← 返回 Skills 市场
sprintmint

cpbox-videos-search

作者 springmint · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
139
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cpbox-videos-search
功能描述
USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination.
使用说明 (SKILL.md)

Videos Search

Paid Videos Search proxy via x402 pay-per-use (HTTP 402).

Prerequisites: This skill requires x402-payment. Complete the setup steps before first use.

Security: Documentation only — no executable code or credentials. Wallet/keys stay on your machine; never stored here.

Service URLs

Role Domain
API Provider https://www.cpbox.io
Facilitator https://www.cppay.finance

Endpoint (Agent Interface)

GET  /api/x402/videos-search
POST /api/x402/videos-search/post

Payment Flow (x402 Protocol)

  1. First request -> 402 Payment Required with requirements JSON
  2. Sign & retry with PAYMENT-SIGNATURE -> result JSON

With @springmint/x402-payment or x402-sdk-go, payment is automatic.

Quick Start (cURL)

Basic Search

curl -s "https://www.cpbox.io/api/x402/videos-search?q=python+tutorial" \
  -H "Accept: application/json"

With Parameters

curl -s "https://www.cpbox.io/api/x402/videos-search" \
  -H "Accept: application/json" \
  -G \
  --data-urlencode "q=machine learning explained" \
  --data-urlencode "country=US" \
  --data-urlencode "search_lang=en" \
  --data-urlencode "count=20" \
  --data-urlencode "freshness=pm"

Using with x402-payment

npx @springmint/x402-payment \
  --url "https://www.cpbox.io/api/x402/videos-search?q=python+tutorial&count=20" \
  --method GET

Parameters

Parameter Type Required Default Description
q string Yes - Search query (1-400 chars, max 50 words)
country string No US Search country (2-letter country code or ALL)
search_lang string No en Language preference (2+ char language code)
ui_lang string No en-US UI language (e.g., "en-US")
count int No 20 Number of results (1-50)
offset int No 0 Page offset (0-9)
safesearch string No moderate Adult content filter (off/moderate/strict)
freshness string No - Time filter (pd/pw/pm/py or date range)
spellcheck bool No true Auto-correct query
operators bool No true Apply search operators
include_fetch_metadata bool No false Include fetched_content_timestamp in results

Freshness Values

Value Description
pd Past day (24 hours)
pw Past week (7 days)
pm Past month (31 days)
py Past year (365 days)
YYYY-MM-DDtoYYYY-MM-DD Custom date range

Response Format

{
  "type": "videos",
  "query": {
    "original": "python tutorial",
    "spellcheck_off": false
  },
  "extra": {
    "might_be_offensive": false
  },
  "results": [
    {
      "type": "video_result",
      "title": "Python Tutorial for Beginners",
      "url": "https://www.youtube.com/watch?v=rfscVS0vtbw",
      "description": "Learn Python programming from scratch...",
      "age": "February 12, 2025",
      "page_age": "2025-02-12T00:00:00",
      "page_fetched": "2025-02-12T15:00:00Z",
      "thumbnail": {
        "src": "https://imgs.search.provider/...",
        "original": "https://i.ytimg.com/vi/rfscVS0vtbw/hqdefault.jpg"
      },
      "video": {
        "duration": "03:45:00",
        "views": 1523000,
        "creator": "freeCodeCamp",
        "publisher": "YouTube",
        "requires_subscription": false,
        "tags": ["python", "programming"],
        "author": {
          "name": "freeCodeCamp.org",
          "url": "https://www.youtube.com/@freecodecamp"
        }
      },
      "meta_url": {
        "scheme": "https",
        "netloc": "youtube.com",
        "hostname": "www.youtube.com",
        "favicon": "https://imgs.search.provider/...",
        "path": "\u203a watch"
      }
    }
  ]
}

Response Fields

Field Type Description
type string Always "videos"
query.original string The original search query
query.altered string? Spellcheck-corrected query (if changed)
query.cleaned string? Cleaned/normalized query
query.spellcheck_off bool? Whether spellcheck was disabled
query.show_strict_warning bool? True if strict safesearch blocked adult results
query.search_operators object? Applied search operators (applied, cleaned_query, sites)
extra.might_be_offensive bool Whether results may contain offensive content
results[].type string Always "video_result"
results[].url string Source URL of the video
results[].title string Video title
results[].description string? Video description
results[].age string? Human-readable age (e.g. "6 months ago") or absolute date (e.g. "February 12, 2025")
results[].page_age string? Page age from source (ISO datetime)
results[].page_fetched string? ISO datetime when page was last fetched (e.g. 2025-02-12T15:00:00Z)
results[].fetched_content_timestamp int? Fetch timestamp (only with include_fetch_metadata=true)
results[].video.duration string? Time string (variable format)
results[].video.views int? View count as integer
results[].video.creator string? Channel/creator name
results[].video.publisher string? Platform (YouTube, Vimeo, etc.)
results[].video.requires_subscription bool? Whether video requires a subscription
results[].video.tags list[str]? Tags relevant to the video
results[].video.author object? Author profile
results[].video.author.name string Author name
results[].video.author.url string Author profile URL
results[].video.author.long_name string? Extended author name
results[].video.author.img string? Author profile image URL
results[].thumbnail.src string Served thumbnail URL
results[].thumbnail.original string? Original thumbnail URL
results[].meta_url.scheme string? URL protocol scheme
results[].meta_url.netloc string? Network location
results[].meta_url.hostname string? Lowercased domain name
results[].meta_url.favicon string? Favicon URL
results[].meta_url.path string? URL path

