windows-ui-automation
Expert in Windows UI Automation (UIA) and Win32 APIs for desktop automation. Specializes in accessible, secure automation of Windows applications including element discovery, input simulation, and process interaction. HIGH-RISK skill requiring strict security controls for system access.
Install with Tessl CLI
npx tessl i github:martinholovsky/claude-skills-generator --skill windows-ui-automation70
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description establishes a clear Windows desktop automation niche with appropriate technical terminology, but suffers from lack of explicit trigger guidance and somewhat abstract capability descriptions. The 'Expert in...' framing and missing 'Use when...' clause significantly weaken its utility for skill selection among many options.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when automating Windows desktop applications, controlling GUI elements, or when user mentions UIA, Win32, or Windows app automation'
Replace abstract terms like 'element discovery' and 'process interaction' with concrete actions like 'click buttons, read window text, fill forms, navigate menus, capture screenshots'
Include natural language variations users might say: 'automate Windows programs', 'control desktop apps', 'GUI automation', 'Windows scripting'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Windows UI Automation, Win32 APIs) and mentions some actions (element discovery, input simulation, process interaction), but these are somewhat abstract rather than concrete specific actions like 'click buttons', 'read window text', or 'automate form filling'. | 2 / 3 |
Completeness | Describes what the skill does (Windows automation capabilities) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. The rubric states missing 'Use when' should cap completeness at 2, and this has no when guidance at all. | 1 / 3 |
Trigger Term Quality | Includes technical terms like 'Windows UI Automation', 'UIA', 'Win32 APIs', 'desktop automation' which are relevant but may not match natural user language. Missing common variations users might say like 'automate Windows app', 'click buttons automatically', 'control desktop programs'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on Windows-specific technologies (UIA, Win32 APIs) and desktop automation creates a clear niche that is unlikely to conflict with web automation, Mac automation, or general scripting skills. The 'HIGH-RISK' designation also helps distinguish it. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for Windows UI Automation with strong security focus. The code examples are executable and comprehensive, the workflow is clearly sequenced with validation checkpoints, and references are appropriately organized. The main weakness is some verbosity in the overview sections that explain Claude's capabilities rather than providing instructions.
Suggestions
Remove or condense sections 1 and 2.3 that describe what Claude 'excels at' or 'understands' - these explain capabilities Claude already has rather than providing new instructions
Consolidate the repeated security principles (appearing in sections 2.1, 2.2, 5, and 14) into a single authoritative location to reduce redundancy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in the overview section explaining what Claude 'excels at' and 'understands' - Claude already knows its capabilities. The security principles are repeated multiple times across sections. However, the code examples are appropriately lean. | 2 / 3 |
Actionability | Provides fully executable Python code examples with complete implementations for secure element discovery, input simulation, process validation, and timeout enforcement. Code is copy-paste ready with proper imports and class structures. | 3 / 3 |
Workflow Clarity | Excellent TDD workflow with clear 4-step sequence (write failing test → implement minimum → refactor → verify). Pre-implementation checklist provides explicit validation checkpoints across three phases. Security validation steps are clearly sequenced with explicit 'MUST' requirements. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview pointing to one-level-deep references (references/advanced-patterns.md, references/security-examples.md, references/threat-model.md). Content is appropriately split between main skill and reference files, with clear navigation signals. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
68%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (644 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 11 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.