dsh-run2skill
Run2Skill 把你在 DeepSeek Harness(DSH)里教给 Agent 的纠正、约束和工作流,整理成可复用的 Skill。
Turn explicit DSH session experience into reviewable native Skills
3187 个插件 · 第 54 页,共 133 页
按 npm 发布时间倒序
Run2Skill 把你在 DeepSeek Harness(DSH)里教给 Agent 的纠正、约束和工作流,整理成可复用的 Skill。
Turn explicit DSH session experience into reviewable native Skills
在 DeepSeek Harness 对话中选取一段范围,分享成带品牌标识的 PNG 长图,范围标记可拖动并磁吸对齐。
Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.
一个基于 Leonxlnx/taste-skill 的 DeepSeek Harness 插件,用于添加具备上下文感知能力的前端设计指导。
A DeepSeek Harness plugin that adds context-aware frontend design guidance based on Leonxlnx/taste-skill.
直接从 DeepSeek Harness 搜索、运行并构建 Apify Actors。
Search, run, and build Apify Actors directly from DeepSeek Harness.
Cordis 插件包,通过 Model Context Protocol 将 DeepSeek Harness (DSH) 连接到持久化的 OKF 记忆库。
Cordis bundle that connects DeepSeek Harness (DSH) to a persistent OKF memory vault over the Model Context Protocol.
Cordis 插件包,可为 DeepSeek Harness(DSH)自动捕获会话记忆:它监视会话,并在检查点(空闲、git commit、压缩和会话结束)将对话记录整理进 OKF 库。
Cordis bundle that auto-captures session memory for DeepSeek Harness (DSH): it watches sessions and digests transcripts into an OKF vault at checkpoints — idle, git commit, compaction, and session end.
让 DeepSeek Harness agent 实时控制你的 ComfyUI 画布(本地或云端):作为分屏标签嵌入,直接在聊天里读取/编辑/运行工作流、排查错误、获取输出图片、批量扫描参数。附带 ComfyUI 侧组件
Give DeepSeek Harness agents live control of your ComfyUI canvas (local or cloud): embed it as a split-screen tab, then read/edit/run workflows, debug errors, fetch output images, and batch-sweep parameters straight from the chat. Ships the ComfyUI-side b
为 DeepSeek Harness 网页端提供多供应商账户监测与 Token 用量分析。
Token usage, provider accounts, session cost estimates, budgets, and exports for the dsh web GUI
DeepSeek Harness (DSH) 插件:在设置页提供「模型健康」面板——列出所有已配置模型,并一键批量测试可用性与延迟。
DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.
DeepSeek Harness 会了解你希望如何完成工作:做什么、在什么条件下做、要避免什么,以及如何检查结果。
DeepSeek Harness learns how you want work done: what to do, under which conditions, what to avoid and how to check the result.
用于 DeepSeek Harness(DSH)的独立 Codebase Memory MCP 桥接插件。
Standalone Codebase Memory MCP bridge plugin for DeepSeek Harness (DSH).
一个为 DeepSeek Harness Web UI 添加专注与休息循环的番茄钟插件。
A Pomodoro plugin that adds focus and break cycles to the DeepSeek Harness Web UI.
由于自定义 TUI 引擎无法支持高级视觉效果或完整的 Markdown 与 Mermaid 集成,未来版本将引入 chafa、mmdc 和 mdcat 等依赖项以增强视觉体验。
As the custom TUI engine cannot support advanced visual effects or full Markdown and Mermaid integration, future versions will incorporate dependencies such as chafa, mmdc, and mdcat to enhance the visual experience.
每个插件终于能自我说明——中文名称、通俗描述、一键启用/禁用,以及为 DeepSeek Harness 提供的界面内备注编辑。
Every plugin finally speaks for itself — Chinese names, plain-language descriptions, one-click enable/disable, and in-UI notes editing for DeepSeek Harness.
一个 DSH(DeepSeek Harness)数据洞察技能插件:将原始数据转化为“业务结论 + 指标 + 图表”的结构化 Markdown 分析报告。
A DSH (DeepSeek Harness) data-insight skill plugin: turns raw data into a structured Markdown analysis report of "business conclusions + metrics + charts".
DeepSeek Harness 的增强版 ACP 服务器:块级流式输出、用量与统计遥测(缓存命中率、token 速度、输入/输出 token、上下文长度、轮次、工具耗时)、模型与推理强度切换,以及通过 ACP 控制权限预设
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wi
在 DeepSeek Harness 中导入、编辑和使用 SillyTavern 预设,并为不同模式、不同会话管理工具开关。
SillyTavern prompt presets, macros and editor for DeepSeek Harness
面向 DeepSeek Harness 的 RAG 式技能路由插件:嵌入技能(其名称 + 描述 + whenToUse 路由面),嵌入每个用户任务,通过基于差距的选择规则仅保留明确相关的技能,并自动注入…
RAG-style skill routing plugin for DeepSeek Harness: embeds skills (their name + description + whenToUse routing surface), embeds each user task, keeps only the clearly-relevant skills with a gap-based selection rule, and auto-injects…
AutoCode 是面向竞赛编程出题人的 AI 出题工作台,支持 Claude Code、Codex 和 DeepSeek Harness (DSH)。
DeepSeek Harness plugin for verified competitive-programming problem-setting workflows.
一个 DeepSeek Harness (dsh) 插件,用于向发往 OpenAI 兼容 LLM 网关(llama.cpp、SGLang、vLLM)的每个 chat-completions 请求注入按模型区分的采样参数。
A DeepSeek Harness (dsh) plugin that injects per-model sampling parameters into every chat-completions request sent to an OpenAI-compatible LLM gateway (llama.cpp, SGLang, vLLM).
DeepSeek Harness 的原生 macOS 控制默认不干扰你的真实光标和前台应用;Bundle 可能会在键盘输入前将目标应用带到前台,以确保输入可靠。
Native macOS control for DeepSeek Harness that keeps your real cursor and foreground application alone by default; the Bundle may bring the target app forward before keyboard input for reliable typing.
更强大的视觉工具包——为 DeepSeek Harness 中的纯文本模型赋予视觉能力:图像问答、长截图 OCR、UI 还原和 GUI 视觉任务,集于一个工具包和 Skill 中。
A more powerful vision toolkit—give text-only models in DeepSeek Harness eyes: image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks in one toolkit and Skill.
面向 DeepSeek Harness 的以消息为锚点的项目文件恢复,并可选从恢复后的请求重新开始。
Message-anchored project-file recovery for DeepSeek Harness, with an option to restart from the restored request.
暖光、暖暗、系统感知。
Warm Light, Warm Dark, System-Aware.