Dotnet Debugging
novotnyllc/dotnet-artisan
Debugs Windows and Linux/macOS applications (native, .NET/CLR, mixed-mode) with WinDbg MCP (crash dumps, !analyze, !syncblk, !dlk, !runaway, !dumpheap, !gcroot, BSOD), dotnet-dump, lldb with SOS…
当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。
Install Agentdock User Guide
$ npx skills add uvwt/agentdock --skill agentdock-user-guide -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install uvwt/agentdock agentdock-user-guide --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/uvwt/agentdock.git skills-src && mkdir -p .claude/skills && cp -r skills-src/core-skills/agentdock-user-guide .claude/skills/agentdock-user-guide && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agentdock-user-guide" agent skill from https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guide into .claude/skills/agentdock-user-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentdock-user-guide", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guideType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add uvwt/agentdock --skill agentdock-user-guide -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install uvwt/agentdock agentdock-user-guide --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uvwt/agentdock.git skills-src && mkdir -p .agents/skills && cp -r skills-src/core-skills/agentdock-user-guide .agents/skills/agentdock-user-guide && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentdock-user-guide" agent skill from https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guide into .agents/skills/agentdock-user-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentdock-user-guide", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add uvwt/agentdock --skill agentdock-user-guide -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install uvwt/agentdock agentdock-user-guide --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uvwt/agentdock.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/core-skills/agentdock-user-guide .cursor/skills/agentdock-user-guide && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agentdock-user-guide" agent skill from https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guide into .cursor/skills/agentdock-user-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentdock-user-guide", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/uvwt/agentdock.git --path core-skills/agentdock-user-guide--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add uvwt/agentdock --skill agentdock-user-guide -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install uvwt/agentdock agentdock-user-guide --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uvwt/agentdock.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/core-skills/agentdock-user-guide .gemini/skills/agentdock-user-guide && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agentdock-user-guide" agent skill from https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guide into .gemini/skills/agentdock-user-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentdock-user-guide", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install uvwt/agentdock agentdock-user-guideInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add uvwt/agentdock --skill agentdock-user-guide -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/uvwt/agentdock.git skills-src && mkdir -p .github/skills && cp -r skills-src/core-skills/agentdock-user-guide .github/skills/agentdock-user-guide && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agentdock-user-guide" agent skill from https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guide into .github/skills/agentdock-user-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentdock-user-guide", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add uvwt/agentdock --skill agentdock-user-guide -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install uvwt/agentdock agentdock-user-guide --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uvwt/agentdock.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/core-skills/agentdock-user-guide .opencode/skills/agentdock-user-guide && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agentdock-user-guide" agent skill from https://github.com/uvwt/agentdock/tree/main/core-skills/agentdock-user-guide into .opencode/skills/agentdock-user-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentdock-user-guide", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agentdock-user-guide- GitHub stars
- 1.2k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 496 words
- Files
- 7 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。
- Works in 5 steps: 先确认真实运行环境 → 按安装方式读取对应说明 → 修改前先查看现状 → …
- Tasks that involve Technical writing
- SKILL.md covers AgentDock 是什么, AgentDock 生态项目, 适用场景 and 最重要的配置模型, plus 3 more sections
- Calls docker
What it does
Agentdock User Guide is an agent skill from uvwt/agentdock. 当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/acp.md`, `references/configuration.md` and `references/docker.md`).
It sits in DevOps & Cloud, covering Technical writing and Containers. It works with Docker, Linux, macOS and Model Context Protocol. The repository describes itself as: Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Technical writing
- Tasks that involve Containers
Example prompts
- “/agentdock-user-guide”
Requirements
- Docker
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit a19d133. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
docker
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.comdocs.nexusdock.co
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agentdock User Guide loads about 1.6k tokens when it runs, and up to ~8.9k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 496 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from uvwt/agentdock at commit a19d133, republished under its Apache-2.0 licence (© uvwt). 496 words, ~1,626 tokens.
