Token导航 LogoToken导航

Agent Skill · 研究检索

surf-paipai-ai(冲浪拍拍艾)

surf-paipai-ai 用于查找、检索和筛选相关信息,适合在 OpenClaw 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。

surf-paipai-ai 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 15,946。

总安装 7,491周安装 306GitHub Stars 公开资料未说明下载 2,399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
MIT-0
版本
1.0.1

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:surf-paipai-ai(冲浪拍拍艾)
来源仓库:https://github.com/allentom/surf-paipai-ai
安装命令:
openclaw skills install surf-paipai-ai
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install surf-paipai-ai

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。

Surf Paipai AI 是与 paip.ai 平台交互的完整技能套件。支持登录注册、资料管理与应用查询操作。适用于 OpenClaw 生态内 paip.ai 用户自动化流程。需绑定 paip.ai 账号并完成 OAuth 授权。建议测试各接口在实际环境中的稳定性。

surf-paipai-ai 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

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 OpenClaw;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 openclaw skills install surf-paipai-ai;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

    它需要需要联网,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

surf-paipai-ai 怎么安装?

在终端执行 openclaw skills install surf-paipai-ai。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

surf-paipai-ai 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

surf-paipai-ai 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

surf-paipai-ai 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

surf-paipai-ai 用的人多吗?

公开数据是累计安装 7,491 次,近一周安装 306 次,下载 2,399 次。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。

surf-paipai-ai 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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 OpenClaw,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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
surf-paipai-ai

冲浪拍拍艾 · 本页

7,491—需要联网MIT-0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

name
paipai-new-skill
description
A complete skill for interacting with the paip.ai (openclaw paip.ai) platform. Supports user login/registration, viewing and updating profile information, querying agents and rooms created by the user, publishing and viewing moments, and more. Use this skill when the user mentions keywords such as paip.ai, Paipai, openclaw, publish a moment, view rooms, agent list, login, or registration.

paipai-new-skill (paip.ai)

A complete operational skill for the paip.ai platform, covering core functions such as authentication, user information, agents, rooms, and moments.

Configuration

BASE_URL = https://gateway.paipai.life/api/v1
TIMEOUT = 300000  # 5-minute timeout (unit: milliseconds)

All endpoints use this address as the prefix. For example: POST https://gateway.paipai.life/api/v1/user/login

Timeout configuration notes:

  • Set the timeout for all API requests to 5 minutes (300 seconds).
  • If no result is returned within 5 minutes, prompt "Request timed out, please try again later".
  • For time-consuming operations such as file uploads, the timeout may be extended appropriately based on the actual situation.

Common Request Headers

Every HTTP request must include the following headers:

Authorization:        Bearer {token}          (obtained after login; may be omitted when not logged in)
X-Response-Language:  zh-cn                   (based on the user's locale, e.g. en-us / ja-jp)
X-DEVICE-ID:          openclaw-{random 8-character alphanumeric string}  (generated once per session and reused throughout the session)
X-User-Location:      {Base64(longitude|latitude|region name)}  (example: MTE2LjQwNjd8MzkuODgyMnzljJfkuqzlpKnlnZs=)
Content-Type:         application/json         (for POST/PUT requests)

X-DEVICE-ID generation example: openclaw-a3f8k2mz X-User-Location format: Base64("116.4067|39.8822|北京市朝阳区") → MTE2LjQwNjd8MzkuODgyMnzljJfkuqzlpKnlnZs= If the location cannot be obtained, use the Base64 encoding of an empty string: ""


1. Authentication Flow (Login / Registration)

Steps

  1. Ask whether the user already has an account:

> "Do you already have a paip.ai account?"

- Has an account → perform Login - Does not have an account → ask whether registration is needed → perform Registration

Login

Ask the user to provide their email address (that is, the username) and password, then call:

POST /user/login
Body: {
  "loginType": 1,
  "username": "{email}",
  "password": "{password}"
}

After success, save the token (used in the Authorization: Bearer {token} header for all subsequent requests), and then immediately perform Display User Information.

Registration

Ask the user to provide an email address and a password (password length requirement: 8-24 characters), then call:

POST /user/register
Body: {
  "username": "{email}",
  "password": "{password}"
}

After successful registration, also save the token, and then immediately perform Display User Information.


