linux-desktop

Use only for Agent Zero's built-in Docker/Xpra Linux Desktop, XFCE apps, LibreOffice GUI apps, file manager, terminal, or visual workflows inside the Agent Zero runtime. Not for A0 CLI /computer-use or computer_use_remote host control.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/_desktop/skills/linux-desktop/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The body is highly actionable with executable commands and well-sequenced, validated workflows, and it correctly externalizes implementation into the bundled scripts. Its main weakness is repetition — several rules are restated across sections — which inflates token cost without adding clarity.

Suggestions

Consolidate the repeated host-use boundary, structured-first hierarchy, and screenshot-staleness rules into a single canonical statement; cross-reference it instead of restating it in Boundary, Operating Model, Practical Rules, and Terminal sections.

Move the long nested-CLI smoke-test example into a reference file (e.g. references/nested-cli.md) and keep a short pointer in SKILL.md to improve progressive disclosure and reduce inline length.

Add an explicit 'if verification fails, fix and retry' loop to the general desktop and calc workflows so workflow_clarity reaches a full 5 across all multi-step paths.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, domain-specific operational detail (Xpra display, desktopctl subcommands, context-id screenshot paths) rather than general-knowledge padding, but it repeats the same few rules across sections — the host-use boundary, structured-first hierarchy, and screenshot-staleness rule each appear 3-4 times — so it could be tightened; it is not a 2 because the bulk earns its place and is not generic fluff.	3 / 5
Actionability	The body is packed with copy-paste-ready, executable commands — '$DESKTOP check', 'launch calc', 'calc-set-cell /a0/usr/workdir/example.xlsx Sheet1 B2 "Cowork verified live"', sequence/batch heredocs, and coordinate flows — covering the common cases end to end, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints (the numbered Terminal verification loop, the nested-CLI smoke test with a verify-before-send step, and 'verify immediately afterward' for coordinate actions); it is not a 5 because only the terminal flow has a full validate->fix->retry feedback loop while the general desktop and calc flows have verification but no explicit retry-on-failure loop.	4 / 5
Progressive Disclosure	Implementation is correctly externalized into the real bundle scripts (scripts/desktopctl.sh, scripts/calc_set_cell.py) referenced by absolute path and one level deep, with clear section headers throughout; it is not a 5 because SKILL.md itself is a long, mostly-inline document whose terminal/nested-CLI examples could be trimmed or split into a reference file.	4 / 5
	Total	16 / 20 Passed

Description

68%Weight 40%Scale 1-5

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 is highly distinctive with explicit trigger and conflict guidance, but it frames the skill as a set of surfaces rather than concrete actions, leaving the capability statement thin. Tightening the 'what' with a few concrete verbs would lift specificity and completeness.

Suggestions

Add 1-2 concrete actions to the description (e.g., 'Launch and control XFCE/LibreOffice apps, drive the terminal, and verify visual workflows') so the 'what' is action-level, not just surface-level.

Consider a short 'Use when ...' phrasing that pairs trigger phrases with the action performed, to push completeness toward 5.

Dimension	Reasoning	Score
Specificity	The description names the domain richly ('built-in Docker/Xpra Linux Desktop, XFCE apps, LibreOffice GUI apps, file manager, terminal, or visual workflows') but lists surfaces rather than concrete actions; there are no capability verbs like launch, control, edit, or verify, matching the 'names the domain but actions are minimal or generic' anchor and falling below the 3 anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It has an explicit 'when' clause ('Use only for ...') and an implied domain-level 'what' (the surfaces it covers), satisfying both halves; it is not a 5 because the 'what' is surface-level rather than concrete trigger-action pairs, and not a 3 because the 'when' guidance is explicit rather than weakly implied.	4 / 5
Trigger Term Quality	Natural terms a user would say are well covered — 'Linux Desktop', 'XFCE apps', 'LibreOffice GUI apps', 'file manager', 'terminal', 'visual workflows' — matching the 'good keyword coverage; a few natural terms missing' anchor; it is not a 5 because some synonyms/extensions are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche ('Agent Zero's built-in Docker/Xpra Linux Desktop') and explicitly disambiguates from the conflicting host-control skill ('Not for A0 CLI /computer-use or computer_use_remote host control'), giving minimal conflict risk per the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: agent0ai/agent-zero
Path: plugins/_desktop/skills/linux-desktop/SKILL.md
Commit: b22a144

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.