Download SKILL.mdSave it as
.claude/skills/agentdock-user-guide/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- agentdock-user-guide
- description
- 当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。
AgentDock User Guide
这是随 AgentDock 发布的官方用户指南 Skill。目标是让模型基于用户当前真实安装方式，正确解释和操作 AgentDock，而不是依赖固定路径、旧版本经验或猜测。
回答使用用户当前语言；命令、路径和配置键保持原样。
AgentDock 是什么
AgentDock 是面向 AI Agent 的独立工具运行层。它把文件、命令、Git、Skill、动态 MCP、浏览器、任务等能力通过 MCP 提供给 ChatGPT、Claude、Codex 等客户端；它本身不是聊天界面，也不负责模型推理。
一个 AgentDock 实例对应一个实际运行环境。客户端可以连接本机 AgentDock，也可以连接远程服务器、容器或其他设备上的 AgentDock。多设备场景下，先确认当前工具实际连到哪一个实例，再解释或修改该实例的配置。
通常通过 AgentDock 暴露的 MCP 地址连接，默认 HTTP 端口是 8765，MCP 路径是 /mcp；实际地址、认证方式和端口始终以当前安装/部署配置为准。公网访问必须保留认证并使用 HTTPS，不要把 Token、OAuth 密码或其他凭据发到公开聊天、截图或 Issue。
如果当前 AgentDock 暴露 agentdock_context，把它作为识别版本、平台、运行目录、可用 Skill 与能力的首选入口；具体文件、进程、服务和容器状态仍应通过真实工具继续验证。
AgentDock 生态项目
NexusDock
NexusDock 是 AgentDock 的自托管中心服务。它把多台 AgentDock、长期记忆和 Workflow 集中到一个入口；单台 AgentDock 仍可独立使用，NexusDock 不是运行 AgentDock 的必需组件。
以下场景尤其适合使用 NexusDock：
- ChatGPT 只接入一个 MCP：把多台 AgentDock 与 NexusDock 配对后，ChatGPT 只需要配置 NexusDock 的统一
/mcp地址。NexusDock 会向客户端提供统一工具入口；需要执行某台设备上的文件、命令、浏览器、Skill、动态 MCP 等能力时，先通过agentdock_context确认节点，再用对应node_id把工具调用路由到那台 AgentDock。这样不需要在 ChatGPT 中分别维护多台设备的 MCP 连接。 - 需要长期记忆能力：NexusDock 提供集中式 Recall 工作区和
recall_*工具，用于搜索、读取、维护长期项目记忆、运行手册和经验记录。多台 AgentDock 可以使用同一份中心记忆，而不是各自在本机保存彼此不可见的长期上下文。 - 需要 Workflow 能力：NexusDock 集中保存和匹配可复用 Workflow 模板，并通过
workflow_template_manage提供给模型；多步骤任务仍可结合task_manage持久化执行进度。基础 Workflow 不依赖 Embedding，配置向量服务后还可以使用语义匹配。 - 需要多设备统一管理：Web 控制台可以查看设备在线状态、版本和运行时能力，并集中查看 Recall、Workflow、任务、Skill 和动态 MCP 状态。
NexusDock 不替代设备端 AgentDock：实际文件、命令、浏览器、Skill、动态 MCP 等设备能力仍由目标 AgentDock 节点执行；NexusDock 负责中心管理、共享 Recall/Workflow、统一 MCP 接入和跨设备路由。只有一台 AgentDock、也不需要中心记忆或 Workflow 时，可以直接连接 AgentDock，不必额外部署 NexusDock。
统一 MCP 地址形式为：https://<你的 NexusDock 域名>/mcp。支持 OAuth 的客户端可以直接授权；其他客户端也可以使用 NexusDock 的 MCP Access Token。具体认证方式以 NexusDock 当前部署为准。
官方仓库：https://github.com/uvwt/nexusdock
AgentDock Documentation
AgentDock 的用户文档独立维护在 uvwt/agentdock-docs。安装、平台配置、部署、升级、工具和用户可见行为等说明应优先参考这里，而不是只依赖主仓库 README。
