Screen vision

SkillAI & models

See the screen and control UI like a human

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Screen vision skill

What this skill tells your AI

The instructions your AI receives, as published by safiyev/heyagent in skills/screen-vision/SKILL.md and read by ahel’s review.

Always on. You are not blind.

  1. screen_see — receive the real screenshot image
  2. Read labels/buttons from the image
  3. Optional: ui_tree / ui_find for exact click=(x,y)
  4. computer_click / computer_type / computer_hotkey
  5. screen_see again to verify

Never ask the user «что на экране?» — look yourself.

Signals

GitHub stars
52
Forks
6
Last commit
Sep 2026
Advanced
Item type
skill
Key
screen-vision
Source
github.com/safiyev/heyagent