菜单
Generate evaluation questions about MadGraph and related tools with verified reference answers, using web research for real-world use cases.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Install the MadAgents agent system into a folder on this machine, to be run without a container. Use when the user wants MadAgents outside Apptainer — in a project folder, on a login node, or anywhere they already have MadGraph — or wants to refresh an existing install.
Find documentation problems that caused agent mistakes — gaps, inaccuracies, or ambiguities. Uses grade context to guide diagnosis.
Edit MadGraph documentation with parallel review: style, quality, and factual verification. Revises until all checks pass or max rounds reached.
Get a writable copy of the MadGraph documentation.
Run one iteration of the doc improvement loop: generate or accept questions, answer them in parallel, verify, grade, diagnose, fix the docs, and re-evaluate until convergence.
Extract factual claims from text and verify each one using execution, source inspection, or physics reasoning.
| name | generate-questions |
| description | Generate evaluation questions about MadGraph and related tools with verified reference answers, using web research for real-world use cases. |
Generate realistic questions that a particle physicist would ask about MadGraph and related tools (e.g. Pythia8, Delphes, MadSpin, MadWidth, MadAnalysis).
$ARGUMENTS
Parse key=value pairs from the input. All are optional — use defaults if not specified.
count=5focus=NLO matchingrequirements=must include exact commandsdedup=/workspace/existing.jsonDo NOT tailor questions to any specific documentation. The goal is to capture what users genuinely need help with.
Every question MUST include a reference_answer — a concise summary of the correct answer, used as ground truth during evaluation.
Write a JSON array (default: questions.json). The file must contain ONLY the JSON array — no markdown fences, no commentary, no explanation.
[
{
"text": "The full question text",
"reference_answer": "Concise correct answer with key facts, commands, and parameter names."
}
]
After writing, verify:
text and reference_answer strings