Token导航 LogoToken导航

Agent Skill · 研究检索

plugin-creator(插件创建者)

plugin-creator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

plugin-creator 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 68,166。

总安装 235周安装 10GitHub Stars 16下载 82核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:plugin-creator(插件创建者)
来源仓库:https://github.com/krzysztofsurdy/code-virtuoso
仓库路径:skills/plugin-creator
安装命令:
npx skills add https://github.com/krzysztofsurdy/code-virtuoso --skill plugin-creator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/krzysztofsurdy/code-virtuoso --skill plugin-creator

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

plugin-creator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于插件创建相关的研究检索任务。通过 npx skills add 命令从 GitHub 仓库安装并使用该技能。

安装前需确认权限范围和维护状态,注意是否涉及联网或文件操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/plugin-creator

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/krzysztofsurdy/code-virtuoso --skill plugin-cr…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

plugin-creator 怎么安装?

在终端执行 npx skills add https://github.com/krzysztofsurdy/code-virtuoso --skill plugin-creator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

plugin-creator 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

plugin-creator 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

plugin-creator 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

plugin-creator 用的人多吗?

公开数据是累计安装 235 次,近一周安装 10 次,下载 82 次,GitHub 16 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

plugin-creator 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
plugin-creator

插件创建者 · 本页

23516调用外部服务未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Plugin Creator

Scaffold a well-formed Claude Code plugin with exactly the components the user wants -- no more, no less. A plugin is a self-contained directory with a manifest (.claude-plugin/plugin.json) plus any of: skills, agents, hooks, MCP servers, LSP servers, bin executables, output styles, default settings. This tool generates the correct structure, writes a valid manifest, adds a marketplace entry when requested, and explains how to test locally with --plugin-dir.

Core Principles

PrincipleMeaning
Manifest is optional, but recommendedIf omitted, the directory name becomes the plugin name and components auto-discover at default locations. Provide one whenever metadata, versioning, or custom paths matter.
Default locations firstPrefer skills/, agents/, hooks/hooks.json, .mcp.json, .lsp.json at plugin root. Only override paths in plugin.json when there is a real reason.
Components live at the root, not in .claude-plugin/Only plugin.json belongs inside .claude-plugin/. Everything else (skills/, agents/, etc.) is at the plugin root. This is the single most common mistake.
Use ${CLAUDE_PLUGIN_ROOT} for every plugin-internal pathAbsolute paths break when the plugin is cached. ${CLAUDE_PLUGIN_ROOT} resolves to the installed plugin directory at runtime. Use ${CLAUDE_PLUGIN_DATA} for state that must survive updates.
Namespacing is automaticPlugin skills are always invoked as /plugin-name:skill-name. Names are derived from the name field in plugin.json (or directory name if no manifest).
Semantic versioning in one placeSet version in plugin.json OR in the marketplace entry -- not both. When present in both, plugin.json wins.

Workflow

This skill uses guided phases -- each phase is a separate file loaded one at a time. Every phase ends with a gate where you must wait for user confirmation before proceeding. Do not skip phases or merge them.

If the user aborts at any phase, discard progress and exit without writing a partial plugin.

PhaseFileWhat it covers
1Plugin IdentityName, description, version, author, optional metadata
2Component SelectionWhich component types to include (skills, agents, hooks, etc.)
3Component DetailsPer-component sub-questionnaires (skills, agents, hooks, MCP, LSP, bin, styles, settings)
4DistributionStandalone, new marketplace, or add to existing marketplace
5Write FilesValidate, confirm, write all files to disk
6Test InstructionsTest commands, reload, validation, next steps

Start by loading Phase 1. After the user confirms each phase, load the next. Never load multiple phases at once. Never skip a phase.


Rules & Guardrails

  • Never put components inside .claude-plugin/. Only plugin.json lives there.
  • Never use absolute paths in plugin.json, hooks, or MCP configs. All plugin-internal paths must start with ./ or use ${CLAUDE_PLUGIN_ROOT}.
  • Never reference files outside the plugin directory via ../ -- the plugin cache will not copy them. Symlinks are preserved, so use those if cross-plugin sharing is truly needed.
  • Never set hooks, mcpServers, or permissionMode on a plugin-shipped agent -- these are blocked for security.
  • Never set both version in plugin.json and in the marketplace entry. Pick one authoritative location.
  • Always bump the version when the plugin content changes. The Claude Code cache uses the version to decide whether to update. Forgetting this is why users do not see plugin updates.
  • Reject reserved marketplace names (claude-code-marketplace, anthropic-marketplace, etc. -- full list in references/marketplace-manifest.md).
  • Validate JSON before writing. A corrupt plugin.json breaks the plugin silently in some cases and loudly in others -- both waste the user's time.

Quick Reference: Minimal Plugin

The smallest valid plugin is a directory with one SKILL.md:

my-plugin/
└── skills/
    └── hello/
        └── SKILL.md

No plugin.json is required -- the directory name becomes the plugin name. Add a manifest only when you need metadata, versioning, or custom paths.


Reference Files

ReferenceContents
plugin-manifest.mdComplete plugin.json schema: required + metadata + component path fields, userConfig, channels, path behavior rules, ${CLAUDE_PLUGIN_ROOT} and ${CLAUDE_PLUGIN_DATA} usage.
marketplace-manifest.mdComplete marketplace.json schema: owner, plugins array, all source types (relative, github, url, git-subdir, npm), strict mode, reserved names.
component-templates.mdReady-to-use templates for plugin.json, SKILL.md, agent files, hooks/hooks.json, .mcp.json, .lsp.json, settings.json, bin/ scripts, and output styles.
distribution.mdHosting options (git hosts, local, URL, npm), semantic versioning, release workflow, auto-update behavior, team marketplace configuration via extraKnownMarketplaces.

Integration with Other Skills

SituationRecommended Skill
Creating the actual skill content inside a pluginskill-creator
Writing the agent body for a plugin-shipped agentCheck existing agent definitions in agents/ for patterns
Generating rules files to pair with a pluginagentic-rules-writer
Writing tickets for plugin-related backlog itemsticket-writer

平台分布

Codex

37.83%
按下载量换算31

Claude

28.76%
按下载量换算24

Cursor

20.72%
按下载量换算17

Gemini CLI

10.34%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills