xby-ocr-captcha
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-ocr-captcha
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-ocr-captcha in DeepSeek Harness to install; the source code is available at https://github.com/xby-skill/xby-ocr-captcha .
About this plugin
In any automation pipeline, a single captcha image is often the one step that forces a human to step in. xby-ocr-captcha removes that bottleneck. Built as a DeepSeek Harness plugin, it takes a common captcha image and returns the text content directly, so the workflow keeps running without manual intervention.
The plugin supports three input methods to match different setups: a remote image file URL, a Base64-encoded string, or a local file path. Whether your scraper grabbed a URL or your automation saved a screenshot to disk, one call gets you the result. The API key is set via a chat command and persists automatically across restarts.
Ideal for developers working with RPA, data collection, or automated form-filling flows that integrate DeepSeek Harness. Anywhere a captcha-reading step exists, this plugin hands that task to the model and eliminates the need for a human on standby.
Use Cases
- Captcha blocking a scraper or RPA workflow — auto-extract the text and let the pipeline proceed
- Auto-filling forms that require image captcha verification without manual input
- Batch processing captcha screenshots to quickly extract text for downstream validation or entry
Best For
- Developers building data collection or RPA pipelines that frequently encounter captchas
- Integration developers orchestrating agent workflows on DeepSeek Harness
- Ops or QA engineers who need unattended captcha text extraction in production or test environments
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.