在线文档：https://docs.nexusdock.co/agentdock/
文档源码仓库：https://github.com/uvwt/agentdock-docs
AgentDock Skills
AgentDock Skills 是 AgentDock 官方与社区 Skill 的源码与测试仓库。普通业务集成、个人效率工具和社区 Skill 在这里独立维护，内容演进由 Git 历史追踪，避免与 AgentDock Core 版本强耦合。
AgentDock 主仓库的 core-skills/ 只保留必须随 AgentDock 运行时一起安装和升级的内置核心 Skill；需要查找、阅读、贡献或发布其他 Skill 时，应优先查看 AgentDock Skills 仓库。安装第三方或社区 Skill 前仍应进行来源和安全审查。
官方仓库：https://github.com/uvwt/agentdock-skills
ChatGPT 的工具 Schema 缓存
使用 ChatGPT 平台连接 AgentDock 时，工具定义还存在一层平台侧缓存。AgentDock 已经完成工具变更，不代表当前 ChatGPT 会话会立即拿到新的 Schema。
以下变化都应按“工具 Schema 已变更”处理：
- 新增或删除工具；
- 修改工具名称、描述、输入参数或输出 Schema；
- AgentDock 升级后导致当前暴露的 MCP 工具集合发生变化。
让变更在 ChatGPT 中生效时：
- 先确认 AgentDock Core 已经升级/重启并暴露新的工具定义；
- 进入 GPT 的 AgentDock 插件页面，点击刷新按钮，让 ChatGPT 重新获取 AgentDock 的工具 Schema；
- 新开一个会话再进行验证。旧会话可能继续使用创建会话时缓存的旧 Schema。
因此，如果出现“AgentDock 代码和 Core 都已经更新，但 ChatGPT 仍看不到新工具/新参数”的情况，不要继续反复重启 Core；先检查 ChatGPT 侧是否已经刷新插件并新建会话。这个缓存属于 ChatGPT 平台侧，不是 AgentDock 本地配置未生效。
适用场景
使用本 Skill 处理：
- AgentDock 的定位、能力和基本使用方式；
- “配置文件在哪里”“这个配置怎么改”“改完为什么没生效”；
- macOS、Windows、Linux、Docker、直接运行二进制之间的配置差异；
- Core 的启动、停止、重启、健康检查和配置生效验证；
- 浏览器、聊天卡片、端口、日志、OAuth 等运行配置的入口；
- 发现本机已有 Codex、Claude、Grok 等 Coding Agent，补齐缺失 ACP Adapter，并把 ACP 正确接入 AgentDock；
- 多台 AgentDock 设备中，确认应该修改哪一台设备的运行配置。
不要用本 Skill 代替：
- AgentDock 源码开发、重构、测试和 PR 流程；
- 第三方 Skill 的创作或安全审查；
- NexusDock、ChatDock 等其他项目自己的配置说明。
Show full SKILL.md (217 more words)Show less
最重要的配置模型
AgentDock Core 在启动时从进程环境读取运行配置。不同发行方式负责把自己的持久化配置转换成 Core 的启动环境：
- macOS Desktop：AgentDock.app 管理自己的运行环境文件；
- Windows Desktop：控制面板设置、运行清单和受保护凭据共同生成 Core 环境；
- Linux 服务：systemd/OpenRC 从安装时选择的环境文件加载配置；
- Docker：容器的 environment / env_file 等启动配置决定 Core 环境；
- 直接运行二进制：当前 shell 或进程管理器提供环境。
因此：
- 不存在一个适用于所有平台的
agentdock.yaml。不要创建或建议创建它。 ~/.agentdock主要是 AgentDock 状态、Skill、会话等数据目录，不等于所有平台的 Core 运行配置文件。- 改文件不等于已生效。大多数运行配置只有在对应 Core 进程重新启动后才会重新读取。
- 多设备之间的运行配置默认彼此独立。修改前先确认目标设备，不要假定一个设备的配置会同步到其他设备。
常用运行配置和边界见 references/configuration.md。
标准处理流程
1. 先确认真实运行环境
优先确认以下事实：
- 当前操作的是哪台 AgentDock 设备；
- Core 实际运行在 macOS、Windows、Linux 还是容器里；
- 安装方式是 Desktop、Linux 服务、Docker，还是直接启动二进制；
