agentmods.dev

scholaraio: Skill for Claude Code

.claude/skills/quantum-espresso/SKILL.md

quantum-espresso is a skill for Claude Code from ZimoLiao/scholaraio. It costs 47 tokens per session (2,345 once invoked), scanned A, original, MIT.

A guide for using Quantum ESPRESSO, a software package for first-principles calculations of materials based on quantum mechanics. It covers tasks such as electronic structure, bands, density of states, and phonons.

In plain words
What is it for?
Use it to plan or carry out crystal-material calculations, including self-consistent calculations, band structures, phonons, electron-phonon coupling, Fermi surfaces, and charge density.
Why use it?
It helps choose the right Quantum ESPRESSO program and follow calculation and parameter-checking rules for demanding materials simulations.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ZimoLiao/scholaraio's own configuration. It tells Claude Code how to work on scholaraio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scholaraio configures →

Part of the scholaraio plugin — 44 skills, 1 hook shipped together

not rated 584repo +1 10d ago A scan SkillSpector: warn 47 tokens original MIT
View source ↗ ZimoLiao/scholaraio zimoliao.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to ZimoLiao/scholaraio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ZimoLiao/scholaraio/main/.claude/skills/quantum-espresso/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ZimoLiao/scholaraio

Made for: Claude Code.

Or install scholaraio, the plugin that ships this one along with the rest of its 44 skills, 1 hook.

Wrote 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.

agentmods badge for quantum-espresso

README.md
[![agentmods](https://agentmods.dev/badge/skills/zimoliao/scholaraio/quantum-espresso/github.svg)](https://agentmods.dev/skills/zimoliao/scholaraio/quantum-espresso)
Your own site
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/quantum-espresso"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/quantum-espresso/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for quantum-espresso

Your own site · 80×15
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/quantum-espresso"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/quantum-espresso.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.02345
Opus 5.5 $0.00019 $0.00938
Sonnet 5.5 $0.00009 $0.00469
Haiku 4.5 $0.00005 $0.00234

Measured 2mo ago against content hash b0e6b22d6473, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quantum-espresso 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 2mo 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.

.claude/skills/quantum-espresso/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quantum ESPRESSO 第一性原理计算

用 Quantum ESPRESSO 做 DFT / DFPT：基态、能带、DOS、声子、电声耦合、费米面和电荷密度分析。

本 skill 故意保持轻量：

  • 它负责告诉 agent 什么时候该用 QE、标准计算链路是什么、哪些物理与数值规范不能忽略
  • 它不承担输入文件字段和程序参数手册的职责
  • 具体输入变量、namelist 字段、程序差异统一去查 scholaraio toolref

Agent 默认协议（toolref-first）

对 QE 问题，agent 默认按这个顺序工作：

  1. 先判断任务属于哪个程序：pw.x、ph.x、matdyn.x、q2r.x、dos.x、projwfc.x
  2. 写输入文件或解释参数前，先用 scholaraio toolref show qe ... 查关键变量
  3. 不确定变量归属时，先 search 再 show
  4. 如果 toolref 已能回答，就不要把 skill 当第二份参数手册
  5. 如果 toolref 缺页或命中不好，先继续完成用户任务，再回报这是 toolref 覆盖缺口，而不是把补文档工作甩给用户

这意味着：

  • 普通用户不需要自己打磨 QE toolref
  • agent 应优先自己查、自己判断、自己退化处理
  • 只有在同一缺口反复出现时，才值得进入正式 onboarding/维护流程

前置条件

# 安装
conda install -c conda-forge qe
# 或编译 GPU 版（推荐 A100）

# 赝势下载
# PseudoDojo NC (DFPT 推荐): http://www.pseudo-dojo.org/
# SSSP Efficiency: https://www.materialscloud.org/discover/sssp

验证：pw.x --version 应显示版本。GPU 版本确认 CUDA 支持。

何时使用

适合：

  • 晶体材料的电子结构、能带、DOS、声子、超导、电荷密度
  • 需要第一性原理精度、并能接受较高计算成本的任务

不适合：

  • 需要大尺度长时间分子动力学时，优先经典 MD
  • 只是想快速试错而没有结构、赝势、收敛策略时，不要直接上正式算例

Toolref 优先

当 agent 不确定 QE 输入变量、程序名、namelist 所属、默认值或适用条件时，先查 toolref。

常用查法：

scholaraio toolref search qe "wavefunction cutoff"
scholaraio toolref show qe pw ecutwfc
scholaraio toolref show qe pw occupations
scholaraio toolref show qe ph tr2_ph
scholaraio toolref show qe matdyn asr

推荐习惯：

  • 写 .in 文件前，先查关键变量
  • 不靠旧博客记忆 SYSTEM / ELECTRONS / INPUTPH 字段
  • 程序切换时先确认变量属于 pw.x、ph.x、matdyn.x 还是别的模块

如果遇到覆盖缺口：

  • 先继续用官方手册或源码文档完成任务
  • 在回答里明确说明“这里使用了 toolref 之外的官方文档”
  • 不要要求用户自己先去补齐文档层

核心工作流

知识库协作模式

  1. 用 scholaraio usearch "<材料名称> DFT" 检索相关论文
  2. 从论文提取：晶体结构、交换关联泛函、k 网格、截断能、实验基准值
  3. 在输入文件注释中标注参数来源
  4. 计算完成后与实验数据（晶格常数、能带间隙、声子频率）对比

计算流程

SCF (pw.x)           → 基态电荷密度
  ├─ NSCF (pw.x)     → 能带/DOS 的本征值
  │   ├─ bands.x     → 能带结构后处理
  │   ├─ dos.x       → 态密度
  │   ├─ projwfc.x   → 投影态密度（轨道分辨）
  │   └─ fs.x        → 费米面 (.bxsf)
  ├─ Phonons (ph.x)  → DFPT 声子计算
  │   ├─ q2r.x       → 实空间力常数
  │   ├─ matdyn.x    → 声子色散插值
  │   └─ e-ph        → 电声耦合 (α²F, λ, Tc)
  └─ pp.x            → 电荷密度/ELF 后处理

Read the full file on GitHub · 198 lines

Changes

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.

  1. 2mo ago First seen · 198 lines · 47 tokens per session scan A b0e6b22d6473

Subscribe to this mod's changes

quantum-espresso is a skill published in the GitHub repository ZimoLiao/scholaraio (584 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 2,345 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Scientificagentic-scienceagentic-searchai-agentcomputational-researchresearch-workflowscientific-computing
Related

quantum-espresso compared with skills from other repositories

quantum-espresso next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
quantum-espressoZimoLiao/scholaraioSkill58410d agoMITA47Claude Code
infrastructure-validationdocxology/templateSkill23yesterdayApache-2.0A54Claude Code, Codex
provenance-dagdocxology/templateSkill23yesterdayApache-2.0A103Claude Code, Codex
scientific-connectorsdocxology/templateSkill23yesterdayApache-2.0A87Claude Code, Codex
infrastructure-search-literaturedocxology/templateSkill23yesterdayApache-2.0A123Claude Code, Codex
template-academic-paper-reviewerdocxology/templateSkill23yesterdayApache-2.0A52Claude Code, Codex
template-reproducibility-auditdocxology/templateSkill23yesterdayApache-2.0A70Claude Code, Codex