Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/anionex-agent-vision-toolkit)MCP servers that connect the AI to services for the same work
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.
Same kind of work, ordered like the Skills list
| This one agent-vision-toolkit | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| Maker | Anionex | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 1,262 | 111,852 | 67,796 | 32,458 | 29,958 |
| Last code change | Oct 13, 2026 | Nov 17, 2026 | Nov 13, 2026 | Jun 24, 2026 | Oct 30, 2026 |
| License | MIT | Apache-2.0 | MIT | MIT | AGPL-3.0 |
1 skills (instruction sets) by Anionex that an AI reads and follows · not an MCP server
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Claude CodeCodexOpenCode
From the maker’s README and the folders in the repo
GitHub account Anionex (person), 3 years old
★ 1,262 stars · code last changed Oct 13, 2026
5 scripts that can run on a computer: scripts/long_screenshot_ocr.py, scripts/dominant_colors.py, scripts/extract_fg.py, scripts/html_shot.py and 1 more
Scripts that go online: scripts/html_shot.py
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 328c0ae (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Uploading to claude.ai would fail: the description is over 200 characters (582). Use "Let the AI install it" instead
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /vision-skills or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
npx skills add Anionex/agent-vision-toolkit --skill vision-skills -a codex -g --copyCopied from the maker’s README; it downloads and runs the maker’s code
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/anionex/agent-vision-toolkit.git /tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae/skills/vision-skills' ~/.claude/skills/vision-skillsThe ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Put the vision-skills folder at ~/.agents/skills/vision-skills
~ is your home folder ($HOME)
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/anionex/agent-vision-toolkit.git /tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae/skills/vision-skills' ~/.agents/skills/vision-skillsChecked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/anionex/agent-vision-toolkit.git /tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae/skills/vision-skills' ~/.agents/skills/vision-skillsCopy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick vision-skills
Checked against official docs Nov 12, 2026 · Source: cursor.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/anionex/agent-vision-toolkit.git /tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-anionex-agent-vision-toolkit-328c0ae/skills/vision-skills' ~/.cursor/skills/vision-skillsFor other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
✓ Commands checked Nov 18, 2026
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: vision-skills
description: >-
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 — and to re-check an
image yourself when a description you were given lacks a detail.
---
# vision-skills
Five local CLIs that give a text-only agent eyes. They read one shared
vision config (`VISION_API_KEY` / `VISION_BASE_URL` / `VISION_MODEL` /
`LANG`), plus the optional Python-client settings `VISION_API_PROTOCOL`,
`VISION_REASONING_EFFORT`, and `VISION_USER_AGENT` — no extra credentials.
Pick the tool by the question you are answering:
| Question | Tool |
|---|---|
| "What does this image show / say?" | `glance` |
| "Where is X?" — a thing you can name | `ground` |
| "Where are all the Xs?" — every instance of a kind | `detect` |
| "What is its exact shape, size, offset?" | `trace` |
| "Cut this box out as its own image file" | `crop` |
| "OCR this long screenshot / scrolling page / chat history" | `scripts/long_screenshot_ocr.py` |
| "Extract the icon/logo foreground as transparent PNG — manual region or auto (cropped+scaled screenshots)" | `scripts/extract_fg.py` |
| "Turn this HTML file into a viewport or full-page screenshot" | `scripts/html_shot.py` |
| "Which colours dominate a region, and which palette value fits it?" | `scripts/dominant_colors.py` |
| A relation none of them return — a gap, a distance between two located things | code over the pixels (Pillow) |
`glance` answers what something is; `ground` and `detect` answer where.
You give `ground` a description of a particular thing; you give `detect` a
kind and it enumerates the instances.
Both give real coordinates, but they are not pixel-exact: the box arrives
on a 0-1000 grid and is scaled to your image, so the last pixel or few are
not reliable. That is accurate enough to crop with, to click, to compare
positions against. When a number has to be exact, `trace` derives it from
the actual pixels — offsets, sizes, shapes.
## Use the provided tools before hand-rolled pixels
Everything this toolkit ships a tool for, call the tool — do not rewrite
it with Pillow in the middle of a task. The CLIs exist so the same pixel
work is not hand-coded differently every time:
- cut a box out of an image → `crop`, not `Image.open(...).crop(...)`
- sample a region's palette → `scripts/dominant_colors.py`
- compare two images → `scripts/pixel_diff.py`
- vectorize to SVG → `trace`
- locate / inventory elements → `ground` / `detect`
- describe / OCR an image → `glance`
- safely split, OCR, and merge a long screenshot → `scripts/long_screenshot_ocr.py`
- HTML file to a viewport or full-page screenshot → `scripts/html_shot.py`
Hand-written Pillow is only for what none of them return: a relation
between two things you already located (a gap, a distance), a resize or
overlay, drawing. If you catch yourself writing `.crop()`, `.convert()`,
or histogram code where one of the tools above fits, replace it with the
tool call — same coordinates, same box format, and the output feeds the
next tool directly.
