{"id":"be6ed0ee-fed1-49fb-9b80-e1d481a857e5","entityType":"agent","slug":"clawhub-globalcaos-youtube-ultimate","name":"YouTube Ultimate","canonicalUrl":"https://www.xpersona.co/agent/clawhub-globalcaos-youtube-ultimate","canonicalPath":"/agent/clawhub-globalcaos-youtube-ultimate","generatedAt":"2026-10-09T18:52:41.545Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Skill: YouTube Ultimate Owner: globalcaos Summary: Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Tags: latest:4.2.2 Version history: v4.2.2 | 2026-02-21T07:34:27.056Z | user Humor boost: 200/month upgrade line v4.2.1 | 2026-02-21T07:33:30.098Z | user Added notes.security transparency block v4.2.0 | 2026-02-21T07:05:24.628Z | user Marketia copy (Hook/Sell/Convert), metadata.openclaw b","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn7623hrcwt6rg73a67xw3wyx580asdw:youtube-ultimate","sourceUrl":"https://clawhub.ai/globalcaos/youtube-ultimate","homepage":"https://clawhub.ai/globalcaos/youtube-ultimate","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/globalcaos/youtube-ultimate","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":67,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Skill: YouTube Ultimate Owner: globalcaos Summary: Free transcripts, 4K download"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":2206,"packageName":null,"latestVersion":"4.2.2","tractionLabel":"2.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-02-28T18:59:11.769Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-28T18:59:11.769Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-01T18:59:11.769Z","lastVerifiedAt":null,"highlights":[{"version":"4.2.2","createdAt":"2026-02-21T07:34:27.056Z","changelog":"Humor boost: 200/month upgrade line","fileCount":4,"zipByteSize":10855},{"version":"4.2.1","createdAt":"2026-02-21T07:33:30.098Z","changelog":"Added notes.security transparency block","fileCount":4,"zipByteSize":10776},{"version":"4.2.0","createdAt":"2026-02-21T07:05:24.628Z","changelog":"Marketia copy (Hook/Sell/Convert), metadata.openclaw block, humor grade 5/10","fileCount":null,"zipByteSize":null},{"version":"1.0.6","createdAt":"2026-02-13T22:12:23.931Z","changelog":"Fix repository/homepage links to fork","fileCount":null,"zipByteSize":null},{"version":"1.0.5","createdAt":"2026-02-13T22:09:09.423Z","changelog":"SEO-optimized description and keywords for better discoverability","fileCount":null,"zipByteSize":null},{"version":"1.0.4","createdAt":"2026-02-11T13:20:05.030Z","changelog":"- Update to version 1.0.4 - Added new metadata file (_meta.json) for enhanced skill management - Updated description in SKILL.md for improved clarity and conciseness","fileCount":null,"zipByteSize":null},{"version":"1.0.3","createdAt":"2026-02-08T23:35:02.689Z","changelog":"Added credits, fixed repository link","fileCount":null,"zipByteSize":null},{"version":"1.0.2","createdAt":"2026-02-08T05:10:50.967Z","changelog":"Fix: removed author attribution with real name","fileCount":null,"zipByteSize":null}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn7623hrcwt6rg73a67xw3wyx580asdw:youtube-ultimate","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T18:52:41.544Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-youtube-ultimate/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: YouTube Ultimate\n\nOwner: globalcaos\n\nSummary: Free transcripts, 4K downloads, and video exploration — zero API quotas burned.\n\nTags: latest:4.2.2\n\nVersion history:\n\nv4.2.2 | 2026-02-21T07:34:27.056Z | user\n\nHumor boost: 200/month upgrade line\n\nv4.2.1 | 2026-02-21T07:33:30.098Z | user\n\nAdded notes.security transparency block\n\nv4.2.0 | 2026-02-21T07:05:24.628Z | user\n\nMarketia copy (Hook/Sell/Convert), metadata.openclaw block, humor grade 5/10\n\nv1.0.6 | 2026-02-13T22:12:23.931Z | user\n\nFix repository/homepage links to fork\n\nv1.0.5 | 2026-02-13T22:09:09.423Z | user\n\nSEO-optimized description and keywords for better discoverability\n\nv1.0.4 | 2026-02-11T13:20:05.030Z | auto\n\n- Update to version 1.0.4\n- Added new metadata file (_meta.json) for enhanced skill management\n- Updated description in SKILL.md for improved clarity and conciseness\n\nv1.0.3 | 2026-02-08T23:35:02.689Z | user\n\nAdded credits, fixed repository link\n\nv1.0.2 | 2026-02-08T05:10:50.967Z | user\n\nFix: removed author attribution with real name\n\nv1.0.1 | 2026-02-06T21:03:04.028Z | user\n\nv1.0.1: Added repository link to OpenClaw fork.