dsh-len-assistant
Run the following command in DeepSeek Harness:
dsh plugin install qing-1-1/dsh-len-assistant
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install qing-1-1/dsh-len-assistant in your DeepSeek Harness terminal; the source code is hosted at https://github.com/qing-1-1/dsh-len-assistant . Restart dsh web and refresh the page after installation to activate the plugin.
About this plugin
When you ask an agent how much battery life is left, you usually get a wall of mAh figures, cycle counts, and a terse try restarting. dsh-len-assistant packages the hardware-diagnosis, parts-recommendation, warranty-check, and service-locator capabilities refined by Lenovo service teams into an installable plugin for DeepSeek Harness, so agents ground their conclusions in documented rules rather than free-associating from raw numbers.
Two capability groups do the heavy lifting. The battery suite collects capacity and cycle metrics, computes dual-method health scores, renders an SVG decay trend chart, generates the system-level official report, and triggers service recommendations based on findings; a built-in rulebook ensures users who installed only the plugin still receive the interpretation standard. The Windows device suite covers performance, process, storage, and app queries; Wi-Fi status with 5-to-60-second jitter monitoring; redacted SVG and self-contained HTML reports; and every controlled action such as opening Settings or copying a diagnostic summary requires explicit per-instance user confirmation.
It suits agent developers building device-health diagnostics on DeepSeek Harness or Claude Code, as well as teams that want a battery checkup or Wi-Fi jitter triage step in their workflow. It does not replace OS-native tools; it fills the two gaps most often missing at the conversation layer: an interpretation standard and a service-closure loop.
Use Cases
- A user asks how long the battery will last and the agent delivers a rule-based structured diagnosis
- Troubleshooting intermittent Wi-Fi drops with jitter monitoring and an auto-generated redacted report
- First-touch device checkup producing capacity, cycle count, and an SVG decay trend in one flow
Best For
- Developers building device-health agents on DeepSeek Harness
- Teams that need battery checkup or network triage steps in their workflow
- Product owners who want to offer a conversational hardware-diagnosis experience to end users
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.