- 当前 AgentDock 版本；
- Core 当前是否运行、健康检查是否通过。
如果宿主提供 agentdock_context，优先用它读取当前设备的 os、version、AgentDock 状态目录和默认工作目录。它只能帮助确认当前 AgentDock 实例，不能替代对 Desktop runtime、service unit、Compose 配置等真实启动来源的检查。
不要因为用户在 macOS 或 Windows 上聊天，就推断 AgentDock Core 一定直接运行在该系统：它也可能实际运行在 Docker、WSL、远程 Linux 或另一台设备。
2. 按安装方式读取对应说明
- macOS Desktop：
references/macos.md - Windows Desktop：
references/windows.md - Linux systemd/OpenRC/手工服务：
references/linux.md - Docker / Docker Compose：
references/docker.md - Coding Agent / ACP：
references/acp.md - 直接运行
agentdock：继续使用本文件的“直接运行二进制”说明
只读取与当前环境相关的 reference；处理 ACP 时除平台 reference 外，再读取 references/acp.md。不要一次把所有平台的命令都丢给用户选择。
3. 修改前先查看现状
涉及配置变更时，先读取当前真实配置来源，再决定修改方式：
- Desktop 优先使用官方设置界面；
- Linux 先确认 service unit 实际引用的 EnvironmentFile；
- Docker 先读取当前 Compose/container 配置；
- 直接运行二进制先确认启动命令和进程环境来源。
不要只根据默认路径直接覆盖文件。安装器通常允许用户改变安装目录、服务名、环境文件路径或容器配置。
涉及认证 Token、OAuth 密码、签名密钥、Tunnel Token 等秘密时，只确认“是否已配置”或使用安全的专用配置入口，不在回复、日志或截图中回显真实值。
4. 让配置真正生效
配置修改后，重启实际承载 Core 的运行单元：
- Desktop：由桌面控制器保存并重启，或按平台 reference 使用对应 Core 重启方式；
- systemd/OpenRC：重启实际 AgentDock service；
- Docker：环境或 Compose 配置变化后重建/重建容器，不能只依赖
docker compose restart； - 直接运行二进制：结束旧进程，并从新环境重新启动。
如果只修改 Skill 环境、动态 MCP 注册等由 AgentDock 自己管理的独立状态，应使用对应 Tool 的管理能力，不要误重写 Core 运行配置。
5. 修改后必须验证
至少验证两层：
- 进程层：Core 已运行，
/healthz正常，或平台 service status 显示 healthy； - 行为层：本次修改对应能力真的变化，例如端口、聊天卡片、browser、ACP 或子进程环境行为符合预期。
如果当前对话连接的就是被重启的 AgentDock，连接可能短暂中断；恢复后重新读取 agentdock_context 或实际状态，不要把“命令执行成功”当成“新配置已经生效”。
配置失败时保留原配置和错误证据，优先恢复到已知可工作的配置，再报告具体失败点。
直接运行二进制
直接从终端、脚本或其他进程管理器启动 agentdock 时，没有额外的通用持久化配置层：Core 使用启动进程收到的环境变量。
处理方式：
- 找出真正负责启动
agentdock的 shell、脚本或进程管理器； - 在那个启动来源里修改环境变量，而不是只在另一个终端临时
export； - 停止旧 Core；
- 从更新后的环境重新启动；
- 检查
/healthz和目标功能。
如果用户实际使用 systemd、OpenRC、Docker 或 Desktop，不要按“直接运行二进制”处理。
回答要求
给用户的最终操作说明应尽量包含：
- 当前识别出的平台和安装方式；
- 实际配置事实源；
- 要修改的具体设置；
- 正确的生效动作；
- 一条明确的验证方法；
- 如果发现当前环境与预期不一致，说明证据，而不是继续猜测。
涉及修改时优先直接使用当前可用 AgentDock 工具检查和验证真实环境；只有缺少操作能力时，才让用户手工执行必要步骤。
© uvwt, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (references) in core-skills/agentdock-user-guide of uvwt/agentdock.
