SkillAgentSearch skills...

computer-use-automation

Decides when a GUI-driving (computer-use) agent beats an API and lints planned screen actions for missing confirmation, verification and grounding

Install / Use

npx skills add borghei/Claude-Skills --skill computer-use-automation

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Category

Automation

Supported Platforms

Universal

Our assessment of computer-use-automation

computer-use-automation scores 87/100 on our quality scale, 1705th of 2,769 Automation skills we index.

Its SKILL.md is 5.9 KB long, well organised into 16 sections with 1 code example: a thorough specification that gives an agent plenty to work with.

It has 817 GitHub stars, a meaningful sign that others use it.

Substance
29/30
Structure
17/20
Description
15/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so computer-use-automation is actively maintained.
  • Our last check on 2026-10-11 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

computer-use-automation compared with similar skills

All 4 of these similar skills score higher than computer-use-automation; compare them before choosing.

SkillScoreStarsUpdatedFormat
computer-use-automation (this skill)by borghei8781757d agoSKILL.md
taste-skillby Leonxlnx100117.6k9d agoCLAUDE.md
Agent-Reachby Panniantong100112.7k9d agoCLAUDE.md
rufloby ruvnet10082.0ktodayCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md

Frequently asked questions

How do I install computer-use-automation?
Run npx skills add borghei/Claude-Skills --skill computer-use-automation. The install tabs above show the steps for each supported agent.
Which AI agents does computer-use-automation work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is computer-use-automation safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is computer-use-automation still maintained?
The repository was last updated about 2 months ago, so computer-use-automation is actively maintained.

name: computer-use-automation description: > This skill should be used when the user asks to "build a computer-use agent", "automate a GUI with an AI agent", "when to use computer use vs an API", "make browser automation reliable", or "design screenshot-driven agent actions". license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: engineering domain: ai-agents updated: 2026-06-29 tags: [computer-use, browser-automation, agents, gui, reliability]

Computer Use Automation

Category: Engineering Domain: AI Agents

Overview

The Computer Use Automation skill helps you design AI agents that operate a graphical interface the way a person does — take a screenshot, reason about what is on screen, then click, type, scroll, or navigate, and repeat. It covers the core perception→reason→action loop, the decision of when computer-use is the right tool versus a structured API/MCP tool (prefer a real API whenever one exists; reach for computer-use only for GUIs with no programmatic surface), reliability patterns (grounding every action in the current screenshot, verifying after each step, recovering from misclicks), safety guardrails (confirmation gates for destructive actions, sandboxing, avoiding blocking dialogs), and how to evaluate a computer-use agent. It is model-agnostic — the patterns apply to any computer-use-capable model and any GUI tool surface.

Clarify First

Before designing or auditing a computer-use agent, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • [ ] Does a real API/MCP tool exist? — whether the target exposes an API, SDK, CLI, or MCP server, or is GUI-only (the single biggest factor; if a real API exists, prefer it and skip computer-use)
  • [ ] Task & risk — what the agent must accomplish and whether any step is destructive or irreversible (delete, send, pay, submit), which sets the confirmation gates and sandboxing
  • [ ] Which tool — advise on tool choice for a target, or lint a planned action sequence for safety (selects tool_choice_advisor.py vs action_safety_linter.py)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Quick Start

# Decide computer-use vs API/MCP for a target
python scripts/tool_choice_advisor.py --api-exists no --gui-stability high --volume low --json

# Lint a planned action sequence for safety/reliability gaps
python scripts/action_safety_linter.py --file planned_actions.json

# Read actions from stdin and emit a markdown risk report
echo '[{"type":"click","target":"Delete"},{"type":"submit","target":"Confirm"}]' \
  | python scripts/action_safety_linter.py --format markdown

Tools Overview

| Tool | Purpose | Key Flags | |------|---------|-----------| | tool_choice_advisor.py | Recommend computer-use vs structured API/MCP for a target, with rationale | --api-exists, --gui-stability, --volume, --reversible, --json | | action_safety_linter.py | Scan a planned action list for destructive verbs, missing verification, missing confirmation gates, and dialog-triggering patterns | --file, --format, --json |

All scripts: Python 3 standard library only, argparse CLI, --json and human-readable output. Run --help for full usage.

Workflows

Decide and Design a Computer-Use Agent

  1. Run tool_choice_advisor.py with the target's API/MCP availability, GUI stability, and volume — if it says "use API/MCP," stop and build against the real interface instead.
  2. If computer-use is justified, draft the action plan as the screenshot→reason→action loop: each step re-grounds on a fresh screenshot before acting.
  3. Add a verification observation after every state-changing action (read back the resulting screen, not the intent).
  4. Insert confirmation gates before any destructive/irreversible step and choose a sandbox (throwaway profile, test account, isolated VM/container).

Audit a Planned Action Sequence

  1. Express the plan as a JSON/text list of actions (type, target, optional verified/confirmed).
  2. Run action_safety_linter.py --file plan.json to flag risky verbs, unverified state changes, ungated destructive actions, and dialog-triggering patterns.
  3. Resolve each finding — add verification steps, add confirmation gates, replace blocking-dialog flows.
  4. Re-run until clean, then dry-run in the sandbox before any real target.

Reference Documentation

  • Computer Use Patterns - The action loop; computer-use vs structured-tool decision matrix; reliability patterns (grounding, verification, recovery); safety guardrails (confirmation gates, sandboxing, blocking dialogs); evaluation approach; and common failure modes.

Common Patterns

Ground Every Action in the Current Screenshot

  • Never act on a stale screenshot or a remembered layout — re-capture before each action.
  • Reference elements by what is visible now (label, position) rather than a cached coordinate from a prior turn.
  • After acting, take a fresh screenshot and confirm the expected change actually happened before continuing.

Gate Destructive Actions and Sandbox by Default

  • Require an explicit confirmation step before delete, send, pay, submit, or any irreversible action.
  • Run in a sandbox first: throwaway browser profile, test account, or isolated VM/container.
  • Avoid flows that spawn blocking modal/native dialogs (file pickers, OS print dialogs) that the agent cannot see or dismiss; prefer paths that keep state on the page.

Prefer the Real Interface When It Exists

  • A documented API, SDK, CLI, or MCP tool is more reliable, cheaper, and more verifiable than pixels — use it.
  • Reserve computer-use for genuinely GUI-only targets, one-off tasks, or bridging gaps an API does not cover.
  • For high-volume or business-critical flows, the cost of computer-use flakiness usually justifies building or requesting an API.

Related Skills

View on GitHub
GitHub Stars817
CategoryAutomation
Updated1mo ago
Forks141

Languages

HTML

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium