Manage Taskboard
shengsheng90/DSH-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions.
Automate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor.
$ npx skills add vellum-ai/vellum-assistant --skill windows-automation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vellum-ai/vellum-assistant windows-automation --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/vellum-ai/vellum-assistant.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/windows-automation .claude/skills/windows-automation && 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 "windows-automation" agent skill from https://github.com/vellum-ai/vellum-assistant/tree/main/skills/windows-automation into .claude/skills/windows-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "windows-automation", 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/vellum-ai/vellum-assistant/tree/main/skills/windows-automationType 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 vellum-ai/vellum-assistant --skill windows-automation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vellum-ai/vellum-assistant windows-automation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/windows-automation .agents/skills/windows-automation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "windows-automation" agent skill from https://github.com/vellum-ai/vellum-assistant/tree/main/skills/windows-automation into .agents/skills/windows-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "windows-automation", 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 vellum-ai/vellum-assistant --skill windows-automation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vellum-ai/vellum-assistant windows-automation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/windows-automation .cursor/skills/windows-automation && 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 "windows-automation" agent skill from https://github.com/vellum-ai/vellum-assistant/tree/main/skills/windows-automation into .cursor/skills/windows-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "windows-automation", 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/vellum-ai/vellum-assistant.git --path skills/windows-automation--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 vellum-ai/vellum-assistant --skill windows-automation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vellum-ai/vellum-assistant windows-automation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/windows-automation .gemini/skills/windows-automation && 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 "windows-automation" agent skill from https://github.com/vellum-ai/vellum-assistant/tree/main/skills/windows-automation into .gemini/skills/windows-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "windows-automation", 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 vellum-ai/vellum-assistant windows-automationInstalls 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 vellum-ai/vellum-assistant --skill windows-automation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/windows-automation .github/skills/windows-automation && 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 "windows-automation" agent skill from https://github.com/vellum-ai/vellum-assistant/tree/main/skills/windows-automation into .github/skills/windows-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "windows-automation", 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 vellum-ai/vellum-assistant --skill windows-automation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vellum-ai/vellum-assistant windows-automation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/windows-automation .opencode/skills/windows-automation && 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 "windows-automation" agent skill from https://github.com/vellum-ai/vellum-assistant/tree/main/skills/windows-automation into .opencode/skills/windows-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "windows-automation", 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.
windows-automationAutomate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor.
Windows Automation is an agent skill from vellum-ai/vellum-assistant. Automate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor. Use for launching or inspecting desktop apps, opening Windows Settings, controlling scriptable Microsoft Office apps, and interacting with native UI when no direct CLI or API is available.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Vellum personal assistants on Windows
It sits in Productivity & Automation, covering Desktop control and Mobile UI design. It works with PowerShell. The repository describes itself as: An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time. The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 33cc983. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are powershell).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Designed for Vellum personal assistants on Windows
From compatibility in the SKILL.md frontmatter.
Windows Automation loads about 1.5k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 486 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.
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.
The full file from vellum-ai/vellum-assistant at commit 33cc983, republished under its MIT licence (© vellum-ai). 486 words, ~1,532 tokens.
.claude/skills/windows-automation/SKILL.md (or your agent's skills folder).Use host_bash for every command in this skill. On Windows, host_bash runs Windows PowerShell with no profile and no interactive prompt. Use PowerShell syntax and Windows paths.
Prefer automation methods in this order:
Avoid screen coordinates and blind keystrokes. They are fragile and can affect the wrong app. Use computer control only when PowerShell and UI Automation cannot complete the task or the user explicitly requests it.
# Find Start menu apps
Get-StartApps | Where-Object Name -Like "*Calculator*"
# Inspect running desktop apps
Get-Process | Where-Object MainWindowTitle | Select-Object Id, ProcessName, MainWindowTitle
# Launch an app or a Windows Settings page
Start-Process calc.exe
Start-Process "ms-settings:privacy-microphone"
# Open a folder in File Explorer
Start-Process explorer.exe -ArgumentList "C:\Users\Public\Documents"Prefer a stable executable, AppUserModelId, URI scheme, process ID, or automation ID over a localized window title.
Microsoft Office desktop apps expose COM APIs. Check that the app is installed before relying on one. Keep the COM object alive for the full operation and release it when finished.
# Create an isolated temporary workbook
$excel = $null
$workbook = $null
$worksheet = $null
$cell = $null
try {
$excel = New-Object -ComObject Excel.Application
$excel.Visible = $true
$workbook = $excel.Workbooks.Add()
if (-not [string]::IsNullOrEmpty($workbook.Path) -or $workbook.AutoSaveOn) {
throw "The workbook is not an isolated temporary document."
}
$worksheet = $workbook.Worksheets.Item(1)
$cell = $worksheet.Cells.Item(1, 1)
$cell.Value2 = "Example"
} finally {
if ($null -ne $workbook) {
$workbook.Close($false)
}
if ($null -ne $excel) {
$excel.Quit()
}
foreach ($comObject in @($cell, $worksheet, $workbook, $excel)) {
if ($null -ne $comObject) {
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($comObject) | Out-Null
}
}
}Close unsaved temporary documents with Close($false), quit the application, and release COM objects in a finally block so cleanup never waits for a save prompt.
Do not use this skill to save, send, delete, or overwrite content. The Windows host executor does not provide an in-process confirmation gate that works for both local and remote assistants.
Treat every existing document, workbook, message, note, calendar item, file, and cloud-backed resource as read-only. AutoSave can persist an edit without an explicit save command. Only edit an isolated temporary document that the automation created during the current task, has no storage path or cloud connection, and has AutoSave definitively disabled. If those conditions cannot be verified, do not edit it.
