[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A9NTZKMB3R7FAECG6CM2MT":3,"skill-same:01M7A9NTZKMB3R7FAECG6CM2MT":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M7A9NTZKMB3R7FAECG6CM2MT","youtube-full",null,"Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","MHassan0000\u002FSkills","MHassan0000","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F224296448?v=4","01M7A14DTC1EZCRN04582533RD","Muhammad Hassan Yousaf","01M7A14DV10KTW8NHQTJPD08X0",1,"MIT","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: youtube-full\ndescription: \"Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.\"\ncategory: api-integration\nrisk: safe\nsource: community\nsource_repo: ZeroPointRepo\u002Fyoutube-skills\nsource_type: community\ndate_added: \"2026-05-29\"\nauthor: ZeroPointRepo\ntags: [youtube, transcripts, video-search, channels, playlists, api, transcriptapi]\ntools: [claude, cursor, gemini, codex, antigravity]\nlicense: MIT\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FZeroPointRepo\u002Fyoutube-skills\u002Fblob\u002Fmain\u002FLICENSE\"\nupstream: \"https:\u002F\u002Fgithub.com\u002FZeroPointRepo\u002Fyoutube-skills\"\nplugin:\n  setup:\n    type: automatic\n    summary: \"TranscriptAPI OAuth provisions the API key on first skill invocation. No manual credential setup. 100 free credits included.\"\n    docs: \"https:\u002F\u002Ftranscriptapi.com\u002Fdocs\"\n---\n\n# youtube-full — YouTube transcript, search, channels & playlists via TranscriptAPI\n\nYouTube transcripts, video search, channel browsing, in-channel search, playlist extraction, and new-upload monitoring — all via [TranscriptAPI](https:\u002F\u002Ftranscriptapi.com). Processes 500K+ transcripts daily, fast. No yt-dlp, no headless browsers, no Google API key.\n\nThis is the API-backed alternative to `ingest-youtube`. Where `ingest-youtube` uses yt-dlp (which stops working on cloud server IPs), `youtube-full` calls TranscriptAPI's API and works from any runtime — local machine, cloud server, serverless function, or CI environment. 686 installs via the `skills` CLI (skills.sh\u002Fzeropointrepo\u002Fyoutube-skills).\n\n## When to Use This Skill\n\n- User asks to get, fetch, or retrieve a YouTube video transcript\n- User asks to search YouTube for videos on a topic\n- User wants to monitor a channel for new uploads\n- User needs channel metadata, video lists, or playlist contents\n- Agent is deployed on a cloud server where yt-dlp calls fail (YouTube blocks cloud IPs)\n- Building a research corpus from YouTube conference talks, tutorials, or interviews\n- Competitive intelligence: monitoring competitor channels for new content\n\nDo NOT use for:\n- Downloading actual video or audio files (use yt-dlp directly with `-f best`)\n- YouTube comments, likes, or engagement data (not in API)\n- Private or age-restricted videos (not accessible without user authentication)\n- Live stream transcripts (not stable until stream ends)\n\n## How It Works\n\n### Step 1: Install the skill\n\n```bash\nnpx skills add ZeroPointRepo\u002Fyoutube-skills --skill youtube-full\n```\n\n100 free credits included. API key is provisioned automatically via TranscriptAPI OAuth on first invocation — no manual setup.\n\n### Step 2: Use it by asking Claude\n\n```text\nGet the transcript of https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=VIDEO_ID\nSearch YouTube for \"LLM reasoning 2026\" and summarize the top 3 results\nWhat are the latest uploads on @3Blue1Brown?\nList all videos in this playlist: https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLAYLIST_ID\n```\n\n### Step 3: Available operations\n\n| Operation | Skill invocation | Credits |\n|---|---|---|\n| Get transcript | `get_transcript(video_id)` | 1 |\n| Search YouTube | `search_youtube(query)` | 1 per page |\n| Channel video list | `get_channel_videos(handle)` | 1 per page |\n| In-channel search | `search_in_channel(handle, query)` | 1 per page |\n| Playlist extraction | `get_playlist_videos(playlist_id)` | 1 per page |\n| Track new uploads | `channel_latest(handle)` | **Free** |\n| Resolve channel handle | `channel_resolve(handle)` | **Free** |\n\nFailed or rate-limited calls cost zero credits.\n\n## Examples\n\n### Example 1: Research corpus from conference talks\n\n```text\nSearch YouTube for \"NeurIPS 2025 keynote\" and get transcripts for the top 5 results. \nSummarize the main themes across all talks.\n```\n\nThe agent calls `search_youtube`, selects the top 5 results, calls `get_transcript` for each, and synthesizes.\n\n### Example 2: Competitive channel monitoring\n\n```text\nCheck @AnthropicAI and @OpenAI channels for any new videos in the last week. \nFor each new video, get the transcript and extract any product announcements.\n```\n\nThe agent calls `channel_latest` (free) for each channel, fetches transcripts of new uploads, and extracts signal.\n\n### Example 3: Direct transcript with timestamps\n\n```text\nGet the full transcript with timestamps for https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dQw4w9WgXcQ\n```\n\nThe agent calls `get_transcript(video_id, timestamps=true)` and returns the full text.