dsh-capitalize
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-capitalize
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-capitalize in the DeepSeek Harness terminal to install the plugin (full source: https://github.com/uckkk/dsh-capitalize); no extra setup required.
About this plugin
When working through DSH sessions, a missing capital letter at the start of a sentence is a small but visible blemish—awkward in English summaries, code comments, or polished prompts. dsh-capitalize turns that fix into a single tool call: once installed, it registers a built-in utility in the session, and invoking it capitalizes the first letter without any extra configuration.
The plugin is written entirely in Node.js with zero network dependencies. It never reaches out to an external service, so it slots neatly into intranet, offline, or compliance-sensitive inference setups without adding attack surface or latency. The logic is intentionally minimal—ready the moment the session starts, and out of the way the instant it finishes.
If you regularly generate English text, draft prompts, or format code annotations through DSH and would rather not hand-correct casing after every run, this plugin is built for that moment. It does not alter model behavior; it simply applies one clean, predictable normalization step at the text layer so the output looks polished before it leaves the session.
Use Cases
- Fix lowercase first letters in model-generated English summaries without leaving the session
- Run text normalization inside an air-gapped or intranet inference pipeline
- Batch-clean prompts or code comments to a consistent capitalized format
Best For
- Developers generating English content through DSH sessions
- Inference-platform operators bound by offline or compliance requirements
- Prompt engineers who want one-click text normalization inside the session
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.