API Designer
Jeffallan/claude-skills
Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.
Operate Virtual Workbench via REST API — prepare materials, move to heating stations, start heating, move to output, transfer resources.
Install Virtual Workbench
$ npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install deepmodeling/Uni-Lab-OS virtual-workbench --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/deepmodeling/Uni-Lab-OS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/virtual-workbench .claude/skills/virtual-workbench && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "virtual-workbench" agent skill from https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbench into .claude/skills/virtual-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "virtual-workbench", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbenchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install deepmodeling/Uni-Lab-OS virtual-workbench --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/Uni-Lab-OS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/virtual-workbench .agents/skills/virtual-workbench && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "virtual-workbench" agent skill from https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbench into .agents/skills/virtual-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "virtual-workbench", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install deepmodeling/Uni-Lab-OS virtual-workbench --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/Uni-Lab-OS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/virtual-workbench .cursor/skills/virtual-workbench && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "virtual-workbench" agent skill from https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbench into .cursor/skills/virtual-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "virtual-workbench", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/deepmodeling/Uni-Lab-OS.git --path .cursor/skills/virtual-workbench--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install deepmodeling/Uni-Lab-OS virtual-workbench --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/Uni-Lab-OS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/virtual-workbench .gemini/skills/virtual-workbench && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "virtual-workbench" agent skill from https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbench into .gemini/skills/virtual-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "virtual-workbench", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install deepmodeling/Uni-Lab-OS virtual-workbenchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/deepmodeling/Uni-Lab-OS.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/virtual-workbench .github/skills/virtual-workbench && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "virtual-workbench" agent skill from https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbench into .github/skills/virtual-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "virtual-workbench", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install deepmodeling/Uni-Lab-OS virtual-workbench --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/Uni-Lab-OS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/virtual-workbench .opencode/skills/virtual-workbench && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "virtual-workbench" agent skill from https://github.com/deepmodeling/Uni-Lab-OS/tree/main/.cursor/skills/virtual-workbench into .opencode/skills/virtual-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "virtual-workbench", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
virtual-workbench- GitHub stars
- 178
- Token cost
- ~2.4k tokens
- SKILL.md length
- 371 words
- Files
- 8
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Operate Virtual Workbench via REST API — prepare materials, move to heating stations, start heating, move to output, transfer resources.
- Works in 12 steps: ak / sk → AUTH → addr → BASE URL → 获取实验室信息（自动获取 lab_uuid） → …
- The user mentions virtual workbench
- SKILL.md covers 设备信息, 前置条件（缺一不可）, Session State and 请求约定, plus 4 more sections
- Calls curl; reaches leap-lab.test.bohrium.com and leap-lab.uat.bohrium.com
What it does
Virtual Workbench is an agent skill from deepmodeling/Uni-Lab-OS. Operate Virtual Workbench via REST API — prepare materials, move to heating stations, start heating, move to output, transfer resources. Use when the user mentions virtual workbench, virtualworkbench, 虚拟工作台, heating stations, material processing, or workbench operations.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `action-index.md`, `actions/manual_confirm.json` and `actions/move_to_heating_station.json`).
It sits in Backend & APIs, covering REST APIs. The repository describes itself as: A Platform for Laboratory Automation. The licence is GPL-3.0.
When your agent uses it
- The user mentions virtual workbench
- Virtualworkbench
- Heating stations
- Material processing
Example prompts
- “/virtual-workbench”
Requirements
- Python 3
Workflow steps
12 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 43923ec. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
leap-lab.test.bohrium.comleap-lab.uat.bohrium.comleap-lab.bohrium.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Virtual Workbench loads about 2.4k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 371 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from deepmodeling/Uni-Lab-OS at commit 43923ec, republished under its GPL-3.0 licence (© deepmodeling). 371 words, ~2,402 tokens.
