跳到正文
cccskills
免费在 GitHub 公开中文介绍

plugin

管理将技能、智能体、规则、MCP服务器和钩子打包在一起的插件。可查看已安装插件、启用、停用或卸载插件,也可将相关自定义配置整理成新插件。

原文查看原文说明

How to manage and create plugins — namespaced bundles of skills, agents, rules, MCP servers and hooks that install, enable and disable as a single unit. Use this skill when the user wants to enable, disable, install or uninstall a plugin, when they want to create a new plugin, or when a new customization should be packaged into a plugin rather than left loose. Also triggered by the /plugin slash command. Don't use for the underlying customization system itself — discovery roots, loading priority, or authoring a standalone skill, agent, rule, hook or MCP server outside a plugin; see the customizations guide skill for those.

asgeirtj/system_prompts_leaks星标 70,416(GitHub 70,416 + cccskills 0)

实测评分 未实测

查看安装方法

适用场景

  • 从Marketplace安装插件
  • 停用或卸载插件
  • 归并相关技能和规则
  • 为自定义配置创建插件

中文介绍

功能

管理由技能、智能体、规则、MCP服务器和钩子组成的插件。可以查看已安装的插件、启用或停用插件、卸载符合条件的插件,也可以创建插件来归并相关自定义配置。添加新功能时,此技能可协助判断应将其加入现有插件还是新建插件,并准备所需的配置文件和子目录。

适用场景

想从Marketplace安装插件、停止或删除不再使用的插件,或者按共同用途整理分散的技能和规则时,可以使用此技能。插件中的内容会作为一个整体启用或停用,因此适合将相关功能一起切换。

使用示例

  • “请安装Marketplace中的这个插件。”
  • “请停用我不再使用的插件。”
  • “请把这个技能和规则放进同一个插件。”

注意事项

管理插件需要连接Antigravity语言服务器。从Marketplace安装需要Marketplace ID;安装插件或创建插件后需要重启。内置插件不能卸载,应通过停用来处理。

本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。

文档检查

AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。

安全性发送数据、删除文件、执行命令等是否有说明
A良好资料要求确认目标,禁止删除内置插件,并说明停用插件的删除前处理。
安装难易度所需工具和 API 密钥是否少且有说明
B部分不足依赖Antigravity语言服务器、环境变量、curl和jq。

不计入评分。 由 AI(OpenAI Codex)于 2026年10月30日 评估。仅供参考,安装前请同时查看原文。

如果您认为评估有误,请申请复核

请写明哪一项有误以及原因。无需登录。我们会对照 SKILL.md 重新评估,并在此处更新结果。

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

包含的文件(1)

  • SKILL.md17.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Plugins

A plugin is a namespaced bundle of customizations that ships, installs, and turns on as one unit. It can contain skills, agents, rules, MCP servers and hooks. When a plugin is on, everything inside it is active; disabling it takes the whole bundle down at once.

Your job is either to change a plugin's lifecycle state or to get new functionality into the right plugin. Step 0 and Step 1 are common to both; Step 1 routes you to Step 2A or Step 2B.

For the underlying customization system — discovery roots, loading priority, what each customization type is for — see the customizations guide skill. This skill does not restate that material.

Quick Start

After writing /tmp/lsrpc.sh in Step 0, prefix every lsrpc call with source /tmp/lsrpc.sh && and key every mutation on <dir> (the install directory name (.path | split("/") | last) from Step 0, never plugin.json's
name):

<!-- mdformat off -->
OperationCommand / ActionKey Guardrail
Inventory installed plugins (Step 0)source /tmp/lsrpc.sh && lsrpc GetAllPlugins '{"workspaceUris":["file:///path/to/workspace"]}' | jq '[.plugins[] | {name, dir: (.path | split("/") | last), disabled: (.disabled // false), isGlobal, skills: [.skills[]?.name], agents: [.agents[]?.name], rules: [.rules[]?.absolutePath], hooks: ((.hooksJson // "") | length > 0), mcp: [.mcpServers[]?.name]}]'Never read GetAllPlugins unfiltered (inlines full SKILL.md text); always pipe through jq and use dir for mutations ('{}' if no workspace is active).
Enable / Disable plugin (Step 2A)source /tmp/lsrpc.sh && lsrpc JetboxWriteState '{"userConfig":{"plugins":{"<dir>":{"enabled":true}}}}' (false to disable)Takes effect live (no restart). Never hand-edit ~/.gemini/config/config.json.
Uninstall user plugin (Step 2A)source /tmp/lsrpc.sh && lsrpc DeletePlugin '{"pluginId":"<dir>"}'Refuse if .path contains /builtin/plugins/ (offer to disable instead). If currently disabled, set "enabled":true via JetboxWriteState before deleting.
Install Marketplace plugin (Step 2A)source /tmp/lsrpc.sh && lsrpc InstallCustomization '{"id":"<marketplace-id>"}'Use <marketplace-id> from the Customizations page or user (never guess from name; only Marketplace plugins can be installed). Requires a restart.
Author / consolidate plugin (Steps 2B–4)Create ~/.gemini/config/plugins/<name>/plugin.json (or in source repo if published) + used subdirectories (skills/, agents/, rules/AGENTS.md, mcp_config.json, hooks.json, assets/logo.svg)Check Step 0 inventory for name collisions first; re-run Step 0 inventory, tell the user to restart, and link as [<name>](customization://<dir>) (never plugin://).
<!-- mdformat on -->