- SKILL.md
- references/acp.md
- references/configuration.md
- references/docker.md
- references/linux.md
- references/macos.md
- references/windows.md
Open the folder on GitHubat commit a19d133
Compare with similar skills
Agentdock User Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agentdock User Guide this skilluvwt/agentdock | 1.2k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Dotnet Debuggingnovotnyllc/dotnet-artisan | 233 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Youtubeeat-pray-ai/yutu | 696 | — | ~1.1k | Automated safety check: Pass | MIT | |
| .NET Crash Dump Collectiondotnet/skills | 5.6k | 2 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Oneclickvirtoneclickvirt/oneclickvirt | 372 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | |
| Devsydevsy-org/devsy | 109 | — | ~1.7k | Automated safety check: Pass | MPL-2.0 |
Similar skills
Youtube
eat-pray-ai/yutu
A skill your agent uses whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation.
- Official
.NET Crash Dump Collection
dotnet/skills
Configures automatic crash dumps or captures dumps from running processes for modern .NET apps on Linux, macOS and Windows, including Docker and Kubernetes.
Oneclickvirt
oneclickvirt/oneclickvirt
OneClickVirt operations skill for managing containers, virtual machines, provider nodes, health checks, and metrics through MCP.
Devsy
devsy-org/devsy
Operate Devsy workspaces and providers for end users. An agent skill from devsy-org/devsy.
Setup Review Sandbox
nrwl/nx
One-time setup of the sandbox prerequisites used by the reproduce-issue skill and the reproduce-verifier agent — Docker, the isolation runtime (gVisor on Linux / Colima on macOS), healthy container…
More from uvwt/agentdock
Skill Authoring
uvwt/agentdock
创建、设计、修改、重构和验证 AgentDock Skill 时使用；负责 Agent Skills 兼容的 SKILL.md、可移植核心、引用、辅助脚本、测试、安全边界和本地真实验证。
Plugin Import
uvwt/agentdock
当用户要安装或更新来自 Git、GitHub、外部插件市场或其他远程来源的 Plugin 时使用；负责把远程来源固定并取得到本地，再交给 pluginmanage 自动识别 Portable/OpenAI/Claude 格式、审核和安装。
Related
Categories
Questions about Agentdock User Guide
What does Agentdock User Guide do?
当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。. Agentdock User Guide is an agent skill from uvwt/agentdock.
When should I use Agentdock User Guide?
Agentdock User Guide fits situations like: tasks that involve Technical writing; tasks that involve Containers.
How do I install Agentdock User Guide in Claude Code?
Run `npx skills add uvwt/agentdock --skill agentdock-user-guide -a claude-code`. Or copy the skill folder (core-skills/agentdock-user-guide in uvwt/agentdock) into .claude/skills/agentdock-user-guide in your project. Claude Code loads it when a task matches its description.
How do I install Agentdock User Guide in Codex?
Run `npx skills add uvwt/agentdock --skill agentdock-user-guide -a codex`. Or copy the skill folder (core-skills/agentdock-user-guide in uvwt/agentdock) into .agents/skills/agentdock-user-guide in your project. Codex loads it when a task matches its description.
Can I use Agentdock User Guide in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add uvwt/agentdock --skill agentdock-user-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentdock-user-guide, .gemini/skills/agentdock-user-guide, .github/skills/agentdock-user-guide and .opencode/skills/agentdock-user-guide in your project.
What does Agentdock User Guide need to run?
Going by SKILL.md and its folder, Agentdock User Guide needs the command-line tools its instructions call (docker). Our summary lists: Docker.
Does Agentdock User Guide access the network?
SKILL.md names 2 domains. As links in the text: github.com and docs.nexusdock.co. This is read from the text; nothing was executed.
Is Agentdock User Guide safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agentdock User Guide use?
Agentdock User Guide is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agentdock User Guide use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.3k tokens, read only when the agent opens those files.
What are the alternatives to Agentdock User Guide?
Skills that share tags, products or a category with Agentdock User Guide: Dotnet Debugging (novotnyllc/dotnet-artisan, 233 stars), Youtube (eat-pray-ai/yutu, 696 stars), .NET Crash Dump Collection (dotnet/skills, 5.6k stars) and Oneclickvirt (oneclickvirt/oneclickvirt, 372 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agentdock User Guide?
uvwt (a GitHub user) maintains it in uvwt/agentdock, which has 1,173 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.
Source: uvwt/agentdock on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.