\n\nv2.0.0 | 2026-02-06T05:55:01.367Z | user\n\nv2 release: Unified transcripts, search, batch ops, and downloads in one skill.\n\nv1.0.0 | 2026-02-03T09:11:53.717Z | user\n\nInitial release of Research Pro\n\nArchive index:\n\nArchive v4.2.2: 4 files, 10855 bytes\n\nFiles: _meta.json (135b), README.md (9591b), scripts/youtube.py (25143b), SKILL.md (1819b)\n\nFile v4.2.2:SKILL.md\n\n---\nname: youtube-ultimate\nversion: 4.2.2\ndescription: \"Free transcripts, 4K downloads, and video exploration — zero API quotas burned.\"\nmetadata:\n  openclaw:\n    owner: kn7623hrcwt6rg73a67xw3wyx580asdw\n    category: media\n    tags:\n      - youtube\n      - transcripts\n      - video-download\n      - media\n      - offline\n    license: MIT\n    notes:\n      security: \"This skill invokes yt-dlp and youtube-transcript-api locally to fetch transcripts and download videos. No credentials stored, no API keys required, no external services beyond YouTube itself. All processing happens on your machine. No data is sent anywhere except standard YouTube HTTP requests.\"\n---\n\n# YouTube Ultimate\n\n**Your agent reads YouTube so you don't have to.** Pull transcripts, summarize videos, and extract knowledge — all without touching YouTube's API quota.\n\n## What It Does\n\n- **Free Transcripts** — Grab any video's transcript instantly. No API key, no quota, no billing surprises at 3 AM. Won't burn through your free-tier quota fetching a single playlist, then suggest you upgrade to the $200/month plan like it's doing you a favor.\n- **4K Video Downloads** — Save videos locally for offline access, training data, or that flight where Wi-Fi costs more than the ticket.\n- **Video Exploration** — Search, browse, and drill into video details without rate-limit anxiety.\n\n## Why It Matters\n\nYouTube's API gives you 10,000 quota units per day. A single search costs 100. A transcript request? Not even supported. YouTube Ultimate sidesteps all of that. Your agent gets full access to video content while your quota counter stays at zero.\n\n*Clone it. Fork it. Break it. Make it yours.*\n\n👉 Explore the full project: [github.com/globalcaos/clawdbot-moltbot-openclaw](https://github.com/globalcaos/clawdbot-moltbot-openclaw)\n\nFile v4.2.2:README.md\n\n# 📺 YouTube Research Pro\n\n**The most comprehensive YouTube skill for AI agents.**\n\nExtract transcripts for FREE, search videos, analyze channels, download content — all from one unified interface.\n\n---\n\n## Why This Skill?\n\nWe analyzed **15+ YouTube MCP servers** and found that each one does _one thing_ well, but none does _everything_. So we built the skill we wished existed.\n\n| What Others Do                     | What We Do                                  |\n| ---------------------------------- | ------------------------------------------- |\n| Transcripts OR search OR downloads | **All three, unified**                      |\n| Burn API quota on transcripts      | **FREE transcripts** (zero quota)           |\n| Single video at a time             | **Batch operations** (50 videos)            |\n| Basic search                       | **Filtered search** (date, duration, order) |\n| Text output only                   | **JSON export** for pipelines               |\n\n### The Killer Feature: FREE Transcripts\n\nMost YouTube tools use the official YouTube Data API for transcripts, which costs **100 quota units per request**. With a daily limit of 10,000 units, you can only fetch ~100 transcripts per day.\n\n**We use `youtube-transcript-api`** — a library that extracts transcripts directly from YouTube's frontend, costing **zero API quota**. Fetch unlimited transcripts, every day.\n\n---\n\n## What Can Your Agent Do With This?\n\n### 🔍 Research & Analysis\n\n- Search YouTube with filters (date, duration, view count)\n- Get video details in batch (up to 50 at once)\n- Extract full transcripts for content analysis\n- Read comments to gauge audience sentiment\n\n### 📝 Content Extraction\n\n- Pull transcripts in any available language\n- Get timestamped transcripts for precise references\n- Export everything as JSON for further processing\n\n### 📥 Downloads\n\n- Download videos at any resolution\n- Extract audio only (podcasts, music, interviews)\n- Grab subtitles as separate files\n\n### 📊 Channel Intelligence\n\n- Analyze channel statistics\n- Track subscriber counts and view totals\n- List and explore playlists\n\n---\n\n## Quick Examples\n\n```bash\n# Get a video transcript (FREE - no API quota!)\nuv run youtube.py transcript dQw4w9WgXcQ\n\n# With timestamps\nuv run youtube.py transcript dQw4w9WgXcQ --timestamps\n\n# Search with filters\nuv run youtube.py search \"machine learning\" --duration long --order viewCount\n\n# Batch video details\nuv run youtube.py video id1 id2 id3 id4 id5 --json\n\n# Download audio as MP3\nuv run youtube.py download-audio VIDEO_ID -f mp3\n\n# Get top comments with replies\nuv run youtube.py comments VIDEO_ID --replies\n```\n\n---\n\n## Complete Command Reference\n\n### Transcripts (FREE - Zero API Quota)\n\n| Command                         | Description                          |\n| ------------------------------- | ------------------------------------ |\n| `transcript VIDEO`              | Extract transcript as plain text     |\n| `transcript VIDEO --timestamps` | Include [MM:SS] timestamps           |\n| `transcript VIDEO -l es,en`     | Prefer Spanish, fall back to English |\n| `transcript VIDEO --json`       | Output as JSON array                 |\n| `transcript-list VIDEO`         | List all available languages         |\n\n### Search & Discovery\n\n| Command                                               | Description                     |\n| ----------------------------------------------------- | ------------------------------- |\n| `search QUERY`                                        | Search YouTube videos           |\n| `search QUERY -l 20`                                  | Return 20 results (default: 10) |\n| `search QUERY --order date`                           | Sort by upload date             |\n| `search QUERY --order viewCount`                      | Sort by popularity              |\n| `search QUERY --duration short`                       | Under 4 minutes                 |\n| `search QUERY --duration long`                        | Over 20 minutes                 |\n| `search QUERY --published-after 2026-01-01T00:00:00Z` | Filter by date                  |\n\n### Video Information\n\n| Command             | Description              |\n| ------------------- | ------------------------ |\n| `video ID`          | Get video details        |\n| `video ID1 ID2 ID3` | Batch mode (up to 50)    |\n| `video ID --json`   | JSON output              |\n| `video ID -v`       | Include full description |\n\n### Comments\n\n| Command                       | Description           |\n| ----------------------------- | --------------------- |\n| `comments VIDEO`              | Get top comments      |\n| `comments VIDEO -l 50`        | Get 50 comments       |\n| `comments VIDEO --replies`    | Include reply threads |\n| `comments VIDEO --order time` | Sort by newest        |\n\n### Channel & User Data\n\n| Command                      | Description          |\n| ---------------------------- | -------------------- |\n| `channel`                    | Your channel info    |\n| `channel CHANNEL_ID`         | Specific channel     |\n| `subscriptions`              | Your subscriptions   |\n| `playlists`                  | Your playlists       |\n| `playlist-items PLAYLIST_ID` | Videos in a playlist |\n| `liked`                      | Your liked videos    |\n\n### Downloads (requires yt-dlp)\n\n| Command                       | Description           |\n| ----------------------------- | --------------------- |\n| `download VIDEO`              | Download best quality |\n| `download VIDEO -r 720p`      | Specific resolution   |\n| `download VIDEO -s en`        | Include subtitles     |\n| `download VIDEO -o ~/Videos`  | Custom output folder  |\n| `download-audio VIDEO`        | Audio only (MP3)      |\n| `download-audio VIDEO -f m4a` | Audio as M4A          |\n\n---\n\n## API Quota Costs\n\n| Operation     | Quota Cost | Notes                       |\n| ------------- | ---------- | --------------------------- |\n| Transcripts   | **0**      | Uses youtube-transcript-api |\n| Downloads     | **0**      | Uses yt-dlp                 |\n| Search        | 100        | Per request                 |\n| Video details | 1          | Per video                   |\n| Comments      | 1          | Per request                 |\n| Channel info  | 1-3        | Varies                      |\n\n**Daily free quota:** 10,000 units\n\n**Pro tip:** For research tasks, always start with transcripts — they're free and contain the most information.