2. Display User Information After Login

Call the following endpoint to obtain information about the currently logged-in user:

GET /user/current/user

Display the following key response fields to the user:

FieldDescription
nicknameNickname
usernameEmail account
userNoUser number
avatarAvatar
bioBio
genderGender (1 = male, 2 = female, 3 = unknown)
mbtiMBTI personality type
constellationConstellation
fansCountNumber of followers
followCountNumber of following

3. Profile Management

Update Basic Information

PUT /user/info/update
Body: {
  "nickname": "Nickname (required, 2-32 characters)",
  "bio": "Bio (optional)",
  "gender": 1,              // 1 = male, 2 = female, 3 = unknown (optional)
  "constellation": "Libra", // optional
  "mbti": "INFJ",           // optional
  "avatar": "Avatar path",      // optional; the path must be obtained by uploading first
  "backgroud": "Background image path"  // optional; the path must be obtained by uploading first
}

Change Password

PUT /user/change/password
Body: {
  "oldPassword": "{old password}",
  "newPassword": "{new password, 8-24 characters}",
  "confirmPassword": "{confirm new password}"
}

Upload Avatar (Avatar / Background Image)

First upload the file to obtain the path, and then update the user information:

POST /user/common/upload/file?type=user&path={file path}&id={user ID}

The response is { "path": "xxx" }. Fill this path into the avatar field of the update information endpoint.


4. Query My Content

Query Agents I Created

GET /user/prompt/list?authorId={current user ID}&page=1&size=10

Display: agent name, description, avatar, mode (public/private), and follower count.

Query Rooms I Am In

GET /room/list?creator={current user ID}&page=1&size=10

Display: room name, type (GROUP/PRIVATE), visibility (PUBLIC/PRIVATE), and member count.

Query Moments I Published

GET /content/moment/list?userId={current user ID}&page=1&size=10

Display: moment content (text/attachments), like count, comment count, favorite count, and publish time.


5. Publish a Moment

Trigger Methods

The user can trigger this in either of the following two ways:

Direct instruction:

"I need to publish a moment on paip.ai. The moment content is: xxx"

Question-driven flow (ask proactively when the user's intent is unclear):

1. "What type of moment would you like to publish? (text only / with images or video)" 2. "Please enter the moment content:" 3. "Visibility scope? (PUBLIC = public / FRIEND = friends only / PRIVATE = only me)" 4. "Would you like to add tags?"

Publish Endpoint

POST /content/moment/create
Body: {
  "content": "Moment text content",
  "publicScope": "PUBLIC",     // PUBLIC | FRIEND | PRIVATE
  "isOpenLocation": false,
  "attach": [],                // optional; array of image/video attachments
  "tags": []                   // optional; array of tag strings
}

Attach object format (fill in after upload):

{
  "type": "image",      // image | video | music | posts
  "source": "upload",   // upload | outside | internal
  "address": "file path",
  "sort": 0
}

Upload content files:

POST /content/common/upload?type=content&path={file path}&id={user ID}

6. Other Common Operations

Like a Moment

POST /content/like/
Body: { "type": "moment", "targetId": {moment ID} }

Comment on a Moment

POST /content/comment/
Body: { "type": "moment", "targetId": {moment ID}, "content": "comment content" }

Search Content

GET /content/search/search?keyword={keyword}&type={moment|video|user|prompt|room}&page=1&size=10

Log Out

POST /user/logout

7. Error Handling

Response Code Rules

All API response bodies contain a code field:

  • code === 0: the request succeeded; process the response data normally.
  • code !== 0: the request failed; display the content of the message field in the response body directly to the user.

Response body structure examples:

{ "code": 0, "message": "success", "data": { ... } }
{ "code": 10001, "message": "This email has already been registered", "data": null }

Timeout Configuration Implementation

All curl requests must set timeout parameters:

# Set a 5-minute timeout (300 seconds)
curl --max-time 300 --connect-timeout 300 [other parameters]

# Example: login request
curl --max-time 300 --connect-timeout 300 -X POST "https://gateway.paipai.life/api/v1/user/login" \
  -H "Content-Type: application/json" \
  -d '{"loginType": 1, "username": "user@example.com", "password": "password123"}'

Timeout handling logic:

  1. Set a 5-minute (300-second) timeout for all requests.
  2. If the request times out, return: "Request timed out, please try again later".
  3. For large-file operations such as file uploads, consider extending the timeout appropriately.
  4. After a timeout, logs should be recorded to facilitate troubleshooting.

HTTP Status Code Handling

ScenarioHandling
401 UnauthorizedPrompt the user to log in again and clear the old token
400 Bad RequestDisplay the message in the response to the user
Network timeoutPrompt "Request timed out, please try again later" (5-minute timeout)
code !== 0Display message directly to the user

References

平台分布

OpenClaw

96.92%
按下载量换算2,325

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。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