If the user requests a consequential action, use a dedicated skill or product workflow with its own hard confirmation gate. If none is available, explain the limitation and ask the user to perform that final action manually.
Load the built-in UI Automation assemblies and identify elements by process ID, automation ID, control type, or name.
Add-Type -AssemblyName UIAutomationClient
$desktop = [System.Windows.Automation.AutomationElement]::RootElement
$windows = $desktop.FindAll(
[System.Windows.Automation.TreeScope]::Children,
[System.Windows.Automation.Condition]::TrueCondition
)
$windows | ForEach-Object {
[pscustomobject]@{
Name = $_.Current.Name
ProcessId = $_.Current.ProcessId
AutomationId = $_.Current.AutomationId
ControlType = $_.Current.ControlType.ProgrammaticName
}
}Once the target window is known, search its descendants with a PropertyCondition and use the supported pattern, such as InvokePattern, ValuePattern, SelectionItemPattern, or TogglePattern. Check TryGetCurrentPattern before invoking a pattern.
If an app exposes no useful automation pattern, verify the process and window before sending keys:
$process = Get-Process notepad -ErrorAction Stop | Select-Object -First 1
$shell = New-Object -ComObject WScript.Shell
if (-not $shell.AppActivate($process.Id)) {
throw "Could not activate Notepad"
}Use keyboard input only after activation succeeds. Never use keyboard input to trigger a consequential action prohibited above.
Get-StartApps.host_bash is non-interactive. Do not use commands that wait for terminal input or depend on a PowerShell profile.© vellum-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/windows-automation of vellum-ai/vellum-assistant.
Open the folder on GitHubat commit 33cc983
Windows Automation 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 |
|---|---|---|---|---|---|---|
| Windows Automation this skillvellum-ai/vellum-assistant | 1.4k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Manage Taskboardshengsheng90/DSH-taskboard | 332 | — | ~885 | Automated safety check: Pass | Apache-2.0 | |
| Phone Usepockebot/openpocket | 847 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Vision SkillsAnionex/agent-vision-toolkit | 1.2k | — | ~4k | Automated safety check: Pass | MIT | |
| Mac Computer UseTo3akaRin/mac-computer-use | 1.1k | — | ~495 | Automated safety check: Pass | MIT | |
| Interceptor iOSHacker-Valley-Media/Interceptor | 522 | — | ~1.9k | Automated safety check: Pass | Custom licence |
shengsheng90/DSH-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions.
pockebot/openpocket
Use OpenPocket MCP tools to inspect or control an Android emulator, physical Android phone, Android TV, or ADB-backed app.
Anionex/agent-vision-toolkit
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…
To3akaRin/mac-computer-use
操作 macOS 桌面应用,探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作,以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收;普通网页任务优先使用已有浏览器工具。
Hacker-Valley-Media/Interceptor
Drive any installed app on an owned, unlocked, Developer-Mode iPhone via interceptor ios : ref-tagged element trees, deterministic coordinate taps (click), reliable text entry (type/keys), scroll…
davidondrej/cloudroom-core
See and control desktop apps on this Cloud sandbox’s virtual Linux screen with cloudroom computer-use: launch GUI apps you build or install, read their UI, click, type, and take screenshots.
vellum-ai/vellum-assistant
Create and configure a GitHub App so the assistant can push commits, open PRs, and comment under its own bot identity.
vellum-ai/vellum-assistant
Connect a Discord bot to the assistant via the Discord Gateway with guided application creation and intent configuration
vellum-ai/vellum-assistant
Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity
vellum-ai/vellum-assistant
Ingest a large dataset into memory as a skimmed map. An agent skill from vellum-ai/vellum-assistant.
vellum-ai/vellum-assistant
A skill your agent uses when the user wants to build, scaffold, ship, or edit a Vellum plugin that bundles multiple surfaces (hooks, tools, skills, and more) into one installable package.
vellum-ai/vellum-assistant
Connect a Slack app to the Vellum Assistant via Socket Mode.
Works with
Categories
Automate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor. Windows Automation is an agent skill from vellum-ai/vellum-assistant. Automate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor.
Windows Automation fits situations like: inspecting desktop apps; opening Windows Settings; controlling scriptable Microsoft Office apps; interacting with native UI when no direct CLI.
Run `npx skills add vellum-ai/vellum-assistant --skill windows-automation -a claude-code`. Or copy the skill folder (skills/windows-automation in vellum-ai/vellum-assistant) into .claude/skills/windows-automation in your project. Claude Code loads it when a task matches its description.
Run `npx skills add vellum-ai/vellum-assistant --skill windows-automation -a codex`. Or copy the skill folder (skills/windows-automation in vellum-ai/vellum-assistant) into .agents/skills/windows-automation in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vellum-ai/vellum-assistant --skill windows-automation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/windows-automation, .gemini/skills/windows-automation, .github/skills/windows-automation and .opencode/skills/windows-automation in your project.
SKILL.md names no scripts, command-line tools or credentials: Windows Automation is instructions for the agent only. Compatibility (from SKILL.md): Designed for Vellum personal assistants on Windows.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
Windows Automation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Windows Automation: Manage Taskboard (shengsheng90/DSH-taskboard, 332 stars), Phone Use (pockebot/openpocket, 847 stars), Vision Skills (Anionex/agent-vision-toolkit, 1.2k stars) and Mac Computer Use (To3akaRin/mac-computer-use, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
vellum-ai (a GitHub organization) maintains it in vellum-ai/vellum-assistant, which has 1,408 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on October 9, 2026.
Source: vellum-ai/vellum-assistant on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.