dsh-keyword-extract
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-keyword-extract
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-keyword-extract in your terminal to install; the source code is available at https://github.com/uckkk/dsh-keyword-extract
About this plugin
Extracting key terms from a block of text is a common need, but pulling in a heavyweight NLP library or firing off an API call adds complexity you may not want. dsh-keyword-extract keeps things deliberately lightweight: a pure Node.js implementation with zero network dependencies and no extra runtime overhead.
The plugin registers a keyword-extraction tool into your session. You call it with a piece of text, and the extracted keywords are returned directly. Because there are no network requests involved, it works reliably in offline environments, air-gapped machines, and CI pipelines where external calls are either blocked or undesirable.
It is a good fit for developers who want a lightweight text-analysis step inside an agent session, or for engineering teams working in restricted or network-isolated setups who would rather not wire up an external service just to pull out a few keywords. Licensed under MIT, so there is no licensing friction to worry about.
Use Cases
- Quickly pull out core terms from a long user prompt inside an agent session
- Run lightweight text analysis in offline or air-gapped environments without any external API calls
- Add a zero-network keyword-extraction step to a CI pipeline
Best For
- Developers who need a lightweight text-analysis tool inside an agent session
- Engineering teams in restricted or network-isolated environments that prefer no external services
- Engineers who want minimal-dependency keyword extraction without heavyweight NLP libraries
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.