linux-at-spi2
Expert in AT-SPI2 (Assistive Technology Service Provider Interface) for Linux desktop automation. Specializes in accessible automation of GTK/Qt applications via D-Bus accessibility interface. HIGH-RISK skill requiring security controls for system-wide access.
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/linux-at-spi2/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 niche with AT-SPI2 and Linux desktop automation, making it distinctive. However, it lacks concrete action verbs describing what the skill actually does and critically omits any 'Use when...' guidance, making it difficult for Claude to know when to select this skill over others.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when automating Linux desktop applications, performing accessibility testing, or scripting GTK/Qt GUI interactions'
Include specific concrete actions such as 'Clicks buttons, reads screen elements, navigates menus, fills forms, and extracts text from accessible UI components'
Add natural user terms alongside technical jargon, such as 'GUI automation', 'screen reader scripting', 'Linux app automation', or 'accessibility API'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AT-SPI2, Linux desktop automation) and mentions GTK/Qt applications and D-Bus accessibility interface, but lacks concrete actions like 'click buttons', 'read screen elements', 'navigate menus', or 'automate form filling'. | 2 / 3 |
Completeness | Describes what the skill is about (AT-SPI2 expertise, accessible automation) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes technical terms like 'AT-SPI2', 'GTK', 'Qt', 'D-Bus', and 'Linux desktop automation', but misses natural user phrases like 'automate Linux apps', 'screen reader', 'accessibility testing', 'GUI automation', or 'desktop scripting'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of AT-SPI2, Linux desktop, GTK/Qt, and D-Bus accessibility creates a very specific niche that is unlikely to conflict with other skills; this is clearly distinct from general automation or other platform-specific tools. | 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 with excellent actionability through complete, executable code examples and clear security patterns. The TDD workflow and pre-implementation checklist provide good validation checkpoints. Minor verbosity in the overview sections explaining Claude's expertise areas could be trimmed, but overall the content is appropriately dense for a high-risk automation skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in the overview section listing expertise areas Claude already possesses. The 'Core Expertise Areas' and 'Core Responsibilities' sections repeat concepts. However, the code examples are appropriately dense and the security tables are efficient. | 2 / 3 |
Actionability | Excellent executable code examples throughout - the SecureATSPI class, ElementFinder, event monitoring, and text input patterns are all copy-paste ready. The TDD workflow includes complete test examples with proper imports and assertions. | 3 / 3 |
Workflow Clarity | Clear multi-step TDD workflow with explicit phases (write failing test → implement → refactor → verify). The pre-implementation checklist provides explicit validation checkpoints across three phases. Security validation steps are clearly sequenced with feedback loops. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to implementation patterns to security standards. References to external files (security-examples.md, threat-model.md, advanced-patterns.md) are one level deep and clearly signaled at the end. | 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.