computer-use-agents SKILL.md skillA
computer-use-agents from davila7/claude-code-templates is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add davila7/claude-code-templates/computer-use-agents@git:20261024.13da94cPins git:20261024.13da94c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- davila7/claude-code-templates
- Path
cli-tool/components/skills/ai-research/computer-use-agents/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261024.13da94c, committed Oct 24, 2026
- First version recorded
- Jan 25, 2026
- Size
- 9,440 bytes
- Repository stars
- 33,152
- License
- MIT
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
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 Agents
## Patterns
### Perception-Reasoning-Action Loop
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.
Key components:
1. PERCEPTION: Screenshot captures current screen state
2. REASONING: Vision-language model analyzes and plans
3. ACTION: Execute mouse/keyboard operations
4. FEEDBACK: Observe result, continue or correct
Critical insight: Vision agents are completely still during "thinking"
phase (1-5 seconds), creating a detectable pause pattern.
**When to use**: ['Building any computer use agent from scratch', 'Integrating vision models with desktop control', 'Understanding agent behavior patterns']
```python
from anthropic import Anthropic
from PIL import Image
import base64
import pyautogui
import time
class ComputerUseAgent:
"""
Perception-Reasoning-Action loop implementation.
Based on Anthropic Computer Use patterns.
"""
def __init__(self, client: Anthropic, model: str = "claude-sonnet-4-20250514"):
self.client = client
self.model = model
…Read the whole file at its exact version.
How to install
mdr add davila7/claude-code-templates/computer-use-agents@sha256:216a194aed42ccbfThe line at the top of this page pins the label git:20261024.13da94c, 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.
[](https://markdownregistry.com/a/art_cimnnflspyf3g7wr)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jan 25, 2026 and Oct 24, 2026, about one every 136 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.13da94c latest | 2026-10-24 | 13da94c | 9,440 B | A | view · diff |
| git:20260804.afc6e69 | 2026-08-04 | afc6e69 | 9,428 B | A | view · diff |
| git:20260125.1deb97c | 2026-01-25 | 1deb97c | 9,435 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9440 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
davila7/claude-code-templates · 33,152 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cimnnflspyf3g7wr GET https://markdownregistry.com/api/v1/resolve?ref=davila7/claude-code-templates/computer-use-agents GET https://markdownregistry.com/api/v1/blob/216a194aed42ccbfb95d33da5a66398a9f21ee5c0744c9f8a0c9298f8ec567c5
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.