dsh-swapcase
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-swapcase
Paste the following prompt into your AI chat to install this plugin:
Install it in DeepSeek Harness by running dsh plugin install uckkk/dsh-swapcase; the full source is available at https://github.com/uckkk/dsh-swapcase.
About this plugin
Model-inference pipelines occasionally need a quick case-swap on a snippet of text—flipping upper to lower, lower to upper, or toggling every character. dsh-swapcase exists to handle exactly that, so you never have to spin up a separate script or hit an external service for such a small transformation.
Built as a pure Node.js plugin with zero external dependencies and no network calls, it registers a swapcase tool into your DeepSeek session the moment you install it. The model invokes the tool when needed; the input text is case-swapped and returned instantly, all locally.
If your inference workflow routinely includes data cleaning, prompt-template preprocessing, or format normalization, dsh-swapcase keeps that step lightweight—no extra tooling, no context switch—so the conversation flows smoothly from one turn to the next.
Use Cases
- Flipping case on variable fields during inference
- Normalizing user input before feeding it to the model
- Toggling case style quickly while debugging prompt templates
Best For
- Inference developers needing lightweight text transformation
- Teams that prefer zero-dependency, fully local tooling
- Engineers processing text inline within DeepSeek sessions
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.