← All skills
vision-skills
92 / 100 · Low risk
Fine to try. Some of what it can do is expected: a media skill usually calls an AI service over the internet.
By Anionex/agent-vision-toolkit (GitHub) · media · 1,256 stars · scanned at commit 328c0ae
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — …
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 19 places.
Show 16 more
- skills/vision-skills/SKILL.md, line 126
$ ground screenshot.png "the send button" - skills/vision-skills/SKILL.md, line 137
detect <image> # every UI element - skills/vision-skills/SKILL.md, line 159
trace <image> # b/w spline SVG to stdout - skills/vision-skills/SKILL.md, line 175
crop <image> --region X1,Y1,X2,Y2 # writes <image-stem>.crop.png next to the input - skills/vision-skills/SKILL.md, line 194
python3 scripts/extract_fg.py shot.png --region X1,Y1,X2,Y2 -o icon.png - skills/vision-skills/SKILL.md, line 220
python3 scripts/html_shot.py page.html # writes page.png, 1280x800 - skills/vision-skills/SKILL.md, line 240
python3 scripts/pixel_diff.py <a> <b> # path is relative to this skill dir - skills/vision-skills/SKILL.md, line 250
python3 scripts/dominant_colors.py <image> --region X1,Y1,X2,Y2 # top colour clusters + shares - skills/vision-skills/SKILL.md, line 269
cp "<the temp path>" work/shot.png - skills/vision-skills/scripts/html_shot.py, line 237
def wait_for_devtools_port(profile: Path, process: subprocess.Popen, - skills/vision-skills/scripts/html_shot.py, line 432
process: subprocess.Popen | None = None - skills/vision-skills/scripts/html_shot.py, line 436
process = subprocess.Popen(command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) - skills/vision-skills/scripts/html_shot.py, line 488
except subprocess.TimeoutExpired: - skills/vision-skills/scripts/html_shot.py, line 548
result = subprocess.run(command, text=True, capture_output=True) - skills/vision-skills/scripts/long_screenshot_ocr.py, line 645
completed = subprocess.run( - skills/vision-skills/scripts/long_screenshot_ocr.py, line 1239
except (OSError, ValueError, FileNotFoundError, RuntimeError, subprocess.TimeoutExpired) as exc:
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README. Expected for a media skill.
Found in 2 places.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'vision-skills' ] || [ -L ~/.agents/skills/'vision-skills' ]; then echo 'A skill folder named vision-skills already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Anionex/agent-vision-toolkit' "$d" && git -C "$d" checkout --quiet '328c0ae015a109d0b5539f0dd38cd65974b8147e' -- 'skills/vision-skills' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/vision-skills' ~/.agents/skills/'vision-skills' && 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/'vision-skills' ~/.claude/skills/'vision-skills' (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 Anionex/agent-vision-toolkit shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/Anionex/agent-vision-toolkit/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 328c0ae | 92 |
| 2026-11-07 | 328c0ae | 92 |