computer-use-agents

The fundamental architecture of computer use agents: observe screen, reason about next action, execute action, repeat. This loop integrates vision models with action execution through an iterative pipeline.

Quality

17%

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/AI-Agents-Safe-Coding-Skills/skills/computer-use-agents/SKILL.md

The canonical home for this skill is computer-use-agents in sickn33/agentic-awesome-skills

Quality

Content

27%Scale 1-3

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

This skill attempts to cover a complex topic (computer use agents) but suffers from multiple truncated code blocks that render examples non-executable, placeholder content in the sharp edges table, and excessive verbosity without proportional value. The structure dumps everything into one file with no progressive disclosure, and critical safety workflows lack validation checkpoints despite the high-risk nature of desktop automation.

Suggestions

Complete all truncated code blocks or remove them and replace with focused, minimal executable examples that demonstrate one concept each

Fix the sharp edges table - replace placeholder 'Issue' text with actual issue descriptions and provide real solutions instead of vague comments

Split the three major patterns (loop, sandboxing, Anthropic implementation) into separate referenced files, keeping SKILL.md as a concise overview with navigation links

Add explicit validation/verification steps to the workflow, such as 'verify screenshot captured successfully before sending to model' and 'confirm action result before proceeding to next step'

Dimension	Reasoning	Score
Conciseness	The content is extremely verbose with large code blocks that are incomplete (truncated mid-function), explains concepts Claude already knows (what a PDF is equivalent: what a screenshot is, what Docker is), and includes unnecessary commentary like 'Claude 3.5 Sonnet was the first frontier model to offer computer use.' The sharp edges table has empty/vague content ('Issue' repeated without actual issue descriptions).	1 / 3
Actionability	The code examples are partially concrete and show real library usage (pyautogui, Anthropic SDK, Docker), but multiple code blocks are truncated mid-function (cut off at 'buffer = io.BytesIO()' equivalent points), making them non-executable. The sharp edges table has placeholder content with no actual solutions, just vague comments like '## ALWAYS use sandboxing'.	2 / 3
Workflow Clarity	The Perception-Reasoning-Action loop is clearly enumerated (4 steps), and the sandboxing section lists isolation requirements. However, there are no validation checkpoints, no error recovery feedback loops, and no guidance on what to do when the agent fails or produces unexpected results. For a system involving destructive desktop operations, this is a significant gap.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with three large inline code blocks (all truncated). There are no references to external files for detailed content, no clear navigation structure, and the sharp edges table is broken with placeholder content. Everything is dumped into one file with no organization strategy.	1 / 3
	Total	6 / 12 Passed

Description

7%Scale 1-3

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

This description reads like an academic summary of a concept rather than a functional skill description. It lacks concrete actions, natural trigger terms, and any explicit 'Use when...' guidance, making it very difficult for Claude to know when to select this skill from a list of alternatives.

Suggestions

Replace the abstract architectural description with concrete actions, e.g., 'Automates desktop tasks by taking screenshots, identifying UI elements, clicking buttons, typing text, and navigating applications.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to control their computer, automate mouse clicks, interact with desktop applications, or perform screen-based automation.'

Remove conceptual/academic language like 'fundamental architecture' and 'iterative pipeline' in favor of user-facing terminology that describes what the skill actually does for the user.

Dimension	Reasoning	Score
Specificity	The description uses abstract, conceptual language ('fundamental architecture', 'iterative pipeline') rather than listing concrete actions. It describes a pattern ('observe screen, reason, execute, repeat') but not specific capabilities a user would invoke.	1 / 3
Completeness	The description explains a conceptual 'what' (the architecture of computer use agents) but provides no 'when' clause or explicit trigger guidance. It reads more like a textbook definition than a skill description.	1 / 3
Trigger Term Quality	The description uses technical jargon like 'vision models', 'action execution', 'iterative pipeline' rather than natural terms users would say. Terms like 'computer use agents' are somewhat relevant but most users would say things like 'control my computer', 'click', 'automate desktop tasks', etc.	1 / 3
Distinctiveness Conflict Risk	The 'computer use agents' domain is somewhat specific and distinguishable from other skills, but the abstract framing ('fundamental architecture', 'iterative pipeline') could overlap with general AI/ML architecture skills or documentation skills.	2 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/computer-use-agents/SKILL.md
Commit: 7520423

Reviewed: ~15 hours 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.