Token导航 LogoToken导航

Agent Skill · 研究检索

alova-client-usage(alova 客户端使用)

alova-client-usage 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。

alova-client-usage 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,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 39,473。

总安装 1,409周安装 57GitHub Stars 3下载 442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:alova-client-usage(alova 客户端使用)
来源仓库:https://github.com/alovajs/skills
仓库路径:skills/alova-client-usage
安装命令:
npx skills add https://github.com/alovajs/skills --skill alova-client-usage
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/alovajs/skills --skill alova-client-usage

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。

alova-client-usage 提供 Alova 客户端侧使用的快速参考索引。适合在 Codex、Claude、Cursor、Gemini CLI 中查找 API 用法和选项时使用。分为两层结构:本文件和官方文档,优先查阅本文件再按需获取官方文档。

安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。alova 处于活跃开发中,官方实时文档比训练数据更可靠。

来源仓库内路径:skills/alova-client-usage

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/alovajs/skills --skill alova-client-usage;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

    它需要接触敏感数据,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

alova-client-usage 怎么安装?

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

alova-client-usage 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。

alova-client-usage 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

alova-client-usage 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。

alova-client-usage 用的人多吗?

公开数据是累计安装 1,409 次,近一周安装 57 次,下载 442 次,GitHub 3 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。

alova-client-usage 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
alova-client-usage

alova 客户端使用 · 本页

1,4093接触敏感数据未明确有提醒

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

alova banner

Alova Client-Side Usage

For server-side (Node/Bun/Deno), see alova-server skill. For alova openapi usage, see alova-openapi skill.

How to Use This Skill

This skill is structured in two layers:

  1. This file — Quick-reference index: what each API does and when to use it. Read this first.
  2. Official docs (fetch on demand) — For full options, edge cases, or unfamiliar APIs, fetch the URL listed in each section to get the latest accurate information.
Always fetch the official doc before answering questions about specific API options or behaviors — alova is actively developed and live docs are more reliable than training data.

Installation & Setup

See references/SETUP.md for:

  • Installation
  • Creating Alova instance
  • Framework-specific StatesHook
  • Request adapters
  • Global request sharing and timeout
  • Create interceptor about Token-based login, logout and token refresh
  • cache logger
  • limit number of method snapshots

Create Method Instance

alova provides a total of 7 request types.

Instance creation functionParameters
GETalovaInstance.Get(url[, config])
POSTalovaInstance.Post(url[, data[, config]])
PUTalovaInstance.Put(url[, data[, config]])
DELETEalovaInstance.Delete(url[, data[, config]])
HEADalovaInstance.Head(url[, config])
OPTIONSalovaInstance.Options(url[, config])
PATCHalovaInstance.Patch(url[, data[, config]])

Parameter Description:

  • url is the request path;
  • data is the request body data;
  • config is the request configuration object, which includes configurations such as request headers, params parameters, request behavior parameters, etc.;

In fact, the above functions calling are not sending request, but creates a method instance, which is a PromiseLike instance. You can use then, catch, finally methods or await to send request just like a Promise object.

alovaInstance
  .Get('/api/user')
  .then((response) => {
    // ...
  })
  .catch((error) => {
    // ...
  })
  .finally(() => {
    // ...
  });

// or
try {
  await userMethodInstance;
} catch (error) {
  // ...
} finally {
  // ...
}

See Method Documentation if need to know full method instance API.

Method Metadata

Add additional information to specific method instances to facilitate their identification or additional information in global interceptor such as different response returning, global toast avoiding. please set method metadata. See -> Method Metadata.

Core Hooks

Use these hooks in components instead of hand-rolling common request patterns.

import from alova/client.
HookWhen to useDocs
useRequestFetch on mount, or trigger once on a user action (button click, form submit)Docs
useWatcherRe-fetch automatically when reactive state changes (search input, filter, tab, page)Docs
useFetcherPreload data silently in background, or refresh from outside the component that owns the dataDocs

Business Strategy Hooks

import from alova/client.
ScenarioHookKey capabilityDocs
Paginated list / infinite scrollusePaginationAuto page management, preload next/prev, optimistic insert/remove/replaceDocs
Form submit (any complexity)useFormDraft persistence, multi-step state sharing, auto-resetDocs
Polling / focus / reconnect refreshuseAutoRequestConfigurable triggers, throttleDocs
Sms, email verification code send + countdownuseCaptchaCooldown timer built-inDocs
Cross-component request triggeractionDelegationMiddleware + accessActionNo prop-drilling or global storeDocs
Chained dependent requestsuseSerialRequest / useSerialWatcherEach step receives previous resultDocs
Retry with exponential backoffuseRetriableRequestConfigurable attempts + jitterDocs
File upload with progressuseUploaderConcurrent limit, progress eventsDocs
Server-Sent EventsuseSSEReactive data + readyStateDocs
Seamless data interactionuseSQRequestinteract with UI can be responded immediately without waitingDocs

Cache Strategy

Alova has L1 (memory) and L2 (persistent/restore) layers, plus automatic request sharing (dedup).

Set cache globally and scoped

Key rule: prefer hitSource auto-invalidation — it requires zero imperative code and decouples components.

Hooks Middleware

Middleware allows you to intercept and control request behavior in useHooks. Common scenarios include:

  • Ignoring requests under certain conditions
  • Transforming response data
  • Changing request method or forcing cache bypass
  • Error handling (capture or throw custom errors)
  • Controlling response delays
  • Modifying reactive states (loading, data, etc.)
  • Implementing request retry logic
  • Taking full control of loading state

For full middleware API and examples, see Request Middleware.

Mock Request

Setup mock data for specific requests. See Mock Request.

Best Practices

  • Create multiple alova instances for different domains, APIs, or environments.
  • Provide a folder that uniformly stores request functions, to keep your code organized.
  • prefer using hooks in components, directly call method instance in other places.
  • prefer binding hooks events with chain calling style, like useRequest(method).onSuccess(...).onError(...).

Common Pitfalls

PitfallFix
useWatcher first arg is a Method instanceAlways wrap: () => method(state.value)
updateState silently does nothingOnly works while owning component is mounted; use setCache otherwise
Cache ops called synchronously in v3await invalidateCache / setCache / queryCache
useWatcher doesn't fetch on mountSet immediate: true

TypeScript

Annotate the response shape on the Method instance — hooks infer from it automatically:

const getUser = (id: number) => alovaInstance.Get<User>(`/users/${id}`);
// or need to transform data.
const getUser = (id: number) =>
  alovaInstance.Get(`/users/${id}`, {
    transform(user: User) {
      return {
        ...user,
        name: user.lastName + ' ' + user.firstName,
      };
    },
  });

const { data } = useRequest(getUser(1)); // data: Ref<User>

📄 TypeScript docs

SSR Component Party

alova can manage APIs on both server and client, instead using different request solutions on the server and client sides respectively.

CSR

Generally, alova's hooks only work in client side.

// won't send request in server side.
useRequest(getUser(1));

Nextjs

directly await method instance in server components.

const App = async () => {
  const data = await alovaInstance.Get('/todo/list');
  // then ... code
  return <div>{...}</div>;
};
export default App;

Nuxt

Using await before alova's hooks keep states on both ends in sync, which is the same effect as useFetch.

const { data } = await useRequest(getUser(1));

Sveltekit

directly await method instance in +page.server.[j|ts].

/** @type {import('./$types').PageServerLoad} */
export async function load({ params }) {
  return {
    list: alovaInstance.Get('/todo/list'),
  };
}

Custom Adapter

If all preset adapters not meet your needs, custom your own adapter.

Custom Method Key

Change cache, request sharing and state updating matching strategy by setting key. See Custom Method Key.

平台分布

Codex

36.26%
按下载量换算160

Claude

29.3%
按下载量换算130

Cursor

16.83%
按下载量换算74

Gemini CLI

9.18%
按下载量换算41

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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