Search Operators

Use search operators to refine results:

  • site:youtube.com - Limit to specific site
  • "exact phrase" - Match exact phrase
  • -exclude - Exclude term

Set operators=false to disable operator parsing.

Use Cases

  • Video content research: Find tutorials, explainers, and reviews by topic. Use the video.duration, video.views, and video.creator metadata to filter and rank results programmatically. Prefer videos-search over web-search when you need a dedicated video index with richer metadata (duration, views, creator, tags) and up to 50 results per request.
  • Fresh video monitoring: Use freshness=pd or freshness=pw to track newly published video content on trending topics or specific subjects.
  • Platform-specific search: Use site:youtube.com or site:vimeo.com operators to target specific video platforms.
  • Video metadata extraction: Get view counts, durations, creator info, and tags for analytics, content curation, or recommendation systems.

Notes

  • Pagination: Use offset (0-9) with count for more results
  • Max results: Up to 50 results per request
安全使用建议
This skill appears to do what it says: call cpbox.io's paid video-search API and return structured results. Before installing or using it: 1) Verify the reputation and authenticity of the external endpoints (https://www.cpbox.io and https://www.cppay.finance) and the referenced GitHub repo; the registry metadata lacks a homepage/source. 2) Be cautious when running npx (npx @springmint/x402-payment) because npx downloads and executes remote npm code—only run it if you trust the package and maintainer. 3) The skill itself doesn't ask for secrets, but the payment flow requires signing with a wallet/private key on your machine—ensure you never paste private keys into untrusted prompts and that signing is done locally. 4) If you need higher assurance, ask the skill author for the source repository or a signed package and review the x402 payment SDK code before using it.
功能分析
Type: OpenClaw Skill Name: cpbox-videos-search Version: 1.0.0 The skill bundle 'cpbox-videos-search' is a documentation-only package providing an interface for an AI agent to access a video search API via the x402 payment protocol. It contains no executable code (Python/JS) and focuses entirely on defining API endpoints (cpbox.io), parameters, and response formats in SKILL.md. While it references an external payment SDK (@springmint/x402-payment), this is consistent with the stated purpose of a paid search proxy, and there are no indicators of data exfiltration, malicious execution, or prompt injection.
能力评估
Purpose & Capability
Name/description match the SKILL.md: it proxies a paid video search (cpbox.io) and returns the listed fields. However the registry metadata lacks a source/homepage and the skill depends on an external x402 payment flow (cppay.finance / @springmint/x402-payment). That dependency is reasonable for a pay-per-use proxy but worth validating since the skill package itself contains no provenance.
Instruction Scope
The SKILL.md only instructs HTTP requests to https://www.cpbox.io and the payment facilitator https://www.cppay.finance; it does not instruct reading system files or unrelated environment variables. A notable instruction is to use npx @springmint/x402-payment, which will fetch and execute code from the npm registry at runtime—this is expected for the advertised automatic payment flow but increases runtime trust requirements.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by the skill itself. No package downloads or extract steps are declared in the skill bundle.
Credentials
The skill declares no required environment variables or credentials. That said, the payment flow requires signing payment requests with a local wallet/key (per the SKILL.md). The skill doesn't request secrets itself, but using the payment SDK or signing commands will require a wallet private key be present on the user's machine—ensure keys are kept local and not uploaded.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent system privileges or modify other skills' configurations. Autonomous invocation is allowed (platform default) and not flagged on its own.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install cpbox-videos-search
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cpbox-videos-search 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial publish
元数据
Slug cpbox-videos-search
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

cpbox-videos-search 是什么?

USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 139 次。

如何安装 cpbox-videos-search?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install cpbox-videos-search」即可一键安装,无需额外配置。

cpbox-videos-search 是免费的吗?

是的,cpbox-videos-search 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

cpbox-videos-search 支持哪些平台?

cpbox-videos-search 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 cpbox-videos-search?

由 springmint(@sprintmint)开发并维护,当前版本 v1.0.0。

💬 留言讨论