host-computer-use-linux

Backend-specific Linux guidance for `computer_use_remote`. Load after `status` or `start_session` reports backend_family `linux`, backend_id `wayland`, or AT-SPI features. Covers AT-SPI structural targeting, Wayland portal 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

High

Do not use without reviewing

Quality

Content

100%

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

A lean, highly actionable skill body with explicit verification feedback loops and clean sectioning. No bundle files are referenced, so the single-file, well-sectioned organization is appropriate.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes competence (never explains what AT-SPI/Wayland/Linux are), and every section — JSON examples, operation lists, shortcut bullets — earns its place without padding.	3 / 3
Actionability	It provides complete, copy-paste-ready JSON tool calls for ax_snapshot and ax_action, concrete operation/shortcut lists, and exact error codes with a precise stop-and-ask response.	3 / 3
Workflow Clarity	Sequences are explicit with feedback loops: snapshot-then-narrow on ambiguity/missing targets, an ordered fallback chain, and 'inspect the fresh screenshot before saying it worked; if text lands in the wrong app, stop and reassess'.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the skill is self-contained with no external file references, organized into clear sections, fitting the 'no need for external references → 3 with well-organized sections' carve-out.	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 strong, specific description with explicit what-and-when trigger guidance and a clear niche. The only weakness is that trigger terms are backend machine-signals rather than natural user language.

Dimension	Reasoning	Score
Specificity	It enumerates concrete capability areas — 'AT-SPI structural targeting, Wayland portal caveats, and screenshot verification' — for a named backend, matching the 'lists multiple specific concrete actions' anchor rather than just naming a domain.	3 / 3
Completeness	It states what it covers ('Backend-specific Linux guidance... Covers AT-SPI structural targeting, Wayland portal caveats, and screenshot verification') and gives an explicit 'Load after...' trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Triggers are precise machine signals ('backend_family linux', 'backend_id wayland', 'AT-SPI features') rather than natural phrases a user would say, so coverage is relevant but leans toward technical jargon over user utterances.	2 / 3
Distinctiveness Conflict Risk	The Linux/Wayland backend niche with backend_family/backend_id signal triggers is highly specific and unlikely to fire for the wrong skill.	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-linux/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.