rare disease information. They measure EK ratio to confirm esoteric medical insights and run evals on AI diagnostic agents, ensuring reliability and adherence to regulatory standards before deployment.
Offer the skill as part of a cloud-based platform where users pay a monthly fee to access EK ratio measurement and quality eval tools. This model generates recurring revenue by providing continuous updates, API integrations, and support for enterprises and researchers managing knowledge packs.
Provide expert consulting services to help organizations implement the skill, including custom eval set creation, integration with existing AI systems, and interpretation of results. This model leverages deep expertise to drive high-value projects, with revenue from one-time engagements or retainer contracts.
Offer a free basic version of the skill for individual users or small teams to measure EK ratios, with premium features like advanced analytics, automated reporting, and priority support available for a fee. This model attracts a broad user base and converts high-need customers to paid plans.
💬 Integration Tip
Ensure the OpenRouter API key is properly configured via environment variables or OpenClaw auth to avoid authentication errors during blind probing and eval runs.
Scored Jun 19, 2026
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per t...
Score startup idea through S.E.E.D. niche check + STREAM 6-layer analysis + Devil's Advocate inversion, auto-pick stack, and generate PRD with acceptance cri...
提供基于ultralytics库的YOLO模型加载、推理、训练、验证、导出及目标跟踪功能,并辅以源码解析与示例代码。
另一个TA:输入人名/主题/模糊需求/网络链接/已有Skill,自动深度调研→框架提炼→生成完整 Agent 人设文件包,直接覆盖当前 Agent workspace 的人设文件。 五种入口:(1)明确人名→蒸馏为Agent (2)模糊需求→诊断推荐→再蒸馏 (3)网络链接→基于内容蒸馏 (4)已有Skill→读...