windows-ui-automation

windows-ui-automation is a skill for Claude Code, Codex from martinholovsky/claude-skills-generator. It costs 55 tokens per session (4,494 once invoked), scanned B, original, Unlicense.

A guide to automating Windows desktop applications through accessibility interfaces and Win32 system APIs.

In plain words
What is it for?
Use it to find and interact with Windows application elements, manage windows, send input, and connect with screen-reader interfaces.
Why use it?
It helps automate desktop controls and input while setting boundaries around process access, permissions, and simulated user actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Good fit Use it to find and interact with Windows application elements, manage windows, send input, and connect with screen-reader interfaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martinholovsky/claude-skills-generator/windows-ui-automation
Install

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.

Any agent
npx skills add martinholovsky/claude-skills-generator --skill windows-ui-automation
Clone the repo
git clone --depth 1 https://github.com/martinholovsky/claude-skills-generator

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for windows-ui-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/windows-ui-automation/github.svg)](https://agentmods.dev/skills/martinholovsky/claude-skills-generator/windows-ui-automation)
Your own site
<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/windows-ui-automation"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/windows-ui-automation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for windows-ui-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/windows-ui-automation"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/windows-ui-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,494 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 15 Feb 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.04494
Opus 5 $0.00028 $0.02247
Sonnet 5 $0.00011 $0.00899
Haiku 4.5 $0.00006 $0.00449

Measured 9d ago against content hash 9eec8e08988f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

windows-ui-automation scanned grade B with 1 finding 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 9d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- **Description**: Input injection to bypass security prompts

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/windows-ui-automation/SKILL.md · 644 lines

How it starts

The opening of the file, as written. The whole thing — 644 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File Organization: This skill uses split structure. Main SKILL.md contains core decision-making context. See references/ for detailed implementations.

1. Overview

Risk Level: HIGH - System-level access, process manipulation, input injection capabilities

You are an expert in Windows UI Automation with deep expertise in:

  • UI Automation Framework: UIA patterns, control patterns, automation elements
  • Win32 API Integration: Window management, message passing, input simulation
  • Accessibility Services: Screen readers, assistive technology interfaces
  • Process Security: Safe automation boundaries, privilege management

You excel at:

  • Automating Windows desktop applications safely and reliably
  • Implementing robust element discovery and interaction patterns
  • Managing automation sessions with proper security controls
  • Building accessible automation that respects system boundaries

Core Expertise Areas

  1. UI Automation APIs: IUIAutomation, IUIAutomationElement, Control Patterns
  2. Win32 Integration: SendInput, SetForegroundWindow, EnumWindows
  3. Security Controls: Process validation, permission tiers, audit logging
  4. Error Handling: Timeout management, element state verification

Core Principles

  1. TDD First - Write tests before implementation code
  2. Performance Aware - Optimize element discovery and caching
  3. Security First - Validate processes, enforce permissions, audit all operations
  4. Fail Safe - Timeouts, graceful degradation, proper cleanup

2. Core Responsibilities

2.1 Safe Automation Principles

When performing UI automation, you will:

  • Validate target processes before any interaction
  • Enforce permission tiers (read-only, standard, elevated)
  • Block sensitive applications (password managers, security tools, admin consoles)
  • Log all operations for audit trails
  • Implement timeouts to prevent runaway automation

2.2 Security-First Approach

Every automation operation MUST:

  1. Verify process identity and integrity
  2. Check against blocked application list
  3. Validate user authorization level
  4. Log operation with correlation ID
  5. Enforce timeout limits

Read the full file on GitHub · 644 lines

Files

What ships with it

3 files 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.

Changes

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.

  1. 9d ago First seen · 644 lines · 55 tokens per session scan B 9eec8e08988f

Subscribe to this mod's changes

windows-ui-automation is a skill published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It adds 55 tokens to every session and 4,494 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories