Agent skill

Plugin Creator

by useLexora in useLexora/Lexora

创建、修改并验证可安装的 Lexora 桌面插件,包括工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。

AGPL-3.0Auto-check passedAgent Workflows

Install Plugin Creator

skills CLI
$ npx skills add useLexora/Lexora --skill plugin-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install useLexora/Lexora plugin-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/useLexora/Lexora.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/buddy/service/resources/skills/plugin-creator .claude/skills/plugin-creator && rm -rf skills-src

Use ~/.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/

Facts

Skill name
plugin-creator
GitHub stars
522
Token cost
~1k tokens
SKILL.md length
169 words
Files
11 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
AGPL-3.0

At a glance

创建、修改并验证可安装的 Lexora 桌面插件,包括工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。

  • Works in 6 steps: 读取 协议与清单 和 完整 API 类型。这些文件与当前 Lexora… → 在当前可写工作区创建独立源码目录,例如… → 新建独立插件时通过 lexora_tool_search 查找… → …
  • Tasks that involve Hooks and plugins
  • SKILL.md covers 理解需求, 按需求组合能力, 阅读协议并创作 and 编译与修正, plus 1 more section
  • Runs TypeScript scripts from its folder

What it does

Plugin Creator is an agent skill from useLexora/Lexora. 创建、修改并验证可安装的 Lexora 桌面插件,包括工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `references/agent-settings.md`, `references/api.d.ts` and `references/capabilities.md`).

It sits in Agent Workflows, covering Hooks and plugins and Autonomous loops. It works with Model Context Protocol, Rust and Linux. The repository describes itself as: A self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agent。 The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Hooks and plugins
  • Tasks that involve Autonomous loops

Example prompts

  • “/plugin-creator”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 读取 协议与清单 和 完整 API 类型。这些文件与当前 Lexora 一起分发;不要根据其他产品的插件格式猜测接口。
  2. 在当前可写工作区创建独立源码目录,例如 plugins/<插件名>/。通过文件工具写入真实文件,保留源码以便后续对话修改。不需要用户另外安装 Node、Bun 或 SDK。
  3. 新建独立插件时通过 lexora_tool_search 查找 lexora_plugin_identity,传入按功能选定的简短英文 slug,将返回的 id、author 和 engines 写入…
  4. 按选定组合声明视图、命令、导航和挂载点,明确每项能力由宿主入口还是视图入口调用;限定页面时使用公开上下文和声明条件。仅声明实际需要的权限;没有对应能力时解释限制,不绕过隔离访问宿主…
  5. 使用自包含 TS/JS 和包内资源。复制 references/api.d.ts 为源码目录的 lexora.d.ts,仅通过 import type 引用。源码清单设置 format: "source"。视图导出 render(context…
  6. 事件、定时器、动画在关闭时清理,动画结束回收节点、空闲时停止循环。页面使用主题变量;窗口效果保持透明、不阻挡输入,并尊重减少动态效果偏好。

What it can do on your machine

Read from SKILL.md and the folder at commit da2406a. 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

    Ships script files (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Plugin Creator loads about 1k tokens when it runs, and up to ~21k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 169 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~21k

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 useLexora/Lexora at commit da2406a, republished under its AGPL-3.0 licence (© useLexora). 169 words, ~1,028 tokens.

Download SKILL.mdSave it as .claude/skills/plugin-creator/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
plugin-creator
description
创建、修改并验证可安装的 Lexora 桌面插件,包括工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。

创建 Lexora 插件

将用户的需求变成可安装、可修改的真实插件。完成最小可用版本,再依据编译诊断与用户的实际体验迭代。不要用占位 demo 代替需求。

理解需求

先利用当前对话确定输入、触发时机、呈现位置与生效范围、需要保留的数据和停止方式。描述充分时直接实施;只询问会改变实现的缺失信息。短需求选择轻量默认值并说明,不要求用户先填技术问卷。没有设置需求时优先复用插件管理中的启用、禁用,不额外增加导航和配置页面。

