Amber Md Expert

Community

makabaka007x

amber-md-expert

Prepare, package, resume, and analyze Amber/AmberTools molecular dynamics workflows for local or cluster execution. Use for Amber, AmberTools, pdb4amber, tleap, antechamber, parmchk2, pmemd/pmemd.cuda, cpptraj, MMPBSA.py, PBSA, REMD, membrane systems, implicit solvent, Zn or nonstandard residues, nucleic acids, contact analysis, DSSP/DSSPplot, or requests to create reproducible MD run directories.

Overview

Publisher	makabaka007x
Repository	`cadd-skill`
Skill name	`amber-md-expert`
Stars	54
Forks	6
Bundled files	53
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
53 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by makabaka007x on GitHub. Read the source before you install it.

Installation

Install the Amber Md Expert AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/makabaka007x/cadd-skill/tree/main/skills/amber-md-expert
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/makabaka007x/cadd-skill.git /tmp/cadd-skill
mkdir -p .claude/skills
cp -r /tmp/cadd-skill/skills/amber-md-expert .claude/skills/amber-md-expert

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Amber Md Expert in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Amber Md Expert on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Amber Md Expert is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Amber 分子动力学专家

概述

用这个 skill 把 Amber 工作整理成可复用、可检查的准备、运行或分析流程。默认目标不是只解释 Amber，而是给用户留下一个能在目标机器上适配后运行的目录。

默认工作流

先把请求归到下面三类入口之一：

原始结构准备

适用于用户只有蛋白、配体、复合物或残基文件，还没有最终 Amber 拓扑和坐标。
使用 pdb4amber、antechamber、parmchk2 和 tleap 完成准备。
先确认用户机器上的 AmberTools 环境名或安装路径，不把某个 conda 环境当成全局默认。
然后打包成可在本地或目标集群适配运行的任务目录。

已有 Amber 拓扑打包

适用于用户已经有 .top/.prmtop/.parm7 和 .crd/.inpcrd/.rst7。
跳过本地建模。
直接打包成可运行或可上传的任务目录。

仅分析后处理

适用于用户已经有轨迹，或者想做 cpptraj、MMPBSA、contact、DSSP/DSSPplot。
默认按需生成分析包，而不是预先塞进每个上传目录。

除非请求明确属于其他分支，否则优先走标准蛋白-配体显式溶剂流程。

打包规则

准备本地或集群任务目录时，遵循这些默认规则：

先确认目标执行环境、队列/分区、模块名、GPU/CPU 资源和 wall-time 策略。
GPU Amber 生产脚本使用通用占位配置，交付前必须按目标集群改成真实分区和 QOS。
优先创建新的任务目录，而不是直接修改标准模板。
任务目录命名采用 project_stage，例如 proj1_explicit_gpu。
可直接运行的文件放在任务根目录。
追溯来源文件放在 prep/。
生成 UPLOAD_AND_RUN.md，写清上传、提交和续跑说明。
可以给出 scp 或 rsync 命令模板，但不要真的执行上传。
不要把某个机构的 partition、QOS、module 或 wall-time 写成通用默认值。
如果模板里有 #SBATCH 占位值，提醒用户按实际集群策略修改。

在需要稳定打包时，使用 scripts/create_run_dir.py。更新上传说明时，使用 scripts/render_upload_manifest.py。把目录当成“已就绪”之前，先运行 scripts/validate_amber_task.py。

力场与模板选择

在锁定流程之前，先用自然语言推荐当前体系最合适的力场和水模型组合。可以用模板作为默认值，但不要静默假设每次都是同一个科学选择。

优先参考：

标准工作流和默认模板： references/core-workflow.md
力场与水模型建议： references/force-fields-and-water-models.md
Zn、核酸、非标准残基、糖基化样特殊成键： references/special-cases-nonstandard-zn-glyco-nucleic.md

打包时使用这些模板目录：

assets/templates/standard-explicit/
assets/templates/implicit-solvent/
assets/templates/remd/
assets/templates/membrane/
assets/templates/nonstandard/
assets/templates/zn/

