Embedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.
Cross-session core memory for the DeepSeek Harness — workspace-scoped persistent facts (ctx.memoryCore) with a stable system-prompt section (KV-cache safe) and a memory_remember tool.
Memory and knowledge · Skills · Agent collaboration · Productivity
Hybrid memory search for the DeepSeek Harness — sqlite-vec vector arm + FTS5 lexical arm (RRF fusion) over session events, with local bge embeddings via transformers.js. Provides ctx.memorySearch.
Memory and knowledge · Skills · Agent collaboration · Productivity
Model-facing memory_search tool for the DeepSeek Harness — hybrid lexical+semantic recall over a session's earlier conversation via ctx.memorySearch, with bounded snippets.
Memory and knowledge · Skills · Agent collaboration · Productivity
DeepSeek Harness plugin that bundles the ppt-maker skill and the PPT tool surface: create, inspect, edit, undo and redo a PPTD v3 project that exports to a locally generated .pptx.
Skills
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:OMSociety/dsh-ppt-maker
The research plugin market inside DeepSeek Harness: browse a curated index of literature, reference, writing and workbench plugins in Settings and install them with one click — 科研插件市场,在设置里浏览并一键安装。
Skills
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dsh-research/dsh-research
CJK-aware ctx.sessionQuery backend for the DeepSeek Harness — SQLite FTS5 provider with a trigram tokenizer table so Chinese full-text search actually matches (upstream unicode61 does not segment CJK), plus a LIKE fallback for 1-2 character CJK queries.
Memory and knowledge · Skills · Agent collaboration · Productivity
Tool-result dedup policy for the DeepSeek Harness — replaces byte-identical repeated plain-text tool results with a pointer to the first occurrence (hash-indexed), saving input tokens on long sessions.
Memory and knowledge · Skills · Agent collaboration · Productivity
AI-for-Science research workflow skill bundle for DeepSeek Harness: multi-angle literature review with per-angle files, anchored experiment design with a caveat list, figures, paper reading; cross-verification briefs.
Desktop host process for dsh-desktopify: boots the desktop profile and serves it through an in-process, portless webServer over byte pipes — upstream apps/desktop-host with the web carrier taken over and the Office skill mount removed.
Expands a referenced skill (`skill:name`) into an injected <skill_content> instructions message and a referenced `@path` into a read-shaped file content block at the pre-step boundary.
Audio: WAV/AIFF/FLAC as a waveform - one row per channel, an adaptive ruler, a min/max envelope with the RMS core, zoom down to samples, selection, and playback on the audio clock - plus the Audio console for this machine's devices. Client-only, read in 2 MiB windows.
Browser: the pack's own web surface, which fetches and renders a page on the HOST in a disposable sandboxed engine behind an egress gate instead of framing it remotely - three tools and three routes. Currently disabled by dsh-vn-master's `browser` row; re-enabling it is deleting those two lines.
Generate and display images inline in the DSH chat via API channels or local CLIs (mmx / codex / agy), and read images into structured JSON evidence (OCR / layout / semantics) on any model — with backend probing and a bundled recovery skill.
Skills · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:corrinehu/dsh-chat-imagine
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.