DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
62 个项目，匹配「omp」
ming-14
Give your AI agent a real terminal: persistent PTY sessions, prompt-triggered returns, screen snapshots, and TUI/GUI/crash awareness.
rootkiller6788
An agent-native compilation & verification pipeline that converts software capabilities such as CLI, APIs, and local services into installable, testable, verifiable DeepSeek Harness plugins.
rrrrrredy
Require fresh, file-bound verification evidence before coding agents declare completion.
wuwuzhige-sudo
A manual Terminal tab for the DeepSeek Harness (dsh) web UI — run commands on the host machine, persistent cwd, sudo password prompt, command history.现在可以在web界面内直接执行命令行了
BrambleXu
Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration. DeepSeek Harness 可复用 Markdown Prompt Profile，支持单轮模型选择、参数替换和状态恢复。
DBinK
Send Your IDE Selection to Any Agent.
GuoCheng24
Make your research agent hard to fool — the discipline layer for agentic research: breakthrough loop, hard-to-fool harness checklist, claim-polarity gates, engineering rules with their tuition
Qidianyan
DeepSeek Harness 扩展开发脚手架：dshdev CLI（agent preset / 插件 bundle / MCP 一键生成与校验）+ Claude Code 中文导航 Skill。Complements official tutorials, no restating.
chang416
Vision + smart model routing for DeepSeek Harness. Gemini sees. DeepSeek codes.
lewes2
Agent skill: generate beautiful dark-themed architecture diagrams from your project/demo/idea. Interactive, verifiable, and editable. Delivered as self-contained HTML.
ChenneyZhuang
Bilingual (EN/CN) agent skills: email deliverability audit, competitor recon, resume localization CN→EN, delivery checklist — battle-tested domain workflows as open SKILL.md files.
MkaliezZ
Long-running development-server lifecycle primitives for DSH; blocks compound shell usage.
ffseika0304
Java 版代码所有权体检：判定 Java 代码是原创还是演绎作品。纯本地 JavaParser AST 分析，依赖烤进 audit.jar，零装包、不联网、不调模型。
houyongsheng
The coding agent that grows its own tools. It reflects after each task, writes a reusable tool, tests it, and keeps it in a skill library that compounds.