host-computer-use-windows

Backend-specific Windows guidance for `computer_use_remote`. Load after `status` or `start_session` reports backend_family/backend_id `windows` or Windows UI Automation features. Covers UIA structural targeting, Windows session caveats, and screenshot verification.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, actionable reference with concrete JSON tool-call examples, a clear numbered UIA loop, and built-in verification/error-recovery checkpoints. Content is well-sectioned with no need for external references.

Dimension	Reasoning	Score
Conciseness	The body is dense, domain-specific reference material with copy-paste JSON examples and no padding about concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides fully executable computer_use_remote tool-call JSON examples plus an enumerated list of operations and targeting options, giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	The 'Preferred loop' is an explicit numbered sequence with a fallback, backed by fresh-snapshot feedback loops on ambiguity/missing-target and an explicit verification checkpoint ('UIA actions are attempts, not proof... inspect that image').	3 / 3
Progressive Disclosure	No bundle files are provided and none are needed; the body is organized into clear sections (Targeting, Session Caveats, Geometry), which per the simple-skill guideline earns a top score.	3 / 3
	Total	12 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-scoped, complete description that clearly states both capabilities and a concrete load trigger for the Windows backend. Its main weakness is that the trigger terms are technical system signals rather than natural user phrasing.

Suggestions

Add a plain-language trigger clause users might actually say (e.g. 'Use when the connected backend is Windows and you need to drive native UI controls') alongside the technical backend signal.

Convert the topic-area list into concrete verbs (e.g. 'target UI controls structurally, handle Windows session failures, verify outcomes via screenshots') to sharpen the specificity anchor.

Dimension	Reasoning	Score
Specificity	Enumerates concrete capability areas — 'UIA structural targeting, Windows session caveats, and screenshot verification' — rather than vague actions, matching the multiple-specific-concrete-actions anchor.	3 / 3
Completeness	Explicitly states what ('Covers UIA structural targeting, Windows session caveats, and screenshot verification') and when ('Load after status or start_session reports backend_family/backend_id windows'), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	Triggers are technical/system signals ('backend_family/backend_id windows', 'Windows UI Automation features') rather than phrasing a user would naturally say, so coverage of natural keywords is partial.	2 / 3
Distinctiveness Conflict Risk	Tightly scoped to the Windows computer-use backend with backend-specific triggers, making it unlikely to fire for other host-computer-use skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agent0ai/agent-zero
Path: plugins/_a0_connector/skills/host-computer-use-windows/SKILL.md
Commit: 391fab9

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.