Plugin directory / Vision / free-vision-skill
free-vision-skill
Verified · install-tested on dsh niyongsheng
What it does
Local-only vision skill for macOS 本地化识图技能
Works — verified, early-stage project
Local-only vision skill for macOS 本地化识图技能 It installs cleanly and boots without issues in our testing. It's early-stage but functional.
“Verified” means our automated CI actually ran dsh plugin add in a clean profile and it booted — nothing more. Feature descriptions and version compatibility are the author’s claims. This is not a security audit and not an endorsement of third-party code.
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
Install
Install the catalog once, then DeepSeek Harness can find and install any plugin from this site automatically:
dsh plugin add dshbase-catalogThen say "install free-vision-skill for me" — your agent finds it in the directory and installs it. Docs: dshbase-catalog · verified packs.
This plugin is GitHub source (not published to npm) — install it straight from the repo:
Web profile:
dsh plugin --profile web add github:niyongsheng/free-vision-skillHeadless (CLI) profile:
dsh plugin --profile headless add github:niyongsheng/free-vision-skillTest report
Verified: L1 install + L2 load + L3 runtime from GitHub source on dsh 0.1.0-rc.6.
When to use it
Give the model eyes — image understanding, OCR, or screen grounding — so it reads visuals instead of guessing.
Who it's for
Users who hand the model screenshots, diagrams, or photos and want them understood natively.
For developers — extending it
Vision backends and preprocessing are the seams — add OCR, region cropping, or tune resolution and model routing.
Share this badge
Drop this badge into your README — it links back here and updates automatically when our test status changes:
[](https://dshbase.com/plugins/free-vision-skill/)<a href="https://dshbase.com/plugins/free-vision-skill/"><img src="https://dshbase.com/badges/free-vision-skill.svg" alt="dshbase install-tested"></a>