Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/madgraphteam/madagents/generate-questionsnpx skills add MadGraphTeam/MadAgents --skill generate-questionsgit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/madgraphteam/madagents/generate-questions)<a href="https://agentmods.dev/skills/madgraphteam/madagents/generate-questions"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/generate-questions.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.00570 |
| Opus 5 | $0.00014 | $0.00285 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
generate-questions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Evaluation Questions
Generate realistic questions that a particle physicist would ask about MadGraph and related tools (e.g. Pythia8, Delphes, MadSpin, MadWidth, MadAnalysis).
Parameters
$ARGUMENTS
Parse key=value pairs from the input. All are optional — use defaults if not specified.
- count: Number of questions (default: 10). Example:
count=5 - focus: Topic area. Example:
focus=NLO matching - requirements: Extra constraints. Example:
requirements=must include exact commands - dedup: Path to existing questions file to avoid duplicates. Example:
dedup=/workspace/existing.json
Goal
- Search the web for real-world use cases: forum posts (Launchpad, MadGraph mailing list), HEP Stack Exchange, tutorials, conference proceedings, and papers that describe MadGraph/Pythia8/Delphes workflows. Focus on what users actually struggle with.
- Generate questions based on what real users need — common workflows, pitfalls, misconfigurations, advanced features, and edge cases. Questions may involve MadGraph alone or in combination with related tools.
Do NOT tailor questions to any specific documentation. The goal is to capture what users genuinely need help with.
Requirements
- Questions must be self-contained (no references to "the above" or prior context).
- If a dedup file was given, check each candidate question against existing ones and skip near-duplicates.
Reference Answers
Every question MUST include a reference_answer — a concise summary of the correct answer, used as ground truth during evaluation.
- State the key facts: the correct approach, relevant commands, and important parameter names.
- Keep it brief — a few sentences to a short paragraph. The evaluation pipeline independently verifies claims, so exhaustive detail is not needed.
- Base answers on your knowledge. Use web search only to confirm specific details you are unsure about.
Output
Write a JSON array (default: questions.json). The file must contain ONLY the JSON array — no markdown fences, no commentary, no explanation.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 61 lines · 27 tokens per session scan A e831c310adf4
generate-questions is a skill published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 570 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
proof-writer
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
tooluniverse-organic-chemistry
Organic chemistry reasoning guide for reaction product prediction, mechanism analysis (electrophilic/nucleophilic substitution, addition, elimination, pericyclic, radical), and spectroscopy interpretation (1H/13C NMR, IR, MS). Reasons from first principles (electron flow, kinetic vs thermodynamic) rather than…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…
edu-chem-reaction
把一个化学反应做成自包含的微观 3D 交互演示网页：左/上为 Three.js 可交互分子动画 （拖滑块看断键·成键·原子重组，分步高亮），右为 KaTeX 反应方程 + 分步讲解 + 原子守恒计数 + 可选能量-反应进程曲线。支持三入口——给定文字反应/方程、随机出题、上传图片识别后演示。 覆盖燃烧、化合/分解/置换/复分解、氧化还原（电子转移可视化）、有机机理（酯化等含催化剂·过渡态）。 统一由 sympy 精确驱动：自动配平方程、校验原子守恒与原子映射、推导键的断/成，答案与几何同源一致。 内置两套引擎并自动选择：morph（原子变形，展示原子守恒）与 mechanism（机理关键帧，展示催化/过渡态）。 混合几何：默认自建…
edu-solid-geometry
把一道立体几何题解成一个自包含的交互教学网页：左侧 MathJax 分步解析， 右侧 Three.js 可交互 3D 模型（分步高亮 + 镜头切换）。支持三种入口——给定文字题目、 随机出题、上传题目图片识别后解题。覆盖正方体/长方体、棱锥/棱柱、圆柱/圆锥上的线面角、 二面角、异面直线夹角、点到平面距离、体积等题型，统一用"建系+向量法"，并由 sympy 精确 计算驱动（答案、3D 坐标、步骤数值同源一致）。其他 agent 也可调用本技能生成此类网页。 触发词：立体几何, 线面角, 二面角, 异面直线, 点到平面距离, 正四棱锥, 正方体求角, 解这道几何题, 随机出一道立体几何题, 这张图里的立体几何题; solid…