Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aloth/powerskills/desktopnpx skills add aloth/PowerSkills --skill desktopgit clone --depth 1 https://github.com/aloth/PowerSkillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00053 | $0.00585 |
| Opus 5 | $0.00026 | $0.00293 |
| Sonnet 5 | $0.00011 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
powerskills-desktop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
PowerSkills — Desktop
Desktop automation: screenshots, window management, keystrokes, app launching.
Requirements
- Windows with .NET Framework (System.Windows.Forms, System.Drawing)
Actions
.\powerskills.ps1 desktop <action> [--params]
| Action | Params | Description |
|---|---|---|
screenshot |
--out-file path.png [--window "title"] |
Full screen or window capture |
windows |
List all visible windows with title, PID, process name | |
focus |
--window "title" |
Bring window to foreground |
minimize |
--window "title" |
Minimize window |
maximize |
--window "title" |
Maximize window |
keys |
--keys "{ENTER}" [--window "title"] |
Send keystrokes (SendKeys syntax) |
launch |
--app notepad [--app-args "file.txt"] [--wait-ms 3000] |
Launch application |
Examples
# Full screen screenshot
.\powerskills.ps1 desktop screenshot --out-file screen.png
# Capture a specific window
.\powerskills.ps1 desktop screenshot --out-file outlook.png --window "Outlook"
# List all windows
.\powerskills.ps1 desktop windows
# Focus and type into Notepad
.\powerskills.ps1 desktop focus --window "Notepad"
.\powerskills.ps1 desktop keys --keys "Hello world{ENTER}" --window "Notepad"
# Launch an app
.\powerskills.ps1 desktop launch --app "notepad.exe" --app-args "C:\temp\notes.txt"
SendKeys Syntax
| Key | Syntax |
|---|---|
| Enter | {ENTER} |
| Tab | {TAB} |
| Escape | {ESC} |
| Ctrl+C | ^c |
| Alt+F4 | %{F4} |
| Shift+Tab | +{TAB} |
See Microsoft SendKeys docs for full syntax.
Output Fields
windows
title, pid, process, hwnd
screenshot
saved, width, height, window (if window capture)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 75 lines · 53 tokens per session scan A 51f71b1a530a
powerskills-desktop is a skill published in the GitHub repository aloth/PowerSkills (35 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 585 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…
opencli-adapter-author
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…