dsh-subagent-profile
DeepSeek Harness 子 Agent 派发插件:按任务为子代理选模型、推理强度与工具范围,常用组合存成命名方案随时复用;内置安全检查、成本估算与节省分析、完整决策台账。
544 results
DeepSeek Harness 子 Agent 派发插件:按任务为子代理选模型、推理强度与工具范围,常用组合存成命名方案随时复用;内置安全检查、成本估算与节省分析、完整决策台账。
Multi-agent collaboration suite for DeepSeek Harness: a user-configured specialist roster with on-demand dispatch (team_call / roundtable), model comparison, and a multimodal vision bridge — models come from the official provider flow, no bundled adapters.
DSH 社区插件生态指南 + 两个审计工具:注册「dsh-community-plugins」skill,让每个会话都知道如何发现、评估、安装社区插件;注册离线工具 dsh_plugin_audit,把已装插件的 bundle 层完整性、peer 区间、官方包的具名导出、slot 契约与服务注入逐条比对到本机 dsh 构建;注册联网工具 dsh_plugin_inspect,在安装前下载 tarball、校验 integrity、在临时目录里审计后删除,不安装、不执行 lifecycle 脚本。只提供方法与事实,不推荐任何第三方插件或市场。轻量:纯 JavaScript、单一依赖、无构建步骤。
DeepSeek Harness 中文汉化插件:在运行时把所有系统提示词、工具描述、运行时上下文与前端 UI 文本翻译成中文(system-prompt/assemble 瀑布钩子 + client 端 locale.lookup / commands.list patch,不修改任何源码)。
Claude Code-style @path imports for DSH: expands @imports in AGENTS.md/CLAUDE.md and injects the referenced files into model context at session start
Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model over its native wire protocol (OpenAI / Anthropic / Gemini) via the pi-ai SDK
Persistent web file explorer: lazy directory tree, search/filter (Ctrl+F), preview + inline editing (Markdown render, syntax highlight, line numbers, virtualized large files), IDE-style context menu (new/rename/copy/paste/delete-to-trash/paths), drag-and-drop move, dock/float panel, workspace follow.
Spec-driven development loop for DeepSeek Harness: a /spec command family drives propose → approve → implement → verify → archive with OpenSpec-compatible change directories, a durable session projection, and a change card in the composer dock.
Add no-key hosted or OpenAI-compatible vision to DeepSeek Harness while keeping the configured reasoning model
MCP 服务器管理面板:GUI 增删改 MCP 服务器配置(写入 profile cordis.patch.yml 的 mcp-client insert 行,配置 HMR 实时挂载)+ 工具浏览 + agent 面 mcp_* 管理工具。连接生命周期委托官方 @deepseek-ai/dsh-mcp-client。
DSH diff tool: structured comparison of text/JSON/CSV/Markdown plus unified diff generation and in-memory patch validation. Zero-dependency, read-only.
Figma/SVG to Lottie animation compiler for DeepSeek Harness. Turn SVG paths and keyframe data into self-contained .lottie.json files.
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
DeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool
DeepSeek Harness 全能插件:识别/生图/改图一体化,无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型(gemini_vision / gemini_generate_image / gemini_optimize_image)。多后端:Gemini 原生 + 任意 OpenAI 兼容服务(GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转等),生成后自动视觉自检反馈,优于 modlens。
Global model request headers plus image input, reasoning, and DeepSeek system-role compatibility for custom providers
DSH plugin: image understanding via any OpenAI-compatible vision API, paste-to-describe, and an animated whale-buddy desktop pet with status bubbles and a floating settings panel
Discovery + management wrappers around the gh CLI for AI coding agents. Ships as a standard agent skill, an Agent Plugins 1.0 plugin (plugin.json + skills/), and a dsh plugin (dsh.bundle.patch registers the skill at runtime).
Session environment selector for DeepSeek Harness: per-language conda / standalone R / WSL / custom-path slots behind a /env command, the session_env tool, DSH_ENV_* shell facts, and a conversation-header dropdown. Installs with dsh plugin add.
Out-of-tree DSH plugin collection (compatibility fixes and enhancements)
通用 DSH 插件库(pnpm monorepo):模板插件、插件开发工具包、一键聚合安装包。根包同时是全家桶 bundle(dsh.bundle.patch),DSH 与插件市场可直接识别安装。
A DeepSeek Harness (dsh) plugin: orchestrates complex tasks across multiple models — a 'main brain' decomposes the task and dispatches subtasks to GLM / Kimi / Qwen etc. sub-agents by each model's strengths, with per-model token usage.
Model Capability Manager for DSH Web: per-model thinking levels, context window, output caps, input modalities, gateway compat, route defaults, one-click presets, EN/中文 UI.
Learning assistant extension for DeepSeek Harness (dsh): DeepTutor tutoring for your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving (HTTP/WS first, CLI fallback; auto-adapts local/remote deployment).