Windows Lab

Organization

Tavotto

windows-lab

在常驻 Windows Lab（腾讯云 Windows Server 2025）上验证 Tavotto 的 Windows 问题——用户说「去 Windows Lab 验证」「在 Windows 上跑一下」「Windows 真机试试」，或改动涉及 Windows 路径 / 编码 / 进程 / 打包时用。只经 scripts/winlab/winlab.py，不直接 ssh。

Overview

Publisher	Tavotto
Repository	`Tavotto`
Skill name	`windows-lab`
Stars	508
Forks	25
Bundled files	Instructions only
License	AGPL-3.0
Links	Skill source Repository Homepage

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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by Tavotto on GitHub. Read the source before you install it.

Installation

Install the Windows Lab 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/Tavotto/Tavotto/tree/main/.claude/skills/windows-lab
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/Tavotto/Tavotto.git /tmp/Tavotto
mkdir -p .claude/skills
cp -r /tmp/Tavotto/.claude/skills/windows-lab .claude/skills/windows-lab

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

Use it in TypingMind

Enable Windows Lab 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 Windows Lab 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 Windows Lab 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.

Windows Lab

规则全文 docs/rules/ci/windows-lab.md，运维 docs/ci/windows-lab.md——动手前读规则那份。

先 python3 scripts/winlab/winlab.py doctor：remote.result 不是 passed 就停下，报告哪一项，不要绕。连不上（本机没有 tavotto-win-lab 别名 / 云端会话没有本机密钥）就说明 Lab 不可用。
选任务（agent.py 的 TASKS 是闭集，winlab.py test -h 看全）：
- 指定用例：test pytest --tests tests/test_x.py::name --ref HEAD
- 渲染 / 导出 / 保存重载：test render-roundtrip --ref HEAD
- 全量分片（慢，约同 CI）：test pytest-shard --shard N/4 --ref HEAD
- 网络：network --mode all；AI 宿主 L2/L3：test hosts --ref HEAD
- 真宿主 L4/L5（真 Claude Code + 国内模型，花模型费用，先问用户）：test hosts-live --ref 会先过可信度检查再同步代码：只有 origin/main 或你本人提交的分支能上 Lab。
长任务用后台运行，结论以输出 JSON 的 result 为准；不是 passed 就读 summary / counts，需要原始日志时说明它在 Lab 的 C:\TavottoLab\runs\<run_id>\evidence\。
失败先分清产品缺陷还是 Lab 环境问题（doctor、environment 字段）；修产品就按 .github/AGENTS.md 先写 tests/test_windows_regressions.py 用例，再修，再回 Lab 复验。不许降低断言、删用例、加 skip 让它变绿。
向用户汇报时附 run id、提交、result，并照抄报告里的 unverified。

不做：admin … 动词（要用户在场）、改 Lab 的系统配置、经代理下载大文件、碰 DMIT。

Frequently asked questions

What does the Windows Lab AI skill do?

Why use Windows Lab on TypingMind?

Because you install it once and use it with any model. Windows Lab 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 Windows Lab in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Tavotto/Tavotto/tree/main/.claude/skills/windows-lab. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Windows Lab?

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 Windows Lab?

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

Is the Windows Lab AI skill free?

Yes. It is published on GitHub by Tavotto under the AGPL-3.0 license. 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

Telegram E2e Userbot

openclaw

OrganizationPopular

Prove user-visible OpenClaw Telegram behavior on Telegram's Test Server with Convex-leased team credentials; drive real-user turns and record messages, edits, deletions, reactions, typing, or rich…

Module Regression

Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed…

Test Collaboration

Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing…

Competitive Report Structure

affaan-m

CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Windows Lab

Frequently asked questions

Related AI Skills

Set up your own AI workspace now