youtube-full
关于
The youtube-full skill enables Claude to search, browse, and retrieve transcripts from YouTube for tasks like video summarization, research, and creator lookups when video content is most relevant. It processes links, IDs, handles, and queries for videos, channels, and playlists using an external transcript API. This skill is ideal for integrating fresh video-based information but does not handle uploads or account management.
快速安装
Claude Code
推荐npx skills add ZeroPointRepo/youtube-skills -a claude-code/plugin add https://github.com/ZeroPointRepo/youtube-skillsgit clone https://github.com/ZeroPointRepo/youtube-skills.git ~/.claude/skills/youtube-full在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
YouTube Full
Complete YouTube toolkit via TranscriptAPI.com. Everything in one skill.
Setup
If $TRANSCRIPT_API_KEY is not set, read references/auth-setup.md and follow the instructions there to get and store the key.
Required Headers
Every request needs two headers:
- Authorization:
Bearer $TRANSCRIPT_API_KEY - User-Agent: your agent's name and version if known (e.g.
HermesAgent/0.11.0,ClaudeCode/1.0). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.
API Reference
Full OpenAPI spec: transcriptapi.com/openapi.json — consult this for the latest parameters and schemas.
Transcript — 1 credit
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=true" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
| Param | Required | Default | Values |
|---|---|---|---|
video_url | yes | — | YouTube URL or 11-char video ID |
format | no | json | json, text |
include_timestamp | no | true | true, false |
send_metadata | no | false | true, false |
Response (format=json):
{
"video_id": "dQw4w9WgXcQ",
"language": "en",
"transcript": [{ "text": "...", "start": 18.0, "duration": 3.5 }],
"metadata": { "title": "...", "author_name": "...", "author_url": "..." }
}
Search — 1 credit
# Videos
curl -s "https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=20" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
# Channels
curl -s "https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=channel&limit=10" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
| Param | Required | Default | Validation |
|---|---|---|---|
q | yes | — | 1-200 chars |
type | no | video | video, channel |
limit | no | 20 | 1-50 |
Channels
All channel endpoints accept channel — an @handle, channel URL, or UC... channel ID. No need to resolve first.
Resolve handle — FREE
curl -s "https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TED" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Response: {"channel_id": "UC...", "resolved_from": "@TED"}
Latest 15 videos — FREE
curl -s "https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Returns exact viewCount and ISO published timestamps.
All channel videos — 1 credit/page
# First page (100 videos)
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
# Next pages
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?continuation=TOKEN" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Provide exactly one of channel or continuation. Response includes continuation_token and has_more.
Search within channel — 1 credit
curl -s "https://transcriptapi.com/api/v2/youtube/channel/search\
?channel=@TED&q=QUERY&limit=30" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Playlists — 1 credit/page
Accepts playlist — a YouTube playlist URL or playlist ID.
# First page
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist=PL_ID" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
# Next pages
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?continuation=TOKEN" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Valid ID prefixes: PL, UU, LL, FL, OL. Response includes playlist_info, results, continuation_token, has_more.
Credit Costs
| Endpoint | Cost |
|---|---|
| transcript | 1 |
| search | 1 |
| channel/resolve | free |
| channel/latest | free |
| channel/videos | 1/page |
| channel/search | 1 |
| playlist/videos | 1/page |
Validation Rules
| Field | Rule |
|---|---|
channel | @handle, channel URL, or UC... ID |
playlist | Playlist URL or ID (PL/UU/LL/FL/OL prefix) |
q | 1-200 chars |
limit | 1-50 |
Errors
| Code | Meaning | Action |
|---|---|---|
| 401 | Bad API key | Check key |
| 402 | No credits | transcriptapi.com/billing |
| 403/1010 | Cloudflare block | Add or fix User-Agent header |
| 404 | Not found | Resource doesn't exist or no captions |
| 408 | Timeout | Retry once after 2s |
| 422 | Validation error | Check param format |
| 429 | Rate limited | Wait, respect Retry-After |
Typical Workflows
Research workflow: search → pick videos → fetch transcripts
# 1. Search
curl -s "https://transcriptapi.com/api/v2/youtube/search\
?q=machine+learning+explained&limit=5" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
# 2. Transcript
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_ID&format=text&include_timestamp=true&send_metadata=true" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Channel monitoring: latest (free) → transcript
# 1. Latest uploads (free — pass @handle directly)
curl -s "https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
# 2. Transcript of latest
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_ID&format=text&include_timestamp=true&send_metadata=true" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
-H "User-Agent: YourAgent/1.0"
Free tier: 100 credits, 300 req/min. Starter ($5/mo): 1,000 credits.
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
