computer-use-automation SKILL.md skillA

computer-use-automation from borghei/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add borghei/claude-skills/computer-use-automation@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
borghei/claude-skills
Path
engineering/computer-use-automation/SKILL.md
Versions recorded
3
Latest version
v1.0.0, committed Oct 23, 2026
First version recorded
Jun 29, 2026
Size
7,872 bytes
Repository stars
1,075
License
a license file GitHub does not identify

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".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add borghei/claude-skills/computer-use-automation@sha256:8aaa56f19ec56ba7

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_m3237e7w5icycr4z.svg)](https://markdownregistry.com/a/art_m3237e7w5icycr4z)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jun 29, 2026 and Oct 23, 2026, about one every 58 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-23 1b15d44 7,872 BA view · diff
v1.0.02026-10-23 2b5180a 6,169 BA view · diff
v1.0.02026-06-29 5e4f0f8 6,066 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7872 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

borghei/claude-skills · 1,075 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_m3237e7w5icycr4z
GET https://markdownregistry.com/api/v1/resolve?ref=borghei/claude-skills/computer-use-automation
GET https://markdownregistry.com/api/v1/blob/8aaa56f19ec56ba729a1db9f6b8022ef931586256300b44f0fa600d556fae7a2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from borghei/claude-skills

python-tools Cursor rule
borghei/claude-skills · .cursor/rules/python-tools.mdc · Conventions for the Python automation tools that ship inside skills.
git:20260629.ee6fb37 · audit A · 1,075 stars
repo-overview Cursor rule
borghei/claude-skills · .cursor/rules/repo-overview.mdc · What the AI Skills Library is, its structure, and core principles. Apply when reasoning about the repo as a whole.
git:20261023.4fa0452 · audit A · 1,075 stars
skill-authoring Cursor rule
borghei/claude-skills · .cursor/rules/skill-authoring.mdc · Conventions for writing or editing a SKILL.md skill package.
git:20260629.ee6fb37 · audit A · 1,075 stars
.cursorrules Cursor rule
borghei/claude-skills · .cursorrules
git:20261023.4fa0452 · audit A · 1,075 stars
AGENTS.md AGENTS.md file
borghei/claude-skills · AGENTS.md
git:20261007.6533a59 · audit A · 1,075 stars
CLAUDE.md CLAUDE.md file
borghei/claude-skills · CLAUDE.md
git:20261007.4a698e8 · audit A · 1,075 stars
CLAUDE.md@agents CLAUDE.md file
borghei/claude-skills · agents/CLAUDE.md
git:20260321.deb73d4 · audit A · 1,075 stars
CLAUDE.md@business-growth CLAUDE.md file
borghei/claude-skills · business-growth/CLAUDE.md
git:20260527.3201c50 · audit A · 1,075 stars
channel-economics SKILL.md skill
borghei/claude-skills · business-growth/channel-economics/SKILL.md · Channel economics: design and analyze the financial structure of go-to-market channels. Use when picking a channel mix…
v1.0.0 · audit A · 1,075 stars
churn-prevention SKILL.md skill
borghei/claude-skills · business-growth/churn-prevention/SKILL.md · SaaS churn reduction covering cancel flow design, dynamic save offers, exit survey architecture, dunning sequences…
v1.0.0 · audit A · 1,075 stars
commercial-policy SKILL.md skill
borghei/claude-skills · business-growth/commercial-policy/SKILL.md · Commercial policy: the governance framework defining what terms sales can offer and what triggers approval. Use when…
v1.0.0 · audit A · 1,075 stars
competitive-teardown SKILL.md skill
borghei/claude-skills · business-growth/competitive-teardown/SKILL.md · Systematic competitor analysis covering product teardowns, 12-dimension scoring rubric, feature comparison matrices…
v1.0.0 · audit A · 1,075 stars

Every file in borghei/claude-skills

Browse by kind, by grade A, or by owner.