\n\n---\n\n## Setup\n\n### 1. Install dependencies\n\n```bash\nbrew install uv yt-dlp  # macOS\n# or\npip install uv && pip install yt-dlp  # other\n```\n\n### 2. Get YouTube API credentials\n\n1. Go to [Google Cloud Console](https://console.cloud.google.com/apis/credentials)\n2. Create a project (or select existing)\n3. Enable \"YouTube Data API v3\"\n4. Create OAuth 2.0 Client ID (Desktop app)\n5. Download JSON → save as `~/.config/youtube-skill/credentials.json`\n\n### 3. Authenticate\n\n```bash\nuv run youtube.py auth\n```\n\n---\n\n## Command Aliases\n\nFor faster typing:\n\n| Full              | Alias  |\n| ----------------- | ------ |\n| `transcript`      | `tr`   |\n| `transcript-list` | `trl`  |\n| `search`          | `s`    |\n| `video`           | `v`    |\n| `comments`        | `c`    |\n| `channel`         | `ch`   |\n| `subscriptions`   | `subs` |\n| `playlists`       | `pl`   |\n| `playlist-items`  | `pli`  |\n| `download`        | `dl`   |\n| `download-audio`  | `dla`  |\n\n---\n\n## Comparison with Other Tools\n\n| Feature          | YouTube Research Pro | kimtaeyoon83 | kevinwatt/yt-dlp | dannySubsense | kirbah |\n| ---------------- | -------------------- | ------------ | ---------------- | ------------- | ------ |\n| Free transcripts | ✅                   | ✅           | ❌               | ❌            | ❌     |\n| Search           | ✅                   | ❌           | ✅               | ✅            | ✅     |\n| Filtered search  | ✅                   | ❌           | ✅               | ❌            | ❌     |\n| Batch operations | ✅                   | ❌           | ❌               | ❌            | ✅     |\n| Comments         | ✅                   | ❌           | ❌               | ✅            | ✅     |\n| Downloads        | ✅                   | ❌           | ✅               | ❌            | ❌     |\n| Audio extraction | ✅                   | ❌           | ✅               | ❌            | ❌     |\n| JSON output      | ✅                   | ❌           | ❌               | ❌            | ✅     |\n| Multi-language   | ✅                   | ✅           | ✅               | ❌            | ❌     |\n| URL + ID support | ✅                   | ❌           | ✅               | ❌            | ❌     |\n\n**Result:** No other skill covers all these capabilities in one package.\n\n---\n\n## Use Cases\n\n### 📚 Research Assistant\n\n\"Summarize the key points from this conference talk\"\n→ Fetch transcript, analyze with LLM, extract insights\n\n### 🎓 Learning Helper\n\n\"Create study notes from this lecture series\"\n→ Batch fetch transcripts from playlist, synthesize content\n\n### 📰 News Monitoring\n\n\"What are people saying about [topic] this week?\"\n→ Search recent videos, extract transcripts, analyze trends\n\n### 🎵 Music/Podcast\n\n\"Download this interview as audio for my commute\"\n→ Extract audio, convert to MP3\n\n### 📊 Competitor Analysis\n\n\"How is [channel] performing?\"\n→ Get channel stats, analyze recent videos, track growth\n\n---\n\n## License\n\nMIT — use it, fork it, improve it.\n\n---\n\n_Built for the [OpenClaw](https://github.com/openclaw/openclaw) community._\n\nFile v4.2.2:_meta.json\n\n{\n  \"ownerId\": \"kn7623hrcwt6rg73a67xw3wyx580asdw\",\n  \"slug\": \"youtube-ultimate\",\n  \"version\": \"4.2.2\",\n  \"publishedAt\": 1771659267056\n}\n\nArchive v4.2.1: 4 files, 10776 bytes\n\nFiles: _meta.json (135b), README.md (9591b), scripts/youtube.py (25143b), SKILL.md (1674b)\n\nFile v4.2.1:SKILL.md\n\n---\nname: youtube-ultimate\nversion: 4.2.1\ndescription: \"Free transcripts, 4K downloads, and video exploration — zero API quotas burned.\"\nmetadata:\n  openclaw:\n    owner: kn7623hrcwt6rg73a67xw3wyx580asdw\n    category: media\n    tags:\n      - youtube\n      - transcripts\n      - video-download\n      - media\n      - offline\n    license: MIT\n    notes:\n      security: \"This skill invokes yt-dlp and youtube-transcript-api locally to fetch transcripts and download videos. No credentials stored, no API keys required, no external services beyond YouTube itself. All processing happens on your machine. No data is sent anywhere except standard YouTube HTTP requests.\"\n---\n\n# YouTube Ultimate\n\n**Your agent reads YouTube so you don't have to.** Pull transcripts, summarize videos, and extract knowledge — all without touching YouTube's API quota.\n\n## What It Does\n\n- **Free Transcripts** — Grab any video's transcript instantly. No API key, no quota, no billing surprises at 3 AM.\n- **4K Video Downloads** — Save videos locally for offline access, training data, or that flight where Wi-Fi costs more than the ticket.