← All skills

visual-observation-targeting

100 / 100 · Low risk

Fine to try.

By leeoohoo/chatos_rs (GitHub) · other · 312 stars · scanned at commit 1dd3979

Locate visible macOS targets from fresh screenshots and convert screenshot pixels to global display points without confusing the AI cursor or physical pointer.

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'visual-observation-targeting' ] || [ -L ~/.agents/skills/'visual-observation-targeting' ]; then echo 'A skill folder named visual-observation-targeting already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/leeoohoo/chatos_rs' "$d" && git -C "$d" checkout --quiet '1dd3979d80737893fea57d8ac0908f6daa40de13' -- 'plugins/computer-use/skills/visual-observation-targeting' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/computer-use/skills/visual-observation-targeting' ~/.agents/skills/'visual-observation-targeting' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'visual-observation-targeting' ~/.claude/skills/'visual-observation-targeting' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for leeoohoo/chatos_rs shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/leeoohoo/chatos_rs.svg)](https://zalavijaysinh.github.io/skilltrust/repos/leeoohoo/chatos_rs/)

Score history