分别确定事件来自哪里、内容画在哪里、何时可见。事件来自某个控件,不意味着内容只能画在该控件内;保留用户指定的窗口、分屏或局部区域,不擅自缩小范围。未指定的视觉细节可以选择默认值;指定范围缺少正式能力时明确说明,不能用相近位置代替交付。

用户提供外部参考时先阅读公开说明或代码,提取需要复现的用户行为,再映射到 Lexora 的正式能力。参考项目的内部接口不能直接移植;读取失败时说明缺少的依据,不把推测写成已经核对的实现。

用户给出的作者署名或调用名不符合规则时,说明具体原因并给出 1–3 个保留原意的可用候选,通过对话请用户确定后继续。不要静默截断、转拼音、替换为系统账号或生成陌生名称;中文作者署名本身合法,无需改成英文。尚未指定调用名时可以按插件功能提出简短名称。

按需求组合能力

读取 能力选择与组合,将需求对应到输入来源、呈现方式、运行入口与状态归属,再确定最小清单。一个插件可以组合多种正式扩展点,也可以只提供命令或一个文件视图;现有示例不是插件类别或必须复制的模板。

查询宿主扩展能力时,通过 lexora_tool_search 查找 lexora_plugin_capabilities。先无参数查询当前宿主的简短目录,再按 kind 或 target 获取所需能力的契约;不要把完整目录提前塞进提示词。内容区的共同规则见 内容插槽。没有匹配位置时说明能力缺口,不借助 CSS 选择器或相近区域模拟替换。

先说明所选组合能完成的用户行为,再创作。文件阅读工具需要按文件打开的独立视图和各自的阅读状态;常驻信息条可能需要底部挂载、宿主查询命令与私有设置。不要因为都“有界面”就统一做导航页,也不要为了演示全部 API 给插件添加无关权限。

阅读协议并创作

继续旧对话创作时,重新读取当前技能与协议。历史消息、旧工具结果和压缩摘要中的命名示例不作为新插件的身份依据;维护已有插件时读取实际源码清单,并保留其中的 ID。

  1. 读取 协议与清单 和 完整 API 类型。这些文件与当前 Lexora 一起分发;不要根据其他产品的插件格式猜测接口。 需要实时配置、表单依赖或运行状态判断时,读取 条件函数,声明数据输入与作用域,不将函数序列化进清单。需要 Agent 指令、后台任务动作、模型调用、任务标题或原生设置时,追加读取 Agent 与设置,并确认当前宿主能力目录支持。事件驱动动作与订阅按 事件与触发列表 选择精确入口和载荷,不把普通事件监听器当作任务能力调用。
  2. 在当前可写工作区创建独立源码目录,例如 plugins/<插件名>/。通过文件工具写入真实文件,保留源码以便后续对话修改。不需要用户另外安装 Node、Bun 或 SDK。
  3. 新建独立插件时通过 lexora_tool_search 查找 lexora_plugin_identity,传入按功能选定的简短英文 slug,将返回的 id、author 和 engines 写入 extension.json。作者未指定时省略参数,使用已保存的默认署名;明确不署名时传空字符串。作者名支持中文,不要求用户提供英文名、平台账号或唯一名称,也不从系统用户名、Git 配置或目录推断署名。不要自行编造 ID 或继续生成 local.*。修改、升级、换电脑维护及分发沿用源码内已有 ID,不重新调用身份生成工具;包括已有的 local.*。只有创建独立副本时生成新 ID 并同步内部引用。
  4. 按选定组合声明视图、命令、导航和挂载点,明确每项能力由宿主入口还是视图入口调用;限定页面时使用公开上下文和声明条件。仅声明实际需要的权限;没有对应能力时解释限制,不绕过隔离访问宿主 DOM、内部接口或文件。明确用户第一次如何启动、关闭后如何再次打开;普通挂载需要显式打开;内容插槽和替换控件的启用、回退与配置归属按 内容插槽 实现。现有入口足够时不额外增加设置页。
  5. 使用自包含 TS/JS 和包内资源。复制 references/api.d.ts 为源码目录的 lexora.d.ts,仅通过 import type 引用。源码清单设置 format: "source"。视图导出 render(context, container),需要命令、存储或调度时再添加宿主入口 activate(context)。
  6. 事件、定时器、动画在关闭时清理,动画结束回收节点、空闲时停止循环。页面使用主题变量;窗口效果保持透明、不阻挡输入,并尊重减少动态效果偏好。

