LLM Evaluation Harness
大模型评估技能，使用 lm-evaluation-harness 在 MMLU、HumanEval、GSM8K 等基准上系统评测模型能力。
LLM Evaluation Harness is an Agent skill for Data & Visualization. 大模型评估技能，使用 lm-evaluation-harness 在 MMLU、HumanEval、GSM8K 等基准上系统评测模型能力。 Tags: 评估 · evaluation · MMLU · HumanEval · GSM8K · 基准.
What is LLM Evaluation Harness
LLM Evaluation Harness packages a Data & Visualization workflow for agents. 大模型评估技能，使用 lm-evaluation-harness 在 MMLU、HumanEval、GSM8K 等基准上系统评测模型能力。
Install LLM Evaluation Harness in Cursor / Claude / Codex
Claude Code Install with the command on this page, or place the skill in ~/.claude/skills or project .claude/skills so Claude can detect LLM Evaluation Harness.
Cursor After the install command writes the skill directory, invoke LLM Evaluation Harness by name in the Cursor agent.
Codex Install into the Codex skills directory and call it by name. If only a generic command is listed, run it locally and confirm Codex can see the skill.
One-click Install
Run the following command in your terminal to install the skill into your AI agent:
npx skillsadd obra/superpowersHow to Use
Claude Code: Place the skill in ~/.claude/skills (personal) or the project .claude/skills directory, and Claude will auto-detect it.
Cursor / Windsurf: After installing via npx skillsadd, the skill directory is placed in the configured path.
Codex CLI: After installation it loads automatically from the skills directory and is invoked by name.
Tags
Similar recommendations
Data Analysis
数据分析技能，使用 Python（pandas / numpy）清洗、转换与统计分析结构化数据，输出洞察与可视化图表。
Diagram Generator
图表生成技能，将文字描述转化为 Mermaid、PlantUML 与 Excalidraw 流程图、架构图与时序图。
Financial Research
金融研究技能，抓取财报、行情与宏观数据，进行估值建模、趋势分析与风险测算，输出结构化研报。
Finance Report Generator
财务报表生成技能，将原始账目数据转换为资产负债表、利润表与现金流量表，附带财务比率分析。
Structured Data Capture
结构化数据采集技能，从非结构化文本（合同、发票、邮件）中提取字段并输出 JSON / CSV，支持自定义 Schema。
Supabase Postgres Best Practices
Supabase Postgres 最佳实践技能，涵盖 Row Level Security、索引优化、全文检索与实时订阅的性能调优。
FAQ
What is LLM Evaluation Harness for?
LLM Evaluation Harness is a Data & Visualization skill. 大模型评估技能，使用 lm-evaluation-harness 在 MMLU、HumanEval、GSM8K 等基准上系统评测模型能力。
Can Claude, Cursor, and Codex all use LLM Evaluation Harness?
Yes if the client supports Agent Skills and has loaded the skill directory. Check the project home for compatibility notes.
What similar skills exist?
Related items come from the same Data & Visualization group so you can pick a closer workflow.