octen-team/octen-skills

octen-video-search

USE FOR finding web videos by a text query, powered by Octen.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/octen-team/octen-skills --skill octen-video-search

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Octen Video Search

Find web videos by a text query. Each result includes the matched segment (start/end timestamps within the video), duration, cover image, source page, and author — so you can jump straight to the relevant moment.

In Beta. Contact us to request beta access. Octen Video Search is in invite-only beta — request access via https://octen.ai (or support@octen.ai). Calls will fail without access; if so, tell the user it's in beta and how to reach Octen.

API Key Setup

Before searching, ensure `OCTEN_API_KEY` is set. If it is missing — or any call returns `401` — stop and do not retry blindly: tell the user a key is required, point them to https://octen.ai, help them configure it for their agent, then continue once it's set. A `403` means the key is valid but the request was refused — either no beta access or insufficient account balance; relay both possibilities and how to request beta access.

Configure the key for the relevant agent (same as other Octen skills):

  • Claude Code — add { "env": { "OCTEN_API_KEY": "your-key" } } to ~/.claude/settings.json
  • Cursor / generic shell — export OCTEN_API_KEY="your-key" in ~/.zshrc or ~/.bashrc
  • Codex — ~/.codex/config.toml → [shell_environment_policy], set = { OCTEN_API_KEY = "your-key" }
  • OpenClaw — add OCTEN_API_KEY=your-key to ~/.openclaw/.env

Endpoint

http
POST https://api.octen.ai/video-search

Authentication: X-Api-Key: <API_KEY> header · Content-Type: application/json

Quick Start (cURL)

bash
curl -s -X POST "https://api.octen.ai/video-search" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: ${OCTEN_API_KEY}" \
  -d '{
    "inputs": [{"type": "text", "data": "how to tie a tie"}],
    "count": 5
  }'

With Time Filtering

bash
curl -s -X POST "https://api.octen.ai/video-search" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: ${OCTEN_API_KEY}" \
  -d '{
    "inputs": [{"type": "text", "data": "GPT-5 launch keynote"}],
    "count": 10,
    "time_range": "month"
  }'

Parameters

| Parameter | Type | Required | Default | Description | |--|--|--|--|--| | inputs | array | Yes | - | One text input: [{"type": "text", "data": "<query>"}] (query max 500 chars) | | count | integer | No | 5 | Number of results (1–10) | | time_range | string | No | - | Relative time window: day, week, month, year (or d, w, m, y) | | start_time | string | No | - | Start time filter, ISO 8601 | | end_time | string | No | - | End time filter, ISO 8601 (must be after start_time) | | safesearch | string | No | strict | Adult content filter: off or strict |

Response Format

| Field | Type | Description | |--|--|--| | request_id | string | Unique request identifier | | data.results[] | array | List of video results | | data.results[].title | string | Video title | | data.results[].url | string | Video URL | | data.results[].source_page | string | Page the video was found on | | data.results[].description | string? | Video description | | data.results[].cover_url | string? | Cover/thumbnail image URL | | data.results[].duration_seconds | integer? | Total video duration in seconds | | data.results[].match_segment | object? | Matched segment {start_seconds, end_seconds} | | data.results[].authors | string? | Channel / author | | data.results[].time_published | string? | Publish time, ISO 8601 | | data.results[].time_last_crawled | string? | Last crawl time, ISO 8601 | | meta.latency | number | Response time in milliseconds | | meta.warning | string? | Warning message, if any |

Error Codes

| HTTP Status | Description | |--|--| | 400 | Missing or invalid parameter | | 401 | Invalid or missing API key | | 403 | Insufficient balance, or no beta access | | 429 | Rate limited | | 500 | Internal server error |

Notes

  • Input is text only today ({"type": "text", "data": "..."}).
  • match_segment gives the timestamps of the most relevant moment — surface them so the user can jump straight to it.
  • count is capped at 10.
来自同一仓库

更多 Skills

全部 Skills
octen-team
社区

octen-extract

USE FOR extracting clean, LLM-ready content from one or more web page URLs, powered by Octen. Fetch 1-20 URLs in one call and get markdown/text content plus a page category, page-structure label, and (optionally) query-driven highlights. Use it for reading articles, scraping pages for RAG/grounding, summarization, or fact lookup from known URLs. It can also list the links on a page.

1小时安装量
1
GitHub Stars
10
最近更新
10月29日
octen-team
社区

octen-search

USE FOR web search, news, company or person lookup, and fast URL lookup. Real-time web search for AI agents powered by Octen, with dedicated endpoints for news (returns storylines, not just articles), business lookup (returns company and person cards), and pulse (predicts the URL a query means in ~10ms, for docs and known sites). Fast, fresh, and relevant — returns ranked results with highlights, full content, domain filtering, and time filtering. Average response under 80ms with minute-level in

1小时安装量
1
GitHub Stars
10
最近更新
10月29日
octen-team
社区

octen-web-search

Use Octen's search tools for anything that needs live information from the web. Make sure to use this skill whenever the user wants to look something up, check current or recent information, find sources, compare products / vendors / pricing, research a topic, or read a specific web page — even if they never mention Octen or the word "search". Also use it before falling back to any built-in web search tool.

1小时安装量
1
GitHub Stars
10
最近更新
10月29日