Download SKILL.mdSave it as
.claude/skills/virtual-workbench/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- virtual-workbench
- description
- Operate Virtual Workbench via REST API — prepare materials, move to heating stations, start heating, move to output, transfer resources. Use when the user mentions virtual workbench, virtual_workbench, 虚拟工作台, heating stations, material processing, or workbench operations.
Virtual Workbench API Skill
设备信息
- device_id:
virtual_workbench - Python 源码:
unilabos/devices/virtual/workbench.py - 设备类:
VirtualWorkbench - 当前纳入动作: 5 个（
auto-prepare_materials,auto-move_to_heating_station,auto-start_heating,auto-move_to_output,transfer） - 暂跳过动作:
manual_confirm、扣电测试test（需要启用时先从最新注册表重新提取 schema） - 设备描述: 模拟工作台，包含 1 个机械臂（每次操作 2s，独占锁）和 3 个加热台（每次加热 60s，可并行）
典型工作流程
prepare_materials— 生成 A1-A5 物料（5 个 output handle）move_to_heating_station— 物料并发竞争机械臂，移动到空闲加热台start_heating— 启动加热（3 个加热台可并行）move_to_output— 加热完成后移到输出位置 Cn
前置条件（缺一不可）
使用本 skill 前，必须先确认以下信息。如果缺少任何一项，立即向用户询问并终止，等补齐后再继续。
1. ak / sk → AUTH
从启动参数 --ak --sk 或 config.py 中获取，生成 token：base64(ak:sk) → Authorization: Lab <token>
2. --addr → BASE URL
--addr 值 | BASE |
|---|---|
test | https://leap-lab.test.bohrium.com |
uat | https://leap-lab.uat.bohrium.com |
local | http://127.0.0.1:48197 |
| 不传（默认） | https://leap-lab.bohrium.com |
确认后设置：
BASE="<根据 addr 确定的 URL>"
AUTH="Authorization: Lab <token>"两项全部就绪后才可发起 API 请求。
Session State
lab_uuid— 实验室 UUID（首次通过 API #1 自动获取，不需要问用户）device_name—virtual_workbench
请求约定
所有请求使用 curl -s，POST/PATCH/DELETE 需加 Content-Type: application/json。
Windows 平台必须使用
curl.exe（而非 PowerShell 的curl别名）。
API Endpoints
1. 获取实验室信息（自动获取 lab_uuid）
curl -s -X GET "$BASE/api/v1/edge/lab/info" -H "$AUTH"返回 data.uuid 为 lab_uuid，data.name 为 lab_name。
2. 创建工作流
curl -s -X POST "$BASE/api/v1/lab/workflow/owner" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"name":"<名称>","lab_uuid":"<lab_uuid>","description":"<描述>"}'返回 data.uuid 为 workflow_uuid。创建成功后告知用户链接：$BASE/laboratory/$lab_uuid/workflow/$workflow_uuid
3. 创建节点
curl -s -X POST "$BASE/api/v1/edge/workflow/node" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"workflow_uuid":"<workflow_uuid>","resource_template_name":"virtual_workbench","node_template_name":"<action_name>"}'resource_template_name固定为virtual_workbenchnode_template_name— action 名称（如auto-prepare_materials,auto-move_to_heating_station）
4. 删除节点
curl -s -X DELETE "$BASE/api/v1/lab/workflow/nodes" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"node_uuids":["<uuid1>"],"workflow_uuid":"<workflow_uuid>"}'5. 更新节点参数
curl -s -X PATCH "$BASE/api/v1/lab/workflow/node" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"workflow_uuid":"<wf_uuid>","uuid":"<node_uuid>","param":{...}}'参考 action-index.md 确定哪些字段是 Slot。
6. 查询节点 handles
curl -s -X POST "$BASE/api/v1/lab/workflow/node-handles" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"node_uuids":["<node_uuid_1>","<node_uuid_2>"]}'7. 批量创建边
curl -s -X POST "$BASE/api/v1/lab/workflow/edges" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"edges":[{"source_node_uuid":"<uuid>","target_node_uuid":"<uuid>","source_handle_uuid":"<uuid>","target_handle_uuid":"<uuid>"}]}'8. 启动工作流