## glance — ask about an image
```bash
glance <image> # detailed description
glance <image> -q "<question>" # targeted question (qualitative only)
glance <image> --ocr # verbatim OCR
glance <image> --region X1,Y1,X2,Y2 -q "..." # zoom into a crop
glance <img1> <img2> -q "..." # compare in ONE call
```
When you do compare with `glance`, pass all paths to one call — separate
calls cannot see both images, so two descriptions compared afterwards are
two hallucination surfaces, not a comparison. `--region` uploads only the
crop, so small text and icons become readable.
But "what changed between these two?" is not a glance question. A one-word
badge or a small shift is a rounding error to a vision model and exact to
`scripts/pixel_diff.py`. Diff first to get the box, then `glance --region`
that box to read what the change actually is.
For a tall scrolling screenshot, do not send the whole image through one OCR
call and accept the model's downscaling loss. Run the long-screenshot workflow,
which finds low-content cut bands, invokes `glance` on each chunk, uses
structured extraction for chat histories, merges only duplicated overlap, and
writes a boundary audit:
```bash
python3 scripts/long_screenshot_ocr.py work/page.png -o work/page.ocr.md
python3 scripts/long_screenshot_ocr.py work/chat.png --mode chat --resume -o work/chat.ocr.md
```
Read `references/long-screenshot-ocr.md` before using it. It defines the
verification pass for unsafe cuts and chat-message boundaries.
## ground — locate a named target
```bash
ground <image> "<target description>"
ground <image> "<target>" --region X1,Y1,X2,Y2
```
Output: `x1: .., y1: .., x2: .., y2: ..` in original-image pixels — with
`--region` too (crop hits are mapped back).
Provider-native 0-1000 boxes do not all use the same array order: Gemini uses
`[y0, x0, y1, x1]`, while Qwen3-VL, Qwen3.5, and Qwen3.6 use
`[x0, y0, x1, y1]`. Grounding code must select the order by model family (or
an explicit override) before scaling to pixels; never parse every provider as
Gemini-style `yxyx`.
If several boxes come back numbered, your description matched more than
one element rather than picking out a single thing. Narrow it with what
distinguishes the one you mean — its text, its position, the block it sits
in — and ask again.
The box is a handle, not just an answer — it feeds the next call:
```bash
$ ground screenshot.png "the send button"
x1: 1067, y1: 841, x2: 1108, y2: 881
$ glance screenshot.png --region 1067,841,1108,881 -q "is it enabled or greyed out?"
```
That two-step is how you inspect anything too small to survive a
full-image pass.
## detect — find every instance of a kind
```bash
detect <image> # every UI element
detect <image> "buttons" # one kind only
detect <image> --region X1,Y1,X2,Y2 # inside one box
detect <image> "text" --fail-on-empty # fail if no text is detected
```
The default category targets UI screenshots. For photographs or video frames,
pass an explicit category such as `"objects"` or `"text"`. An empty inventory
normally prints `no elements detected` and exits 0; `--fail-on-empty` instead
exits 1 with a stderr diagnostic and no stdout. This reports an empty model
result, not proof that the image has no matching elements.
You name a particular thing for `ground`; you name a kind for `detect` and
it enumerates the instances. Output is a numbered list with each item's
visible text and box. A full-screen
pass is a fast first draft — counts vary run to run on dense screens. For
completeness, detect the layout blocks first, then `detect --region` each
block.
## trace — exact shape geometry (local, no vision API)
```bash
trace <image> # b/w spline SVG to stdout
trace <image> --polygon # boxy diagrams/wireframes
trace <image> --region X1,Y1,X2,Y2 -o out.svg # crop first
```
Coordinates come from the actual pixels, not a model's estimate. Flat,
high-contrast graphics only; text becomes curves (pair with `--ocr` when
the text matters). Small images are upscaled automatically before tracing,
so a 30px icon traces as readily as a screenshot — size is not a reason to
skip the tool. Before shipping or reusing a traced SVG, read
`references/restore-graphic.md` — it holds the reuse traps and the
ship-vs-hand-write call.
## crop — cut a pixel box out of an image (local, no vision API)
```bash
crop <image> --regiAsk, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.