GenUI for DeepSeek Harness: interactive UI components rendered inline in assistant replies via the dsh-ui fence — layout, charts, plots, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model. Ships the fence-teaching host plugin, the browser renderer (client half), and the genui skill.
Turn DeepSeek Harness into a phone app you can securely reach from anywhere: minimal mobile UI rework + pairing-code gateway + PWA + Web Push. 让 DSH 变成可公网安全访问的手机 App
This plugin is used for custom persona configuration. It facilitates users in code development and customized‑role setup, and supports flexible persona adjustments for each conversation.
Dead-code detection for AI-generated codebases: graphlint builds a dependency graph, finds code unreachable from any entry point to enable codebase cleanup and functional‑effectiveness understanding.
DeepSeek Harness (dsh) plugin: registers a global skill that teaches agents how to discover, evaluate and install community plugins from the GitHub dsh-plugin topic, dshmarket and npm. | DSH 社区插件生态指南 skill:让 agent 学会发现、评估、安装社区插件。
pollyreach-dsh-plugin is a phone communication plugin built for DeepSeek Harness (dsh). Powered by the Cordis plugin system, it gives DeepSeek AI agents a dedicated phone number and the ability to make outbound calls, receive incoming calls, retrieve call results, check balances, and customize AI answering behavior.
DSH teacher plugin: Socratic tutor that leads you to answers from a markdown question set, tracks knowledge gaps in-session, and retests them on a spaced-repetition schedule.
Command history for the DeepSeek Harness (DSH) web GUI composer — press ↑ / ↓ to cycle through your previously sent instructions, then restore the draft you were editing when you reach the end of the history.
Per-conversation skill catalog picker for DeepSeek Harness (dsh) — choose which skills are loaded into each conversation. Unselected skills are unavailable in that conversation.
A self-evolving plugin for DeepSeek Harness (dsh). It observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.