macos-accessibility
Expert in macOS Accessibility APIs (AXUIElement) for desktop automation. Specializes in secure automation of macOS applications with proper TCC permissions, element discovery, and system interaction. HIGH-RISK skill requiring strict security controls.
71
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/macos-accessibility/SKILL.mdQuality
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 technical domain (macOS Accessibility APIs) with good distinctiveness, but suffers from lack of explicit trigger guidance and overly technical language that users wouldn't naturally use. The absence of a 'Use when...' clause and concrete action examples significantly weakens its utility for skill selection.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'automate Mac apps', 'control desktop applications', 'UI automation on macOS', or 'interact with app windows'.
List specific concrete actions such as 'click buttons', 'read window text', 'navigate menus', 'fill form fields', or 'interact with system dialogs'.
Include user-friendly synonyms alongside technical terms, e.g., 'desktop automation (AXUIElement)' or 'Mac app control'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (macOS Accessibility APIs, AXUIElement) and mentions some actions (element discovery, system interaction, desktop automation), but doesn't list specific concrete actions like 'click buttons', 'read window contents', or 'navigate menus'. | 2 / 3 |
Completeness | Describes what it does (macOS accessibility automation) 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 description is weak on the 'what' as well. | 1 / 3 |
Trigger Term Quality | Includes technical terms like 'AXUIElement', 'TCC permissions', and 'macOS Accessibility APIs' which are accurate but not natural user language. Missing common variations users might say like 'automate Mac apps', 'control desktop apps', 'UI automation', or 'screen automation'. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche with distinct technical focus on macOS Accessibility APIs specifically. The mention of AXUIElement, TCC permissions, and macOS-specific terminology makes it unlikely to conflict with general automation or cross-platform skills. | 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 strong, well-structured skill for macOS Accessibility automation with excellent actionability through complete, executable code examples and clear TDD workflows with validation checkpoints. The main weakness is moderate verbosity in the overview and repeated security principles that could be consolidated. The security-first approach with permission tiers, blocklists, and audit logging is thoroughly documented.
Suggestions
Consolidate sections 2.1-2.4 into a single 'Core Principles' section to reduce repetition of security concepts
Remove the 'Core Expertise Areas' list in section 1 as it restates what the code examples demonstrate
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in the overview section explaining Claude's expertise areas and repeating security principles multiple times. The tables and framework lists add bulk that could be condensed, though the code examples themselves are appropriately lean. | 2 / 3 |
Actionability | Provides fully executable Python code examples with proper imports, concrete class implementations, and copy-paste ready patterns. The TCC validation, element discovery, and action execution patterns are complete and immediately usable. | 3 / 3 |
Workflow Clarity | Excellent multi-step TDD workflow with explicit validation checkpoints (Step 1-4), clear pre-implementation checklists with phases, and explicit verification commands. The workflow includes feedback loops for error recovery and validation gates before proceeding. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to implementation to verification. References to advanced-patterns.md, security-examples.md, and threat-model.md are one-level deep and clearly signaled at the end. Content is appropriately split between quick reference tables and detailed code. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 12 / 16 Passed | |
- Repository
- martinholovsky/claude-skills-generator
- Commit
1086ef2
- 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.