Step 0: Preflight and inventory

Every path needs to know what is already installed. Talk to the language server over its local Connect endpoint. The address and CSRF token are normally already in your shell environment; you do not need to hunt for a port file.

: "${ANTIGRAVITY_LS_ADDRESS:=localhost:5387}"
curl -sS "http://${ANTIGRAVITY_LS_ADDRESS}/healthz"

Write the helper to a file once, then source it in every call below. Each command you run is a fresh shell, so a function defined in one call is gone by the next; sourcing a file is what makes it reusable.

cat > /tmp/lsrpc.sh <<'EOF'
: "${ANTIGRAVITY_LS_ADDRESS:=localhost:5387}"
lsrpc() {  # usage: lsrpc <MethodName> <json-body>
  curl -sS -X POST \
    "http://${ANTIGRAVITY_LS_ADDRESS}/exa.language_server_pb.LanguageServerService/$1" \
    -H "Content-Type: application/json" \
    -H "x-codeium-csrf-token: ${ANTIGRAVITY_CSRF_TOKEN}" \
    -d "$2"
}
EOF

Now list the installed plugins, passing active workspace URIs in workspaceUris so workspace-scoped plugins are discovered (or '{}' when no workspace is active). Prefix every lsrpc snippet in this skill with
source /tmp/lsrpc.sh &&:

source /tmp/lsrpc.sh && lsrpc GetAllPlugins '{"workspaceUris":["file:///path/to/workspace"]}' | jq '[.plugins[] | {
  name,
  dir: (.path | split("/") | last),
  disabled: (.disabled // false),
  isGlobal,
  skills: [.skills[]?.name],
  agents: [.agents[]?.name],
  rules: [.rules[]?.absolutePath],
  hooks: ((.hooksJson // "") | length > 0),
  mcp: [.mcpServers[]?.name]
}]'

Never read GetAllPlugins unfiltered. The response inlines the full
text
of every bundled SKILL.md. A single plugin can exceed 16KB and a
populated config will flood your context. Always pipe it through jq.

dir is the identifier that matters. It is the install directory name — the last path segment — and it is what every mutation below is keyed on. It is frequently not the same as name from plugin.json: a plugin installed from the Marketplace lands in a directory named after a signed 64-bit hash, so a plugin displayed as data-tools may live in a directory called -1870732469773246571. Using name where dir is expected fails silently or builds a garbage path.

Step 1: Decide the kind

  • The user names an existing plugin and a lifecycle verb — "turn off X", "install Y", "get rid of Z" -> Step 2A.
  • The user wants new capability, or wants existing loose customizations tidied up — "I want a Strava thing", "package these skills together" -> Step 2B.

Step 2A: Lifecycle operations

Resolve the target to its dir from the Step 0 inventory first. If the user's words match several plugins, ask which one rather than guessing.

Enable or disable. This is the same write the Customizations page performs, and it takes effect live — no restart.

# Enable:
source /tmp/lsrpc.sh && lsrpc JetboxWriteState '{"userConfig":{"plugins":{"<dir>":{"enabled":true}}}}'

# Disable:
source /tmp/lsrpc.sh && lsrpc JetboxWriteState '{"userConfig":{"plugins":{"<dir>":{"enabled":false}}}}'

The write deep-merges, so send only the one plugin. Never hand-edit ~/.gemini/config/config.json to do this: writes that bypass the language server miss the live reload and are only picked up by a slow backstop poll.

Uninstall.

source /tmp/lsrpc.sh && lsrpc DeletePlugin '{"pluginId":"<dir>"}'

Check both of these before you run it:

  • Built-in plugins cannot be uninstalled. A plugin whose path contains /builtin/plugins/ ships with the product. Refuse, and offer to disable it instead.
  • Uninstall leaves the enablement entry behind. Nothing clears plugins.<dir> from config.json. If the plugin was disabled and is later reinstalled into the same directory name, it comes back disabled for no visible reason. Before deleting a disabled plugin, set it back to enabled so the stale entry is harmless, and tell the user you did.

Install. For a plugin published to the Agent Marketplace:

source /tmp/lsrpc.sh && lsrpc InstallCustomization '{"id":"<marketplace-id>"}'

You cannot derive this ID from the plugin's name. Take it from the Marketplace tab of the Customizations page, or ask the user for it. If all you have is a name, say so rather than guessing an ID.

A source not found error means one of two things: the ID is wrong, or the Marketplace catalog isn't launched for this user. The catalog case has a tell — the ID comes back empty, so the message reads source for customization not found with nothing between the words. Re-check the ID first.

Only install plugins that have a Marketplace entry. If the plugin has none, or the catalog isn't launched for this user, do not try to install it another way; tell the user it isn't available to install.

A newly installed plugin directory is only discovered on startup. Tell the user to restart before expecting its skills to appear.

Lifecycle operations end here. Skip Step 3, which covers authoring only, and go to Step 4.

Step 2B: Decide where the functionality belongs

A plugin is a bundle, so the first question is never "what do I build" but "where does it go". Take the inventory from Step 0 and see whether the request fits an existing plugin. Plugins tend to cohere around one of three shapes:

  • A data provider or external service. Everything that talks to one system — Strava, GitHub, a particular API. Its MCP server, the skill that drives it, and the rules about its quirks belong together.
  • An artifact or file type. Spreadsheet handling, proto editing, log analysis. Grouped by what the user is operating on.
  • A role or recurring job. Data analysis, running a small business, reviewing documents, writing code. Broader, and the right home when a capability spans several providers in service of one repeated task.

Recommend and proceed. State in one line which plugin you picked and why, then keep going. Use ask_question only when two existing plugins are genuinely close, or when nothing fits and the boundary for a new one is unclear. Do not stall on a decision the user can trivially reverse.

If nothing fits, create a new plugin at ~/.gemini/config/plugins/<name>/. Before settling on a name, check it against the Step 0 inventory: names share one global namespace, and when two plugins claim the same name the first discovered wins and the other is dropped silently.

If the plugin is meant to be shared or published, create it in the source repository it will be published from instead of the user's config directory.

Consolidating loose customizations

When the user asks to tidy up standalone customizations, move the directories: a skill at ~/.gemini/config/skills/foo/ becomes ~/.gemini/config/plugins/<name>/skills/foo/, and a rule becomes rules/AGENTS.md inside the plugin.

MCP servers need a warning first. Moving an entry out of the user's mcp_config.json and into the plugin's own mcp_config.json ties its lifecycle to the plugin: it is assembled only while the plugin is enabled, so disabling the plugin stops its tools being offered along with everything else in the bundle. Control moves with it too, since the server is no longer an entry in the user's own config and is managed through the plugin rather than on its own. Tell the user this before you move the entry.

Step 3: Author the bundle

Create only the subdirectories the plugin actually uses:

~/.gemini/config/plugins/<name>/
├── plugin.json       # required
├── README.md         # user-facing docs; never read by the agent
├── mcp_config.json   # optional, same format as the user's own
├── hooks.json        # optional
├── assets/logo.svg   # optional
├── skills/<skill>/SKILL.md
├── agents/<agent>.md
└── rules/AGENTS.md

Write the inner customizations yourself — the SKILL.md, the agent markdown, the rules, the MCP config. Do not hand that back to the user as a follow-up. Rules in a plugin's rules/AGENTS.md are plain markdown with no frontmatter and are always on while the plugin is enabled.

plugin.json is parsed as JSONC, so comments and trailing commas are allowed:

{
  "name": "strava",
  "description": "Strava integration: pull activity data, summarize training load, and draft workout notes.",
  "logo": "assets/logo.svg",
  "suggestedPrompts": [
    "Summarize this week's workout mileage and heart rate zones",
    "Compare pacing and cadence across my last 4 long runs",
    "Draft an annotated Strava description for my latest activity"
  ]
}
FieldTypeNotes
namestringThe label users see, and the global unique
: : : key — two plugins sharing a name collide :
: : : and one is dropped. Not the install :
: : : identifier; that is the directory. Lowercase :
: : : kebab-case. Defaults to the directory name :
: : : if omitted. :
descriptionstringOne or two sentences saying what the plugin
: : : does and who it is for. This is what :
: : : Marketplace search matches. :
logostringOptional. A path relative to the plugin
: : : directory, such as assets/logo.svg, ending :
: : : in .png, .svg, .jpg, .jpeg or :
: : : .webp. URLs and absolute paths are :
: : : rejected silently — a bad value renders no :
: : : logo rather than erroring. :
suggestedPromptsstring[]Optional. Up to 3 starter prompts for card
: : : and detail views. Exactly 3 prompts are :
: : : recommended for UI card layouts. Empty :
: : : strings are skipped and additional prompts :
: : : beyond 3 are ignored. :
displayNamestringOptional. Human-readable presentation title
: : : shown in UI headers, cards, and slash :
: : : command menus. :
versionstringOptional. Semantic version string.
authorstring /Optional. Developer or team name string, or
: : object : an object with name and optional url :
: : : (https://). :
homepagestringOptional. External https:// website or
: : : documentation URL. :
repositorystring /Optional. Source repository https:// URL
: : object : (or {"type": "git", "url": "https://..."}). :
disabledbooleanOptional. Ships the plugin turned off. A
: : : choice the user has already made wins over :
: : : this field. :

Do not add any other top-level field. Unknown top-level fields are
silently discarded by the loader — they neither take effect nor error out.