\n- **Video Exploration** — Search, browse, and drill into video details without rate-limit anxiety.\n\n## Why It Matters\n\nYouTube's API gives you 10,000 quota units per day. A single search costs 100. A transcript request? Not even supported. YouTube Ultimate sidesteps all of that. Your agent gets full access to video content while your quota counter stays at zero.\n\n*Clone it. Fork it. Break it. Make it yours.*\n\n👉 Explore the full project: [github.com/globalcaos/clawdbot-moltbot-openclaw](https://github.com/globalcaos/clawdbot-moltbot-openclaw)\n\nFile v4.2.1:README.md\n\n# 📺 YouTube Research Pro\n\n**The most comprehensive YouTube skill for AI agents.**\n\nExtract transcripts for FREE, search videos, analyze channels, download content — all from one unified interface.\n\n---\n\n## Why This Skill?\n\nWe analyzed **15+ YouTube MCP servers** and found that each one does _one thing_ well, but none does _everything_. So we built the skill we wished existed.\n\n| What Others Do                     | What We Do                                  |\n| ---------------------------------- | ------------------------------------------- |\n| Transcripts OR search OR downloads | **All three, unified**                      |\n| Burn API quota on transcripts      | **FREE transcripts** (zero quota)           |\n| Single video at a time             | **Batch operations** (50 videos)            |\n| Basic search                       | **Filtered search** (date, duration, order) |\n| Text output only                   | **JSON export** for pipelines               |\n\n### The Killer Feature: FREE Transcripts\n\nMost YouTube tools use the official YouTube Data API for transcripts, which costs **100 quota units per request**. With a daily limit of 10,000 units, you can only fetch ~100 transcripts per day.\n\n**We use `youtube-transcript-api`** — a library that extracts transcripts directly from YouTube's frontend, costing **zero API quota**. Fetch unlimited transcripts, every day.\n\n---\n\n## What Can Your Agent Do With This?\n\n### 🔍 Research & Analysis\n\n- Search YouTube with filters (date, duration, view count)\n- Get video details in batch (up to 50 at once)\n- Extract full transcripts for content analysis\n- Read comments to gauge audience sentiment\n\n### 📝 Content Extraction\n\n- Pull transcripts in any available language\n- Get timestamped transcripts for precise references\n- Export everything as JSON for further processing\n\n### 📥 Downloads\n\n- Download videos at any resolution\n- Extract audio only (podcasts, music, interviews)\n- Grab subtitles as separate files\n\n### 📊 Channel Intelligence\n\n- Analyze channel statistics\n- Track subscriber counts and view totals\n- List and explore playlists\n\n---\n\n## Quick Examples\n\n```bash\n# Get a video transcript (FREE - no API quota!)\nuv run youtube.py transcript dQw4w9WgXcQ\n\n# With timestamps\nuv run youtube.py transcript dQw4w9WgXcQ --timestamps\n\n# Search with filters\nuv run youtube.py search \"machine learning\" --duration long --order viewCount\n\n# Batch video details\nuv run youtube.py video id1 id2 id3 id4 id5 --json\n\n# Download audio as MP3\nuv run youtube.py download-audio VIDEO_ID -f mp3\n\n# Get top comments with replies\nuv run youtube.py comments VIDEO_ID --replies\n```\n\n---\n\n## Complete Command Reference\n\n### Transcripts (FREE - Zero API Quota)\n\n| Command                         | Description                          |\n| ------------------------------- | ------------------------------------ |\n| `transcript VIDEO`              | Extract transcript as plain text     |\n| `transcript VIDEO --timestamps` | Include [MM:SS] timestamps           |\n| `transcript VIDEO -l es,en`     | Prefer Spanish, fall back to English |\n| `transcript VIDEO --json`       | Output as JSON array                 |\n| `transcript-list VIDEO`         | List all available languages         |\n\n### Search & Discovery\n\n| Command                                               | Description                     |\n| ----------------------------------------------------- | ------------------------------- |\n| `search QUERY`                                        | Search YouTube videos           |\n| `search QUERY -l 20`                                  | Return 20 results (default: 10) |\n| `search QUERY --order date`                           | Sort by upload date             |\n| `search QUERY --order viewCount`                      | Sort by popularity              |\n| `search QUERY --duration short`                       | Under 4 minutes                 |\n| `search QUERY --duration long`                        | Over 20 minutes                 |\n| `search QUERY --published-after 2026-01-01T00:00:00Z` | Filter by date                  |\n\n### Video Information\n\n| Command             | Description              |\n| ------------------- | ------------------------ |\n| `video ID`          | Get video details        |\n| `video ID1 ID2 ID3` | Batch mode (up to 50)    |\n| `video ID --json`   | JSON output              |\n| `video ID -v`       | Include full description |\n\n### Comments\n\n| Command                       | Description           |\n| ----------------------------- | --------------------- |\n| `comments VIDEO`              | Get top comments      |\n| `comments VIDEO -l 50`        | Get 50 comments       |\n| `comments VIDEO --replies`    | Include reply threads |\n| `comments VIDEO --order time` | Sort by newest        |\n\n### Channel & User Data\n\n| Command                      | Description          |\n| ---------------------------- | -------------------- |\n| `channel`                    | Your channel info    |\n| `channel CHANNEL_ID`         | Specific channel     |\n| `subscriptions`              | Your subscriptions   |\n| `playlists`                  | Your playlists       |\n| `playlist-items PLAYLIST_ID` | Videos in a playlist |\n| `liked`                      | Your liked videos    |\n\n### Downloads (requires yt-dlp)\n\n| Command                       | Description           |\n| ----------------------------- | --------------------- |\n| `download VIDEO`              | Download best quality |\n| `download VIDEO -r 720p`      | Specific resolution   |\n| `download VIDEO -s en`        | Include subtitles     |\n| `download VIDEO -o ~/Videos`  | Custom output folder  |\n| `download-audio VIDEO`        | Audio only (MP3)      |\n| `download-audio VIDEO -f m4a` | Audio as M4A          |\n\n---\n\n## API Quota Costs\n\n| Operation     | Quota Cost | Notes                       |\n| ------------- | ---------- | --------------------------- |\n| Transcripts   | **0**      | Uses youtube-transcript-api |\n| Downloads     | **0**      | Uses yt-dlp                 |\n| Search        | 100        | Per request                 |\n| Video details | 1          | Per video                   |\n| Comments      | 1          | Per request                 |\n| Channel info  | 1-3        | Varies                      |\n\n**Daily free quota:** 10,000 units\n\n**Pro tip:** For research tasks, always start with transcripts — they're free and contain the most information.\n\n---\n\n## Setup\n\n### 1. Install dependencies\n\n```bash\nbrew install uv yt-dlp  # macOS\n# or\npip install uv && pip install yt-dlp  # other\n```\n\n### 2. Get YouTube API credentials\n\n1. Go to [Google Cloud Console](https://console.cloud.google.com/apis/credentials)\n2. Create a project (or select existing)\n3. Enable \"YouTube Data API v3\"\n4. Create OAuth 2.0 Client ID (Desktop app)\n5. Download JSON → save as `~/.config/youtube-skill/credentials.json`\n\n### 3. Authenticate\n\n```bash\nuv run youtube.py auth\n```\n\n---\n\n## Command Aliases\n\nFor faster typing:\n\n| Full              | Alias  |\n| ----------------- | ------ |\n| `transcript`      | `tr`   |\n| `transcript-list` | `trl`  |\n| `search`          | `s`    |\n| `video`           | `v`    |\n| `comments`        | `c`    |\n| `channel`         | `ch`   |\n| `subscriptions`   | `subs` |\n| `playlists`       | `pl`   |\n| `playlist-items`  | `pli`  |\n| `download`        | `dl`   |\n| `download-audio`  | `dla`  |\n\n---\n\n## Comparison with Other Tools\n\n| Feature          | YouTube Research Pro | kimtaeyoon83 | kevinwatt/yt-dlp | dannySubsense | kirbah |\n| ---------------- | -------------------- | ------------ | ---------------- | ------------- | ------ |\n| Free transcripts | ✅                   | ✅           | ❌               | ❌            | ❌     |\n| Search           | ✅                   | ❌           | ✅               | ✅            | ✅     |\n| Filtered search  | ✅                   | ❌           | ✅               | ❌            | ❌     |\n| Batch operations | ✅                   | ❌           | ❌               | ❌            | ✅     |\n| Comments         | ✅                   | ❌           | ❌               | ✅            | ✅     |\n| Downloads        | ✅                   | ❌           | ✅               | ❌            | ❌     |\n| Audio extraction | ✅                   | ❌           | ✅               | ❌            | ❌     |\n| JSON output      | ✅                   | ❌           | ❌               | ❌            | ✅     |\n| Multi-language   | ✅                   | ✅           | ✅               | ❌            | ❌     |\n| URL + ID support | ✅                   | ❌           | ✅               | ❌            | ❌     |\n\n**Result:** No other skill covers all these capabilities in one package.