Xhs Rental Ocr
v1.0.0从小红书笔记图片提取结构化数据（租金/面积/单价等），自动裁切长图 + OCR 识别 + 导出 Excel。 使用 Apple Vision 框架进行离线 OCR，支持中文识别。 Use when: 用户需要从小红书/社交媒体图片提取表格数据、价格信息、统计数据等。
⭐ 0· 99·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included code: scripts perform image slicing, call Apple Vision via pyobjc, run regex extraction, and export to Excel. The SKILL.md and README correctly describe macOS-only usage and the required Python packages. Minor metadata mismatch: registry metadata lists no required binaries while SKILL.md lists python3 as a required binary, but this is a documentation inconsistency rather than a functional mismatch.
Instruction Scope
Runtime instructions limit work to downloading (TODO)/reading local images, slicing, running Apple Vision OCR, parsing text, and writing Excel files. There are no instructions to read unrelated system files, access credentials, or transmit data to external endpoints. The only network activity implied is cloning the repo and pip-installing dependencies during setup; the OCR itself is performed locally.
Install Mechanism
No automated install spec is provided (instruction-only), and required dependencies are standard Python packages (Pillow, openpyxl, pyobjc-framework-*). These are installed via pip from PyPI in the documentation — acceptable and traceable. No downloads from obscure hosts or archive extraction from arbitrary URLs are present.
Credentials
The skill requests no environment variables, no credentials, and no config paths. This is proportionate to the stated functionality (local OCR and Excel export). The code does write cropped image files alongside originals, which is expected behavior but worth noting.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configs, and is user-invocable only. It does not persist credentials or alter agent policies.
Assessment
This package appears to do what it says: local macOS Apple Vision OCR → parse → Excel. Before installing: 1) Confirm you are on macOS and have Python 3.9+; pyobjc packages require pip and network access to install. 2) Verify the GitHub repo URL actually exists and is from a trusted author (SKILL.md/README reference a GitHub account). 3) Review the scripts if you will process sensitive images (the code writes sliced images to the same folder and performs local file I/O). 4) Run in a contained environment (or inspect the code) if you are unsure; no credentials or network exfiltration are requested by the code, but dependency installation will contact PyPI.Like a lobster shell, security has layers — review code before you run it.
latestvk974drgs1xks93xqx823tv2rnx83h7sh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.