Offer to generate a logo with the generate_image tool. Ask for a square asset of at least 128x128 with a transparent background, high contrast so it reads on both themes, and roughly 10% empty margin baked in — the frame adds no padding of its own and center-crops anything non-square.

Step 4: Verify and hand back

Re-run the Step 0 inventory and confirm the plugin appears with the components you expect. Then tell the user:

  • What changed, and which plugin now owns it.
  • Whether a restart is required. Creating or installing a new plugin directory needs one; enabling, disabling and uninstalling do not.
  • Where to manage it, as a link: [<name>](customization://<dir>) opens the plugin's own page, which lists what it provides and can turn it on and off.

<dir> is the install directory from Step 0, never the manifest name. A plugin directory created in this session is not discovered until a restart, and until then its page reports nothing installed under that id, so give the link and the restart together.

Do not emit plugin:// or plugins:// links; they are not handled and render as dead text.

Constraints & Tips

  • Key every mutation on the install directory name, never plugin.json's name. This is the single most common way to break a plugin operation.
  • Prefer the language server RPCs over editing files. config.json is written atomically at mode 0600 and holds sibling state — userSettings, permission grants. A careless rewrite clobbers them.
  • One coherent purpose per plugin. Bundling unrelated capabilities forces the user into an all-or-nothing toggle. If a request does not fit the plugin's description, that is the signal to create a new one.
  • MCP server names are global too. They collide across the user's config and every installed plugin, so prefix a plugin's servers with the plugin name rather than shipping a generic search or db.
  • Keep description honest and current. It is what the user reads before installing and what search matches. Update it when the bundle's contents change.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

3d-object

免费有简介

使用three.js创建立体模型,在交互式查看器中从各个角度检查形状和材质,并以OBJ + MTL或GLB格式保存,供其他三维制作软件使用。

  • 创建立体模型并从各个角度检查
  • 制作可在Blender中继续编辑的模型
  • 检查模型轮廓和材质效果
asgeirtj/system_prompts_leaks7万2026年10月29日 更新

Audit web accessibility with Chrome DevTools MCP and Lighthouse. Inspect semantic structure, labels, keyboard focus, tap target size, and color contrast, then identify page elements that may need changes based on web.dev guidance.

中文简介正在准备中。当前显示英语简介。

  • Finding missing labels or image alternatives
  • Checking heading structure and reading order
  • Testing keyboard navigation and modal focus
asgeirtj/system_prompts_leaks7万2026年10月29日 更新

action-items

免费有简介

在个人任务清单中记录待办事项、承诺、期限、下一步、待回复对象和阻碍原因,更新进度与依赖关系,合并重复项并归档已结束的任务。

  • 记录有期限的任务与承诺
  • 整理待回复事项及阻碍原因
  • 前置任务完成后更新依赖关系
asgeirtj/system_prompts_leaks7万2026年10月29日 更新

agents

免费

Coordinate a task from a verifiable goal through completion. Handle work directly or split independent tasks across separate agent sessions, track progress, verify results, and arrange pull request merging when included in the goal.

中文简介正在准备中。当前显示英语简介。

  • Split independent tasks across agents
  • Check progress across ongoing tasks
  • Resume a previously started project
asgeirtj/system_prompts_leaks7万2026年10月29日 更新

agy-customizations

免费有简介

了解 Antigravity 如何发现和加载自定义配置,包括配置位置与优先级。借助本指南选择并创建技能、规则、插件、钩子或 MCP 服务器,用于智能体工作流程和外部工具连接。

  • 选择合适的自定义配置类型
  • 查看配置的发现位置和加载顺序
  • 创建技能或规则
asgeirtj/system_prompts_leaks7万2026年10月29日 更新

animated-video

免费有简介

将动画制作成可播放、暂停和定位时间的HTML页面,通过时间轴调整场景时长与速度,并为横屏或竖屏视频导出做好准备。

  • 制作产品操作演示动画
  • 用文字和图形解释内容
  • 制作竖屏动画
asgeirtj/system_prompts_leaks7万2026年10月29日 更新

查看 asgeirtj 的全部技能

报告此技能的问题