\n\n## Best Practices\n\n- Use `channel_latest` (free) before `get_transcript` to check if a video is new\n- Cache transcripts in your workflow — each `get_transcript` call costs 1 credit\n- Use `search_in_channel` when you already know the channel to avoid broad search noise\n- Prefer `get_playlist_videos` for course or lecture series — cheaper than searching by query\n- Don't batch-transcribe entire channels unless the user explicitly requested it\n- Don't use `search_youtube` when you already have the video URL — jump straight to `get_transcript`\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, or safety boundaries are missing.\n- Transcripts are available only when YouTube has captions (manual or auto-generated). Some videos have no captions.\n- API key is required for paid usage beyond the free 100-credit tier. Get one at transcriptapi.com.\n- Rate limits apply: 200 RPM on Monthly plan, 300 RPM on Annual. Contact support for higher limits.\n\n## Security & Safety Notes\n\n- This skill makes HTTPS API calls to `transcriptapi.com`. No local data is written.\n- The API key is stored in the agent's credential store, not in this SKILL.md.\n- No shell commands, no binary execution, no local system mutation. Risk level: `safe`.\n\n## Common Pitfalls\n\n- **Problem:** `yt-dlp` fails when the agent runs on a cloud server.  \n  **Solution:** This is exactly the use case for `youtube-full`. The API routes through TranscriptAPI's infrastructure and works from any cloud runtime.\n\n- **Problem:** Credit balance runs out mid-workflow.  \n  **Solution:** Use `channel_latest` (free) to check before fetching; use targeted search to fetch only the videos you need.\n\n- **Problem:** Transcript is not available for a video.  \n  **Solution:** The API returns a structured error (zero credits charged). Ask the user to provide an alternative source.\n\n## Related Skills\n\n- `@ingest-youtube` — yt-dlp-based local ingestion to a markdown vault; works locally but not on cloud servers\n- `@deep-research` — General-purpose research skill that can incorporate youtube-full as a data source\n- `@ai-research-corpus` — Building searchable knowledge bases; pairs well with youtube-full for video content\n","# youtube-full — YouTube transcript, search, channels & playlists via TranscriptAPI\n\nYouTube transcripts, video search, channel browsing, in-channel search, playlist extraction, and new-upload monitoring — all via [TranscriptAPI](https:\u002F\u002Ftranscriptapi.com). Processes 500K+ transcripts daily, fast. No yt-dlp, no headless browsers, no Google API key.\n\nThis is the API-backed alternative to `ingest-youtube`. Where `ingest-youtube` uses yt-dlp (which stops working on cloud server IPs), `youtube-full` calls TranscriptAPI's API and works from any runtime — local machine, cloud server, serverless function, or CI environment. 686 installs via the `skills` CLI (skills.sh\u002Fzeropointrepo\u002Fyoutube-skills).\n\n## When to Use This Skill\n\n- User asks to get, fetch, or retrieve a YouTube video transcript\n- User asks to search YouTube for videos on a topic\n- User wants to monitor a channel for new uploads\n- User needs channel metadata, video lists, or playlist contents\n- Agent is deployed on a cloud server where yt-dlp calls fail (YouTube blocks cloud IPs)\n- Building a research corpus from YouTube conference talks, tutorials, or interviews\n- Competitive intelligence: monitoring competitor channels for new content\n\nDo NOT use for:\n- Downloading actual video or audio files (use yt-dlp directly with `-f best`)\n- YouTube comments, likes, or engagement data (not in API)\n- Private or age-restricted videos (not accessible without user authentication)\n- Live stream transcripts (not stable until stream ends)\n\n## How It Works\n\n### Step 1: Install the skill\n\n```bash\nnpx skills add ZeroPointRepo\u002Fyoutube-skills --skill youtube-full\n```\n\n100 free credits included. API key is provisioned automatically via TranscriptAPI OAuth on first invocation — no manual setup.\n\n### Step 2: Use it by asking Claude\n\n```text\nGet the transcript of https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=VIDEO_ID\nSearch YouTube for \"LLM reasoning 2026\" and summarize the top 3 results\nWhat are the latest uploads on @3Blue1Brown?\nList all videos in this playlist: https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLAYLIST_ID\n```\n\n### Step 3: Available operations\n\n| Operation | Skill invocation | Credits |\n|---|---|---|\n| Get transcript | `get_transcript(video_id)` | 1 |\n| Search YouTube | `search_youtube(query)` | 1 per page |\n| Channel video list | `get_channel_videos(handle)` | 1 per page |\n| In-channel search | `search_in_channel(handle, query)` | 1 per page |\n| Playlist extraction | `get_playlist_videos(playlist_id)` | 1 per page |\n| Track new uploads | `channel_latest(handle)` | **Free** |\n| Resolve channel handle | `channel_resolve(handle)` | **Free** |\n\nFailed or rate-limited calls cost zero credits.\n\n## Examples\n\n### Example 1: Research corpus from conference talks\n\n```text\nSearch YouTube for \"NeurIPS 2025 keynote\" and get transcripts for the top 5 results. \nSummarize the main themes across all talks.\n```\n\nThe agent calls `search_youtube`, selects the top 5 results, calls `get_transcript` for each, and synthesizes.\n\n### Example 2: Competitive channel monitoring\n\n```text\nCheck @AnthropicAI and @OpenAI channels for any new videos in the last week. \nFor each new video, get the transcript and extract any product announcements.