位置约束规则

在显式溶剂预平衡阶段，默认目标是先让溶剂和离子重排，再让主体逐步放开。

默认 ntr 应约束溶质重原子，而不是水和离子。
不要把 (:WAT|Na+|Cl-) 这类 mask 解释成“约束 DNA”；它实际选中的是溶剂或离子。
写补集 mask 时优先显式加括号，例如 !(:WAT,Na+,Cl-) 或 !(:WAT|:Na+|:Cl-)，避免取反范围歧义。
对“只有核酸 + 水 + 单价离子”的显式溶剂体系，可优先用 !(:WAT,Na+,Cl-) & !@H= 约束核酸重原子。
如果体系里还有蛋白、配体、二价金属或其他辅因子，不要直接套用上面的核酸 mask，先按真实要固定的主体重写。

时长确认规则

在把一个 MD 目录视为“可提交运行”之前，必须停下来确认时长。这是用户的硬性偏好。

在写入最终生产级 .in 文件，或把目录交付为已完成之前：

汇总 minimization 的级数和步数。
汇总 heat 时长。
汇总 NVT 时长。
汇总每个 NPT 阶段时长。
汇总 production 时长。
同时展示人可读时长和 Amber 参数，例如 nstlim、dt。
明确询问用户是保留还是修改当前方案。

如果请求里已经给了明确时长，也要先复述一遍并做最终确认，然后再视为完成。

用 scripts/summarize_timescales.py 生成整洁的阶段汇总。详细规则见 references/timescale-confirmation-policy.md。

续跑与安全规则

在续跑或扩展已有任务之前：

检查 restart 链条。
检查 ntx 和 irest。
检查提交脚本是否读取了正确的 restart 文件。
除非用户明确要求覆盖，否则优先生成新的输出文件名。

可配合 scripts/validate_amber_task.py 和 references/restarts-and-job-control.md 使用。

分析默认策略

不要把分析脚本自动塞进每个上传包。把分析策略保留在 skill 中，等用户明确要分析时再生成分析包。

默认最小 cpptraj 分析包只保留：

autoimage
rms first @CA
strip :WAT|(:Na+|:Cl-)
输出去水去离子轨迹 md-nW.xtc
输出第一帧 md-first.pdb
输出最后一帧 md-last.pdb

生成最小分析包时：

写出 analysis.sh
写出 cpptraj.in
在运行时自动识别最后一帧，而不是硬编码

使用 scripts/generate_analysis_bundle.py 时：

minimal 用于最小轨迹处理和首末帧导出
contact 用于复制 contact 分析辅助脚本
dsspplot 用于复制 DSSP 和绘图辅助脚本

参考：

references/analysis-cpptraj-mmpbsa.md
references/analysis-contact-dssp.md
assets/templates/analysis-minimal/
assets/templates/contact/
assets/templates/dsspplot/

高级分支

当请求明显属于下面场景时，不要继续沿用标准显式溶剂流程：

隐式溶剂
REMD
膜蛋白
Zn 配位
非标准残基
核酸
contact 分析
DSSP 或 DSSPplot

只加载该分支需要的 reference 和 template 子目录。不要一次性读入无关资源。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Amber Md Expert AI skill do?

Why use Amber Md Expert on TypingMind?

Because you install it once and use it with any model. Amber Md Expert is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Amber Md Expert in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/makabaka007x/cadd-skill/tree/main/skills/amber-md-expert. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Amber Md Expert?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Amber Md Expert?

As many as you like. As long as a model supports skills, you can use Amber Md Expert with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Amber Md Expert AI skill free?

It is published on GitHub by makabaka007x. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Draw Your Font

NousResearch

OrganizationPopular

Turn a handwriting photo into an installable TTF font.

Adversarial Ux Test

Roleplay a hostile user to find and triage UX pain points.

3 Statement Model

Build integrated IS/BS/CF financial workbooks in Excel.

Comps Analysis

Build comparable-company valuation workbooks in Excel.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Amber 分子动力学专家

概述

默认工作流

打包规则

力场与模板选择

位置约束规则

时长确认规则

续跑与安全规则

分析默认策略

高级分支

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now