curl -s -X POST "$BASE/api/v1/lab/workflow/<workflow_uuid>/run" -H "$AUTH"9. 运行设备单动作
curl -s -X POST "$BASE/api/v1/lab/mcp/run/action" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"lab_uuid":"<lab_uuid>","device_id":"virtual_workbench","action":"<action_name>","action_type":"<type>","param":{...}}'param 直接放 goal 里的属性，不要再包一层 {"goal": {...}}。
WARNING:
action_type必须正确，传错会导致任务永远卡住无法完成。 从下表或actions/<name>.json的type字段获取。
action_type 速查表
| action | action_type |
|---|---|
auto-prepare_materials | UniLabJsonCommand |
auto-move_to_heating_station | UniLabJsonCommand |
auto-start_heating | UniLabJsonCommand |
auto-move_to_output | UniLabJsonCommand |
transfer | UniLabJsonCommandAsync |
manual_confirm和扣电测试test当前不纳入本 skill 的推荐操作范围；不要基于历史 JSON 直接调用，需先重新生成并校验 schema。
10. 查询任务状态
curl -s -X GET "$BASE/api/v1/lab/mcp/task/<task_uuid>" -H "$AUTH"11. 运行工作流单节点
curl -s -X POST "$BASE/api/v1/lab/mcp/run/workflow/action" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"node_uuid":"<node_uuid>"}'12. 获取资源树（物料信息）
curl -s -X GET "$BASE/api/v1/lab/material/download/$lab_uuid" -H "$AUTH"注意 lab_uuid 在路径中。返回 data.nodes[] 含所有节点（设备 + 物料），每个节点含 name、uuid、type、parent。
13. 获取工作流模板详情
curl -s -X GET "$BASE/api/v1/lab/workflow/template/detail/$workflow_uuid" -H "$AUTH"必须使用
/lab/workflow/template/detail/{uuid}，其他路径会返回 404。
14. 按名称查询物料模板
curl -s -X GET "$BASE/api/v1/lab/material/template/by-name?lab_uuid=$lab_uuid&name=<template_name>" -H "$AUTH"返回 data.uuid 为 res_template_uuid，用于 API #15。
15. 创建物料节点
curl -s -X POST "$BASE/api/v1/edge/material/node" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"res_template_uuid":"<uuid>","name":"<名称>","display_name":"<显示名>","parent_uuid":"<父节点uuid>","data":{...}}'16. 更新物料节点
curl -s -X PUT "$BASE/api/v1/edge/material/node" \
-H "$AUTH" -H "Content-Type: application/json" \
-d '{"uuid":"<节点uuid>","display_name":"<新名称>","data":{...}}'Show full SKILL.md (149 more words)Show less
Placeholder Slot 填写规则
placeholder_keys 值 | Slot 类型 | 填写格式 | 选取范围 |
|---|---|---|---|
unilabos_resources | ResourceSlot | {"id": "/path/name", "name": "name", "uuid": "xxx"} | 仅物料节点（非设备） |
unilabos_devices | DeviceSlot | "/parent/device_name" | 仅设备节点（type=device） |
unilabos_nodes | NodeSlot | "/parent/node_name" | 所有节点（设备 + 物料） |
unilabos_class | ClassSlot | "class_name" | 注册表中已注册的资源类 |
virtual_workbench 设备的 Slot 字段表
| Action | 字段 | Slot 类型 | 说明 |
|---|---|---|---|
transfer | resource | ResourceSlot | 待转移物料数组 |
transfer | target_device | DeviceSlot | 目标设备路径 |
transfer | mount_resource | ResourceSlot | 目标孔位数组 |
prepare_materials、move_to_heating_station、start_heating、move_to_output这 4 个动作无 Slot 字段，参数为纯数值/整数。manual_confirm先跳过，不维护其 Slot 字段表。
渐进加载策略
- SKILL.md（本文件）— API 端点 + session state 管理 + 设备工作流概览
- action-index.md — 按分类浏览 6 个动作的描述和核心参数
- actions/<name>.json — 仅在需要构建具体请求时，加载对应 action 的完整 JSON Schema
完整工作流 Checklist
Task Progress:
- [ ] Step 1: GET /edge/lab/info 获取 lab_uuid
- [ ] Step 2: 获取资源树 (GET #12) → 记住可用物料
- [ ] Step 3: 读 action-index.md 确定要用的 action 名
- [ ] Step 4: 创建工作流 (POST #2) → 记住 workflow_uuid，告知用户链接
