niyongsheng/free-vision-skill
Local‑only vision skill for macOS 本地化识图技能
Listed
3
Vision
Bundle verified
What it does
Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.
Best for
- macOS users who need private, fully local OCR and image understanding
- Workflows extracting table structure and coordinates from screenshots or scanned documents
- Users processing pasted images, local files, URLs, or base64 inputs without uploading image data
Not ideal for
- Windows or Linux environments, because it depends on the macOS Vision Framework
- Macs below macOS 11 or without Xcode Command Line Tools
- Latency-sensitive first-run workflows that cannot accommodate the documented 5-10 second compilation
README
free-vision-skill
Fully-local image understanding (OCR / table extraction / description) via macOS Vision. Images never leave your Mac.
Install (DSH-Plugin)
dsh plugin add @niyongsheng/free-vision-skill
Then add to cordis.patch.yml:
- insert:
- id: free-vision-skill
name: '@niyongsheng/free-vision-skill'
config:
timeout: 120000
Tools
-
view_image— describe image content (scene, people, QR, composition) -
ocr_image— extract text;layout=truefor table structure + coordinates
Input: http(s) URL / base64 / local path.
Paste-to-path (Web UI)
Paste (⌘V) an image in the DSH web input box → its local absolute path is inserted. Loopback-only upload, magic-byte checked: PNG / JPEG / GIF / WebP / HEIC / HEIF.
Usage (Claude Code Skill)
swift scripts/ocr.swift image.png # OCR
swift scripts/ocr.swift --layout image.png # table + coordinates
swift scripts/ocr.swift --describe image.png # describe image
Notes
- Requires macOS 11+ & Xcode Command Line Tools
- First run compiles ~5–10s, cached afterwards
License
MIT © 2026 Nico
Frequently Asked QuestionsFAQ
Use the verified command dsh plugin --profile default add github:niyongsheng/free-vision-skill in a DSH-enabled shell. The command resolves the public package metadata and keeps the plugin attached to the catalog identity shown on this page.
Compatibility follows the bundle and profile status shown above. If a profile is not detected, keep the plugin disabled there and check the repository documentation before enabling it in production.
The GitHub link and activity metadata are the source of truth for releases and maintenance. Revisit this page after a new release to confirm the catalog has observed the latest version.