修改作者署名时直接更新清单 author,保留已有 id 和所有贡献引用,无需调用身份生成工具。ID 的前缀不会自动成为署名;用户说“用户名”或“发布者”且含义不明确时,先区分作者署名与更换插件身份。用户明确要求更换 ID 时,先说明它会被当作另一份插件,既有数据不会自动转移。

编译与修正

通过 lexora_tool_search 查找 lexora_plugin_build,然后调用它:

如果当前明确是在独立 Lexora Plugin SDK 仓库中开发、没有 Lexora 内置工具,使用 SDK 工作流。普通 Lexora 对话不需要这条分支。

json
{ "source": "plugins/my-plugin", "output": "my-plugin-1.0.0.lexora-extension", "review": true }

output 是已存在父目录中的新文件,放在源码目录之外;现有文件不会被覆盖。工具使用内置隔离编译器,不执行 npm 安装脚本或插件代码。错误结果包含 code 与有限的 diagnostics:修正对应问题后重新构建,避免重复提交相同错误。需要重新生成包时使用新的输出文件名。

review: true 请求显示安装确认,用户确认后才会安装。只要求源码或打包时设为 false。不要绕过确认或通过内部配置安装。交付前核对构建结果中的 id、name、author 和 version。author 为空表示安装界面会显示未署名;用户要求署名时,修正清单并重新构建,不能把 ID 前缀当作署名已经生效。构建结果中的 installation 只表示是否发起审核,不代表当前安装状态;旧版本返回的 installed: false 也不能用于断言用户尚未安装。

需要判断安装、待应用更新或加载失败时,通过 lexora_tool_search 查找 lexora_plugin_inspect,以插件 id 读取当前宿主状态。比较当前版本与 pendingVersion,检查可见命令、导航入口、视图 ready 和错误。仍待用户审核时交付结果即可,不循环轮询;工具不可用时明确安装状态未核实。ready 只证明入口完成加载,不能代替实际功能验收。

通过 lexora_output_present 交付源码目录与安装包。不要只在回答中粘贴代码,也不要下载 SDK 或建立另一套构建工程。

验证与迭代

按所选能力检查主要动作,以及真正影响它的边界:文件视图验证两份资源的状态互不覆盖;组合面板验证导航切换和设置刷新;控件验证宿主允许值、失败回退与明确重试;后台命令验证关闭页面后仍按约定运行。再验证禁用后的停止行为,避免机械套用某个示例的测试步骤。

有持久设置时,检查修改后的实际行为、离开页面再返回及重启后的恢复;开关需要验证关闭与重新开启,不能只确认表单显示成功提示。

编译通过只证明包可构建,不证明界面和运行效果通过。Lexora 的浏览器工具只能控制资源浏览器,不能操作插件安装弹窗或窗口效果;不要为此创建另一个 HTML 模拟宿主来代替安装验收。有能操作真实插件界面的工具时执行检查;否则交付编译后的包和待验证项,让用户安装后反馈,不在等待安装期间反复调用无关工具。不要编造截图、通知送达、运行成功或性能数据。

交付简短说明:完成了什么、源码与包的位置、如何触发、已检查和仍待体验的行为。用户反馈后读取现有源码,修正实现、重新编译并再次验证相同场景。保持 ID 与数据含义稳定。发布市场或同步远端单独遵循用户指示。

© useLexora, AGPL-3.0. 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 10 other files (references) in apps/buddy/service/resources/skills/plugin-creator of useLexora/Lexora.