\n\n---\n\n## Use Cases\n\n### 📚 Research Assistant\n\n\"Summarize the key points from this conference talk\"\n→ Fetch transcript, analyze with LLM, extract insights\n\n### 🎓 Learning Helper\n\n\"Create study notes from this lecture series\"\n→ Batch fetch transcripts from playlist, synthesize content\n\n### 📰 News Monitoring\n\n\"What are people saying about [topic] this week?\"\n→ Search recent videos, extract transcripts, analyze trends\n\n### 🎵 Music/Podcast\n\n\"Download this interview as audio for my commute\"\n→ Extract audio, convert to MP3\n\n### 📊 Competitor Analysis\n\n\"How is [channel] performing?\"\n→ Get channel stats, analyze recent videos, track growth\n\n---\n\n## License\n\nMIT — use it, fork it, improve it.\n\n---\n\n_Built for the [OpenClaw](https://github.com/openclaw/openclaw) community._\n\nFile v4.2.1:_meta.json\n\n{\n  \"ownerId\": \"kn7623hrcwt6rg73a67xw3wyx580asdw\",\n  \"slug\": \"youtube-ultimate\",\n  \"version\": \"4.2.1\",\n  \"publishedAt\": 1771659210098\n}","readmeExcerpt":"Skill: YouTube Ultimate Owner: globalcaos Summary: Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Tags: latest:4.2.2 Version history: v4.2.2 | 2026-02-21T07:34:27.056Z | user Humor boost: 200/month upgrade line v4.2.1 | 2026-02-21T07:33:30.098Z | user Added notes.security transparency block v4.2.0 | 2026-02-21T07:05:24.628Z | user Marketia copy (Hook/Sell/Convert), metadata.openclaw b","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Get a video transcript (FREE - no API quota!)\nuv run youtube.py transcript dQw4w9WgXcQ\n\n# With timestamps\nuv run youtube.py transcript dQw4w9WgXcQ --timestamps\n\n# Search with filters\nuv run youtube.py search \"machine learning\" --duration long --order viewCount\n\n# Batch video details\nuv run youtube.py video id1 id2 id3 id4 id5 --json\n\n# Download audio as MP3\nuv run youtube.py download-audio VIDEO_ID -f mp3\n\n# Get top comments with replies\nuv run youtube.py comments VIDEO_ID --replies"},{"language":"bash","snippet":"brew install uv yt-dlp  # macOS\n# or\npip install uv && pip install yt-dlp  # other"},{"language":"bash","snippet":"uv run youtube.py auth"},{"language":"bash","snippet":"# Get a video transcript (FREE - no API quota!)\nuv run youtube.py transcript dQw4w9WgXcQ\n\n# With timestamps\nuv run youtube.py transcript dQw4w9WgXcQ --timestamps\n\n# Search with filters\nuv run youtube.py search \"machine learning\" --duration long --order viewCount\n\n# Batch video details\nuv run youtube.py video id1 id2 id3 id4 id5 --json\n\n# Download audio as MP3\nuv run youtube.py download-audio VIDEO_ID -f mp3\n\n# Get top comments with replies\nuv run youtube.py comments VIDEO_ID --replies"},{"language":"bash","snippet":"brew install uv yt-dlp  # macOS\n# or\npip install uv && pip install yt-dlp  # other"},{"language":"bash","snippet":"uv run youtube.py auth"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: youtube-ultimate\nversion: 4.2.2\ndescription: \"Free transcripts, 4K downloads, and video exploration — zero API quotas burned.\"\nmetadata:\n  openclaw:\n    owner: kn7623hrcwt6rg73a67xw3wyx580asdw\n    category: media\n    tags:\n      - youtube\n      - transcripts\n      - video-download\n      - media\n      - offline\n    license: MIT\n    notes:\n      security: \"This skill invokes yt-dlp and youtube-transcript-api locally to fetch transcripts and download videos. No credentials stored, no API keys required, no external services beyond YouTube itself. All processing happens on your machine. No data is sent anywhere except standard YouTube HTTP requests.\"\n---\n\n# YouTube Ultimate\n\n**Your agent reads YouTube so you don't have to.** Pull transcripts, summarize videos, and extract knowledge — all without touching YouTube's API quota.\n\n## What It Does\n\n- **Free Transcripts** — Grab any video's transcript instantly. No API key, no quota, no billing surprises at 3 AM. Won't burn through your free-tier quota fetching a single playlist, then suggest you upgrade to the $200/month plan like it's doing you a favor.