- [ ] Step 5: 创建节点 (POST #3, resource_template_name=virtual_workbench) → 记住 node_uuid + data.param
- [ ] Step 6: 根据 _unilabos_placeholder_info 和资源树，填写 data.param 中的 Slot 字段
- [ ] Step 7: 更新节点参数 (PATCH #5)
- [ ] Step 8: 查询节点 handles (POST #6) → 获取各节点的 handle_uuid
- [ ] Step 9: 批量创建边 (POST #7) → 用 handle_uuid 连接节点
- [ ] Step 10: 启动工作流 (POST #8) 或运行单节点 (POST #11)
- [ ] Step 11: 查询任务状态 (GET #10) 确认完成典型 5 物料并发加热工作流示例
prepare_materials (count=5)
├─ channel_1 → move_to_heating_station (material_number=1) → start_heating → move_to_output
├─ channel_2 → move_to_heating_station (material_number=2) → start_heating → move_to_output
├─ channel_3 → move_to_heating_station (material_number=3) → start_heating → move_to_output
├─ channel_4 → move_to_heating_station (material_number=4) → start_heating → move_to_output
└─ channel_5 → move_to_heating_station (material_number=5) → start_heating → move_to_output创建节点时，prepare_materials 的 5 个 output handle（channel_1 ~ channel_5）分别连接到 5 个 move_to_heating_station 节点的 material_input handle。每个 move_to_heating_station 的 heating_station_output 和 material_number_output 连接到对应 start_heating 的 station_id_input 和 material_number_input。
start_heating 完成后还需要继续连接到 move_to_output，否则加热完成的物料不会移出加热台：
| source action | source handle | target action | target handle | 传递参数 |
|---|---|---|---|---|
auto-prepare_materials | channel_N | auto-move_to_heating_station | material_input | material_number |
auto-move_to_heating_station | heating_station_output | auto-start_heating | station_id_input | station_id |
auto-move_to_heating_station | material_number_output | auto-start_heating | material_number_input | material_number |
auto-start_heating | heating_done_station | auto-move_to_output | output_station_input | station_id |
auto-start_heating | heating_done_material | auto-move_to_output | output_material_input | material_number |
© deepmodeling, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files in .cursor/skills/virtual-workbench of deepmodeling/Uni-Lab-OS.
- SKILL.md
- action-index.md
- actions/manual_confirm.json
- actions/move_to_heating_station.json
- actions/move_to_output.json
- actions/prepare_materials.json
- actions/start_heating.json
- actions/transfer.json
Open the folder on GitHubat commit 43923ec
Compare with similar skills
Virtual Workbench next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Virtual Workbench this skilldeepmodeling/Uni-Lab-OS | 178 | — | ~2.4k | Automated safety check: Pass | GPL-3.0 | |
| API DesignerJeffallan/claude-skills | 12k | 2 repos | ~2k | Automated safety check: Pass | MIT | |
| Paperclippaperclipai/paperclip | 98k | — | ~9.6k | Automated safety check: Pass | MIT | |
| Nodejs Backend Patternsever-works/ever-works | 158 | 17 repos | ~4k | Automated safety check: Pass | AGPL-3.0 | |
| OpenAPI to MCP Servermcp-use/mcp-use | 11k | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Use Yaakmountain-loop/yaak | 19k | — | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Paperclip
paperclipai/paperclip
Interact with the Paperclip control plane API for task coordination and governance.
