What it does
Xiaomi-OCR-0
- Connects Instruction files the AI reads
- Account or key No key found in README or SKILL.md
- Category Other
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/xiaomi-research-xiaomi-ocr-0)Similar Skills
Same kind of work, ordered like the Skills list
| This one Xiaomi-OCR-0 | llmfit | claude-video | VideoCaptioner | claude-cookbooks | |
|---|---|---|---|---|---|
| Maker | xiaomi-research | AlexsJones | bradautomates | WEIFENG2333 | anthropics |
| Skills | 1 | 1 | 1 | 1 | 4 |
| GitHub stars | 1,161 | 39,096 | 21,249 | 16,577 | 54,867 |
| Last code change | Nov 10, 2026 | Nov 18, 2026 | Sep 25, 2026 | Sep 12, 2026 | Nov 17, 2026 |
| License | Apache-2.0 | MIT | MIT | GPL-3.0 | MIT |
1 skills (instruction sets) by xiaomi-research that an AI reads and follows · not an MCP server
How a Skill differs from MCP
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.
Works with
Not stated by the maker · SKILL.md skills work in apps that support Agent Skills, such as Claude Code, Codex and Cursor
Install
Is it safe?
- Who made it
GitHub account xiaomi-research (organization), 1 years old
- Use and upkeep
★ 1,161 stars · code last changed Nov 10, 2026
- Any scripts?
25 scripts that can run on a computer: skills/xiaomi-ocr/install.sh, skills/xiaomi-ocr/scripts/selftest.py, demo/server.py, demo/static/app.js and 21 more
- Uses the internet?
Scripts that go online: pipeline/ollama_backend.py
- Changes machine-wide settings?
Scripts that touch settings folders (~/.claude or settings.json): skills/xiaomi-ocr/scripts/register_codex_mcp.py
Checked automatically from the repo files at commit 4abc240 (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
Option 1Upload to claude.ai (web and app)
This skill is over 5 MB or 300 files, so we do not build a ZIP. Use "Let the AI install it" instead
Option 1Let Claude Code install it
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 /Xiaomi-OCR-0 or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
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/xiaomi-research/xiaomi-ocr-0.git /tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240/.' ~/.claude/skills/xiaomi-ocr-0Restart Claude Code, then type /Xiaomi-OCR-0 or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
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
Option 2Put the folder there yourself
Put the xiaomi-ocr-setup folder at ~/.agents/skills/xiaomi-ocr-setup
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
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/xiaomi-research/xiaomi-ocr-0.git /tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240/.' ~/.agents/skills/xiaomi-ocr-0
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- 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
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
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
Option 1Let Codex install it
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
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
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/xiaomi-research/xiaomi-ocr-0.git /tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240/.' ~/.agents/skills/xiaomi-ocr-0Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy 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 Xiaomi-OCR-0
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
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/xiaomi-research/xiaomi-ocr-0.git /tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-xiaomi-research-xiaomi-ocr-0-4abc240/.' ~/.cursor/skills/xiaomi-ocr-0In Cursor’s Agent chat, type / and pick Xiaomi-OCR-0
Option 1Let the AI install it
For 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
For Terminal users
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
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
3,821 characters · Open the full file on GitHub
---
name: xiaomi-ocr-setup
description: Install and configure the Xiaomi-OCR-0 Skill and local MCP service for document OCR, KIE, and VQA.
---
# Xiaomi-OCR-0 Skill
The only user-facing installation prompt is:
```text
Read and execute https://raw.githubusercontent.com/SeerRay-Lab/Xiaomi-OCR-0/main/SKILL.md
```
## Install this Skill into the current agent
If this file was read from the Xiaomi-OCR-0 repository and the user asked to install it,
install only the `xiaomi-ocr` Skill globally for the current agent:
```bash
npx skills add SeerRay-Lab/Xiaomi-OCR-0 --skill xiaomi-ocr --full-depth --global --agent <current-agent> --yes
```
Replace `<current-agent>` with the current agent's Skills CLI identifier; do not install to every agent or modify a
project-local skill directory. Then inspect the current agent's MCP configuration and local
machine, and follow [backend selection in the runtime Skill](skills/xiaomi-ocr/SKILL.md#choose-the-inference-backend).
Choose the service from the existing setup, hardware, and accuracy requirements; the user
does not need to name a backend or model in the installation prompt. Apply the selected
backend's environment variables before running the installer.
The runtime imports shared `evaluation_pipeline/` and `postprocess/` modules from the full repository.
Reuse a complete checkout or clone `https://github.com/SeerRay-Lab/Xiaomi-OCR-0.git`
into a user-owned code directory. Run `skills/xiaomi-ocr/install.sh` from that checkout;
do not run a detached Skill copy without setting `XIAOMI_OCR_REPO` to the checkout.
For Codex use `bash install.sh --agent=codex`; for other agents use `bash install.sh`
and merge its generated configuration into only the current agent.
Before running `install.sh`, explain that it creates a private `.venv`, downloads the
MCP dependencies listed in `requirements.txt`, and registers one MCP server entry in
Codex config when applicable. Ask the user to authorize that step if they have not already
authorized environment creation and dependency installation. Preserve all other MCP entries.
Do not install SGLang/vLLM, create an inference environment, or download model weights
unless the user's setup authorization covers those changes. State clearly if an engine or checkpoint
would need to be downloaded; reuse existing compatible installations whenever possible.
Keep any inference listener bound to loopback and do not claim inference is ready until an
image request succeeds.
For a complete agent-assisted installation, include region mode in the setup plan: explain
that PaddlePaddle, PaddleX and PP-DocLayoutV3 weights are needed, then install them in the
MCP environment under the user's existing setup authorization. Do not ask again when
that authorization already covers these dependencies and downloads. Follow step 5 of the
runtime Skill to choose a compatible CPU/GPU build, install `requirements-paddlex.txt`,
and verify a real `mode="region"` request. Respect requests for page-only setup. If the
platform is unsupported or installation fails, report region mode as unavailable and
explain which base functions passed verification; do not claim full setup is complete.
For the runtime workflow, task selection, and output handling, follow
[`skills/xiaomi-ocr/SKILL.md`](skills/xiaomi-ocr/SKILL.md). The model is served locally
through SGLang, vLLM, or the optional Ollama backend; the MCP service performs task-specific prompting, page/region
preprocessing, and result assembly.
Choose `ocr_image`/`ocr_pdf` for document parsing, `kie_image` for JSON key fields, and
`vqa_image` for questions about a document image. Prefer region mode for printed documents;
use whole-page mode for scene text, handwriting, calligraphy, historical documents, and
other nonstandard layouts where region cuts may damage context.
Discussion
Ask, 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.
From GitHub
- GitHub stars
- 1,161
- Maker
- xiaomi-research
- License
- Apache-2.0
- Last code change
- Nov 10, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 2