  • SKILL.md
  • references/agent-settings.md
  • references/api.d.ts
  • references/capabilities.md
  • references/commands.md
  • references/conditions.md
  • references/events.md
  • references/interactions.md
  • references/protocol.md
  • references/sdk-workflow.md
  • references/slots.md

Open the folder on GitHubat commit da2406a

Compare with similar skills

Plugin Creator 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.

Plugin Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plugin Creator this skilluseLexora/Lexora522—~1kAutomated safety check: PassAGPL-3.0
Creating Zed Extensionspr-pm/prpm122—~3.1kAutomated safety check: NotesMIT
Linux Desktop Controlagent-sh/computer-use-linux661—~2.7kAutomated safety check: PassMIT
Horizon Devicepeters/horizon714—~3.4kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • A skill your agent uses when creating Zed extensions with custom slash commands, language support, themes, or MCP servers - provides Rust/WASM extension structure, slash command API…

    122 GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Linux Desktop Control

    agent-sh/computer-use-linux

    Lets an agent observe and operate a local Linux desktop through the computer-use-linux MCP server or Pi tools: accessibility trees, screenshots, windows and input.

    661 GitHub stars~2.7k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed
  • Horizon Device

    peters/horizon

    Manage Horizon native VNC Device panels and drive isolated local desktops for simulators and native application tests through devicepanel and the horizon-device CLI/MCP.

    714 GitHub stars~3.4k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Lean Ctx Review

    yvgude/lean-ctx

    Review how the lean-ctx ctx MCP tools performed in the current session and file upstream issues for confirmed problems.

    3.9k GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from useLexora/Lexora

  • Lexora Buddy Animation

    useLexora/Lexora

    A skill your agent uses when the user asks Lexora Buddy to move, emote, celebrate, rest, or perform a visible desktop-pet action.

    522 GitHub stars~232 tokensUpdated 7 days ago
    Auto-check passed

Categories

Questions about Plugin Creator

What does Plugin Creator do?

创建、修改并验证可安装的 Lexora 桌面插件,包括工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。. Plugin Creator is an agent skill from useLexora/Lexora.

When should I use Plugin Creator?

Plugin Creator fits situations like: tasks that involve Hooks and plugins; tasks that involve Autonomous loops.

How do I install Plugin Creator in Claude Code?

Run `npx skills add useLexora/Lexora --skill plugin-creator -a claude-code`. Or copy the skill folder (apps/buddy/service/resources/skills/plugin-creator in useLexora/Lexora) into .claude/skills/plugin-creator in your project. Claude Code loads it when a task matches its description.

How do I install Plugin Creator in Codex?

Run `npx skills add useLexora/Lexora --skill plugin-creator -a codex`. Or copy the skill folder (apps/buddy/service/resources/skills/plugin-creator in useLexora/Lexora) into .agents/skills/plugin-creator in your project. Codex loads it when a task matches its description.

Can I use Plugin Creator 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 useLexora/Lexora --skill plugin-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plugin-creator, .gemini/skills/plugin-creator, .github/skills/plugin-creator and .opencode/skills/plugin-creator in your project.

What does Plugin Creator need to run?

Going by SKILL.md and its folder, Plugin Creator needs TypeScript for the scripts in its folder. Our summary lists: Node.js.

Does Plugin Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plugin Creator 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 Plugin Creator use?

Plugin Creator is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plugin Creator use?

About 1k tokens (SKILL.md is roughly 4.1k 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 20k tokens, read only when the agent opens those files.

What are the alternatives to Plugin Creator?

Skills that share tags, products or a category with Plugin Creator: Creating Zed Extensions (pr-pm/prpm, 122 stars), Linux Desktop Control (agent-sh/computer-use-linux, 661 stars), Horizon Device (peters/horizon, 714 stars) and MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plugin Creator?

useLexora (a GitHub organization) maintains it in useLexora/Lexora, which has 522 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 30, 2026.

Source: useLexora/Lexora on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.