Nodejs Backend Patterns
ever-works/ever-works
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices.
OpenAPI to MCP Server
mcp-use/mcp-use
Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.
Use Yaak
mountain-loop/yaak
A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…
RuView CLI, API and WASM
ruvnet/RuView
Covers the RuView `wifi-densepose` command line binary, its Axum REST API and the WebAssembly builds for browsers and ESP32, for embedding or scripting RuView.
More from deepmodeling/Uni-Lab-OS
All 10 skills in this repoBatch Submit Experiment
deepmodeling/Uni-Lab-OS
Batch submit experiments (notebooks) to the Uni-Lab cloud platform (leap-lab) — list workflows, generate nodeparams from registry schemas, submit multiple rounds, check notebook status.
Create Device Skill
deepmodeling/Uni-Lab-OS
Create a skill for any Uni-Lab device by extracting action schemas from the device registry.
Filter Workflow By Tags
deepmodeling/Uni-Lab-OS
Query backend workflow list, aggregate all tags, and filter workflows by domain/scenario requirements using tags.
Submit Agent Result
deepmodeling/Uni-Lab-OS
Submit historical experiment results (agentresult) to Uni-Lab cloud platform (leap-lab) notebook — read data files, assemble JSON payload, PUT to cloud API.
Add Device
deepmodeling/Uni-Lab-OS
Guide for adding new devices to Uni-Lab-OS (接入新设备). An agent skill from deepmodeling/Uni-Lab-OS.
Add Resource
deepmodeling/Uni-Lab-OS
Guide for adding new resources (materials, bottles, carriers, decks, warehouses) to Uni-Lab-OS (添加新物料/资源).
Related
Categories
Questions about Virtual Workbench
What does Virtual Workbench do?
Operate Virtual Workbench via REST API — prepare materials, move to heating stations, start heating, move to output, transfer resources. Virtual Workbench is an agent skill from deepmodeling/Uni-Lab-OS. Operate Virtual Workbench via REST API — prepare materials, move to heating stations, start heating, move to output, transfer resources.
When should I use Virtual Workbench?
Virtual Workbench fits situations like: the user mentions virtual workbench; virtualworkbench; heating stations; material processing.
How do I install Virtual Workbench in Claude Code?
Run `npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a claude-code`. Or copy the skill folder (.cursor/skills/virtual-workbench in deepmodeling/Uni-Lab-OS) into .claude/skills/virtual-workbench in your project. Claude Code loads it when a task matches its description.
How do I install Virtual Workbench in Codex?
Run `npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a codex`. Or copy the skill folder (.cursor/skills/virtual-workbench in deepmodeling/Uni-Lab-OS) into .agents/skills/virtual-workbench in your project. Codex loads it when a task matches its description.
Can I use Virtual Workbench in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add deepmodeling/Uni-Lab-OS --skill virtual-workbench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/virtual-workbench, .gemini/skills/virtual-workbench, .github/skills/virtual-workbench and .opencode/skills/virtual-workbench in your project.
What does Virtual Workbench need to run?
Going by SKILL.md and its folder, Virtual Workbench needs the command-line tools its instructions call (curl). Our summary lists: Python 3.
Does Virtual Workbench access the network?
SKILL.md names 3 domains. In commands or code: leap-lab.test.bohrium.com, leap-lab.uat.bohrium.com and leap-lab.bohrium.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Virtual Workbench safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Virtual Workbench use?
Virtual Workbench is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Virtual Workbench use?
About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Virtual Workbench?
Skills that share tags, products or a category with Virtual Workbench: API Designer (Jeffallan/claude-skills, 12k stars), Paperclip (paperclipai/paperclip, 98k stars), Nodejs Backend Patterns (ever-works/ever-works, 158 stars) and OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Virtual Workbench?
deepmodeling (a GitHub organization) maintains it in deepmodeling/Uni-Lab-OS, which has 178 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 24, 2026.
Source: deepmodeling/Uni-Lab-OS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.