xby-ocr
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-ocr
Paste the following prompt into your AI chat to install this plugin:
Install the xby-ocr plugin in DeepSeek Harness by running dsh plugin install xby-skill/xby-ocr (source: https://github.com/xby-skill/xby-ocr).
About this plugin
Turning text hidden in documents, store signage, or screenshot captures into usable content should be a one-step job. xby-ocr is a DeepSeek Harness OCR plugin that takes an image containing text, automatically detects the regions, and transcribes the content — no need to bounce between separate tools or manual annotation.
The plugin balances speed with accuracy and supports three convenient input formats: a file URL, a Base64-encoded string, or a local file path. Whichever way the image is stored, it can be handed straight to the model. The API key is set once in chat and persists across restarts, so there is no re-authentication ritual every session.
It is built for DeepSeek Harness users who routinely pull text out of images: professionals extracting clauses from contract scans, product managers organizing competitor UI screenshots, or developers processing on-site signage photos. If the image has text, xby-ocr turns it into clean, editable, searchable copy.
Use Cases
- Extract key fields from contract or receipt screenshots quickly
- Recognize text on store signage or on-site indicators
- Convert table or paragraph text from UI screenshots into editable copy
Best For
- Office and admin staff who regularly pull text from images
- Product and operations teams organizing competitor UI or product screenshots
- Developers and automation engineers processing on-site photos or signage images
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.