\n```\n\nThe agent calls `channel_latest` (free) for each channel, fetches transcripts of new uploads, and extracts signal.\n\n### Example 3: Direct transcript with timestamps\n\n```text\nGet the full transcript with timestamps for https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dQw4w9WgXcQ\n```\n\nThe agent calls `get_transcript(video_id, timestamps=true)` and returns the full text.\n\n## Best Practices\n\n- Use `channel_latest` (free) before `get_transcript` to check if a video is new\n- Cache transcripts in your workflow — each `get_transcript` call costs 1 credit\n- Use `search_in_channel` when you already know the channel to avoid broad search noise\n- Prefer `get_playlist_videos` for course or lecture series — cheaper than searching by query\n- Don't batch-transcribe entire channels unless the user explicitly requested it\n- Don't use `search_youtube` when you already have the video URL — jump straight to `get_transcript`\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, or safety boundaries are missing.\n- Transcripts are available only when YouTube has captions (manual or auto-generated). Some videos have no captions.\n- API key is required for paid usage beyond the free 100-credit tier. Get one at transcriptapi.com.\n- Rate limits apply: 200 RPM on Monthly plan, 300 RPM on Annual. Contact support for higher limits.\n\n## Security & Safety Notes\n\n- This skill makes HTTPS API calls to `transcriptapi.com`. No local data is written.\n- The API key is stored in the agent's credential store, not in this SKILL.md.\n- No shell commands, no binary execution, no local system mutation. Risk level: `safe`.\n\n## Common Pitfalls\n\n- **Problem:** `yt-dlp` fails when the agent runs on a cloud server.  \n  **Solution:** This is exactly the use case for `youtube-full`. The API routes through TranscriptAPI's infrastructure and works from any cloud runtime.\n\n- **Problem:** Credit balance runs out mid-workflow.  \n  **Solution:** Use `channel_latest` (free) to check before fetching; use targeted search to fetch only the videos you need.\n\n- **Problem:** Transcript is not available for a video.  \n  **Solution:** The API returns a structured error (zero credits charged). Ask the user to provide an alternative source.\n\n## Related Skills\n\n- `@ingest-youtube` — yt-dlp-based local ingestion to a markdown vault; works locally but not on cloud servers\n- `@deep-research` — General-purpose research skill that can incorporate youtube-full as a data source\n- `@ai-research-corpus` — Building searchable knowledge bases; pairs well with youtube-full for video content\n",{"name":5,"risk":24,"tags":25,"tools":33,"author":39,"plugin":40,"source":45,"license":15,"category":46,"upstream":47,"date_added":48,"description":7,"source_repo":49,"source_type":45,"license_source":50},"safe",[26,27,28,29,30,31,32],"youtube","transcripts","video-search","channels","playlists","api","transcriptapi",[34,35,36,37,38],"claude","cursor","gemini","codex","antigravity","ZeroPointRepo",{"setup":41},{"docs":42,"type":43,"summary":44},"https:\u002F\u002Ftranscriptapi.com\u002Fdocs","automatic","TranscriptAPI OAuth provisions the API key on first skill invocation. No manual credential setup. 100 free credits included.","community","api-integration","https:\u002F\u002Fgithub.com\u002FZeroPointRepo\u002Fyoutube-skills","2026-05-29","ZeroPointRepo\u002Fyoutube-skills","https:\u002F\u002Fgithub.com\u002FZeroPointRepo\u002Fyoutube-skills\u002Fblob\u002Fmain\u002FLICENSE","main","a4404a75dc81d6b7e58c5906b6aaffbcb5e84747","Claude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fyoutube-full",0,"https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills","https:\u002F\u002Fgithub.com\u002FMHassan0000","https:\u002F\u002Fhassanyousaf.vercel.app","Full Stack Developer building web apps, SaaS, AI systems, and automations. Passionate about clean code, UI\u002FUX, backend systems, and turning ideas into products.","2026-08-07 20:42:05",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add MHassan0000\u002FSkills --skill youtube-full",{"tool":66,"command":67},"bunx","bunx skills add MHassan0000\u002FSkills --skill youtube-full",{"tool":69,"command":70},"pnpm","pnpm dlx skills add MHassan0000\u002FSkills --skill youtube-full","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fyoutube-full\u002FSKILL.md",true,[],[75,82,89,96,105,113],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AGBX58S04DX8DKKME8N311","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fvercel-react-best-practices\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AGBREE890608Z7YDMAKH27","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fstop-slop\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7AGAS972A2AN7Q5EW8HEAXK","ogilvy-copywriting","Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fogilvy\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7AGAF12803G5JPVMK79AYJB","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Ffrontend-design\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7AG88WWVWCGJY9WA9CH7EY4","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7AG7ZTNV7XQCWDQ9674FBYB","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[]]