Unidock Pro logo

Unidock Pro

Community
makabaka007x
unidock-pro

Run and package UniDock-Pro GPU virtual screening workflows for classical docking, ligand similarity searching, and hybrid docking. Use when the user mentions UniDock-Pro, udp, receptor.pdbqt, reference_ligand, ligand_index, ligand_dir, search_mode, docking score ranking, batch screening, or reproducible UniDock-Pro result summaries.

Overview

Publishermakabaka007x
Repositorycadd-skill
Skill nameunidock-pro
Stars
54
Forks
6
Bundled files
6
Links
  • 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.

  • 6 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 Unidock Pro AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/makabaka007x/cadd-skill/tree/main/skills/unidock-pro
  4. 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.
2

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/unidock-pro .claude/skills/unidock-pro
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Unidock Pro 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 Unidock Pro 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 Unidock Pro 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.

UniDock-Pro 虚拟筛选

把任务默认理解为“交付一个可复现的 UniDock-Pro 运行结果”,不要只解释命令行。 优先使用 scripts/run_unidock_case.py、scripts/make_ligand_index.py、scripts/analyze_unidock_results.py,避免临时手写长命令。

默认工作流

  1. 先读 references/local-setup.md,确认目标机器上的仓库、二进制、conda 环境和文档偏差。
  2. 判断任务属于 pure docking、similarity searching、hybrid 三类之一。
  3. 先检查 build/udp 是否可直接运行;如果不可运行,再切到 unidock-pro 环境,必要时按本地构建指引重建。
  4. 明确搜索框中心、搜索框尺寸和 --search_mode。--search_mode 必须显式设置,不允许省略;如果用户没有明确说用哪一个,每次都先问,不得替用户默认选择。
  5. 优先通过 scripts/run_unidock_case.py 执行,不要直接手写一长串 udp 参数。
  6. 如果用户只有配体目录,没有索引文件,先运行 scripts/make_ligand_index.py。
  7. 运行结束后,用 scripts/analyze_unidock_results.py 汇总 *_out.pdbqt,给出排序结果和输出路径。

输入判定

把请求先归到下面三类之一:

  1. pure docking
  • 有 receptor
  • 没有 reference_ligand
  • 典型目标是经典结构对接
  1. similarity searching
  • 有 reference_ligand
  • 没有 receptor
  • 典型目标是基于已知活性配体做相似性筛选
  1. hybrid
  • 同时有 receptor 和 reference_ligand
  • 典型目标是结合受体结构和参考配体做联合筛选

配体输入只选一种:

  • ligand_index
  • ligand_dir

如果用户同时给了两种来源,先收敛成一种再运行。

快速入口

优先使用脚本入口:

bash
python3 scripts/run_unidock_case.py \
  --mode docking \
  --receptor /path/to/receptor.pdbqt \
  --ligand-index /path/to/ligand_index.txt \
  --center-x 32.79 --center-y 38.34 --center-z 58.49 \
  --size-x 28 --size-y 28 --size-z 28 \
  --search-mode <用户确认的模式> \
  --output-dir /path/to/results

如果用户只有配体目录:

bash
python3 scripts/make_ligand_index.py /path/to/ligands /path/to/ligand_index.txt

结果汇总入口:

bash
python3 scripts/analyze_unidock_results.py /path/to/results /path/to/docking_results.csv --top-n 50

环境与构建

本 skill 依赖目标机器上的 UniDock-Pro 安装事实,不要凭空假设新机器布局。

  • 先尝试直接运行 /path/to/UniDock-Pro/build/udp
  • 如果直接运行失败,再尝试 conda activate unidock-pro
  • 如果 conda activate 不方便,再回退到 /path/to/conda-envs/unidock-pro

如果二进制不存在或不可执行,优先按 references/local-setup.md 中的构建步骤重建。

防呆规则

  • 强制显式传入 --search_mode
  • 如果用户没有明确指定 fast、balance 或 detail,必须先询问,再运行;不要根据任务规模或习惯自动选
  • 文档里常见的 --ligand_directory 不要直接照搬;当前源码真实参数是 --ligand_dir
  • 源码接受 balance/balanced 与 detail/detailed,与用户确认时统一使用规范写法 fast、balance、detail
  • hybrid 模式里的 reference_ligand 必须是与受体对应的共晶姿态;如果用户没有明确说明,先提醒这个前提
  • 批量运行时总是传入新的输出目录,避免把不同任务的 *_out.pdbqt 混在一起

输出约定

交付时优先说明这些内容:

  • 实际运行模式
  • 实际调用方式:直跑二进制、conda activate unidock-pro,还是环境前缀回退
  • 输出目录
  • 生成的 *_out.pdbqt
  • 汇总 CSV 路径
  • 任何关键前提,例如 hybrid 模式共晶参考配体的假设

资源

  • 本地路径、环境和文档偏差:references/local-setup.md
  • 三类任务的命令模板和输出约定:references/workflows.md
  • 统一运行入口:scripts/run_unidock_case.py
  • 配体目录转索引:scripts/make_ligand_index.py
  • 结果排序与 CSV 汇总:scripts/analyze_unidock_results.py

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 Unidock Pro AI skill do?

Run and package UniDock-Pro GPU virtual screening workflows for classical docking, ligand similarity searching, and hybrid docking. Use when the user mentions UniDock-Pro, udp, receptor.pdbqt, reference_ligand, ligand_index, ligand_dir, search_mode, docking score ranking, batch screening, or reproducible UniDock-Pro result summaries.

Why use Unidock Pro on TypingMind?

Because you install it once and use it with any model. Unidock Pro 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 Unidock Pro in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/makabaka007x/cadd-skill/tree/main/skills/unidock-pro. 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 Unidock Pro?

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 Unidock Pro?

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

Is the Unidock Pro 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