\n- **4K Video Downloads** — Save videos locally for offline access, training data, or that flight where Wi-Fi costs more than the ticket.\n- **Video Exploration** — Search, browse, and drill into video details without rate-limit anxiety.\n\n## Why It Matters\n\nYouTube's API gives you 10,000 quota units per day. A single search costs 100. A transcript request? Not even supported. YouTube Ultimate sidesteps all of that. Your agent gets full access to video content while your quota counter stays at zero.\n\n*Clone it. Fork it. Break it. Make it yours.*\n\n👉 Explore the full project: [github.com/globalcaos/clawdbot-moltbot-openclaw](https://github.com/globalcaos/clawdbot-moltbot-openclaw)"},{"path":"README.md","content":"# 📺 YouTube Research Pro\n\n**The most comprehensive YouTube skill for AI agents.**\n\nExtract transcripts for FREE, search videos, analyze channels, download content — all from one unified interface.\n\n---\n\n## Why This Skill?\n\nWe analyzed **15+ YouTube MCP servers** and found that each one does _one thing_ well, but none does _everything_. So we built the skill we wished existed.\n\n| What Others Do                     | What We Do                                  |\n| ---------------------------------- | ------------------------------------------- |\n| Transcripts OR search OR downloads | **All three, unified**                      |\n| Burn API quota on transcripts      | **FREE transcripts** (zero quota)           |\n| Single video at a time             | **Batch operations** (50 videos)            |\n| Basic search                       | **Filtered search** (date, duration, order) |\n| Text output only                   | **JSON export** for pipelines               |\n\n### The Killer Feature: FREE Transcripts\n\nMost YouTube tools use the official YouTube Data API for transcripts, which costs **100 quota units per request**. With a daily limit of 10,000 units, you can only fetch ~100 transcripts per day.\n\n**We use `youtube-transcript-api`** — a library that extracts transcripts directly from YouTube's frontend, costing **zero API quota**. Fetch unlimited transcripts, every day.\n\n---\n\n## What Can Your Agent Do With This?\n\n### 🔍 Research & Analysis\n\n- Search YouTube with filters (date, duration, view count)\n- Get video details in batch (up to 50 at once)\n- Extract full transcripts for content analysis\n- Read comments to gauge audience sentiment\n\n### 📝 Content Extraction\n\n- Pull transcripts in any available language\n- Get timestamped transcripts for precise references\n- Export everything as JSON for further processing\n\n### 📥 Downloads\n\n- Download videos at any resolution\n- Extract audio only (podcasts, music, interviews)\n- Grab subtitles as separate files\n\n### 📊 Channel Intelligence\n\n- Analyze channel statistics\n- Track subscriber counts and view totals\n- List and explore playlists\n\n---\n\n## Quick Examples\n\n```bash\n# Get a video transcript (FREE - no API quota!)\nuv run youtube.py transcript dQw4w9WgXcQ\n\n# With timestamps\nuv run youtube.py transcript dQw4w9WgXcQ --timestamps\n\n# Search with filters\nuv run youtube.py search \"machine learning\" --duration long --order viewCount\n\n# Batch video details\nuv run youtube.py video id1 id2 id3 id4 id5 --json\n\n# Download audio as MP3\nuv run youtube.py download-audio VIDEO_ID -f mp3\n\n# Get top comments with replies\nuv run youtube.py comments VIDEO_ID --replies\n```\n\n---\n\n## Complete Command Reference\n\n### Transcripts (FREE - Zero API Quota)\n\n| Command                         | Description                          |\n| ------------------------------- | ------------------------------------ |\n| `transcript VIDEO`              | Extract transcript as plain text     |\n| `transcript VIDEO --timestamps` | Include [MM:SS] timesta"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7623hrcwt6rg73a67xw3wyx580asdw\",\n  \"slug\": \"youtube-ultimate\",\n  \"version\": \"4.2.2\",\n  \"publishedAt\": 1771659267056\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Skill: YouTube Ultimate Owner: globalcaos Summary: Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Tags: latest:4.2.2 Version history: v4.2.2 | 2026-02-21T07:34:27.056Z | user Humor boost: 200/month upgrade line v4.2.1 | 2026-02-21T07:33:30.098Z | user Added notes.security transparency block v4.2.0 | 2026-02-21T07:05:24.628Z | user Marketia copy (Hook/Sell/Convert), metadata.openclaw b","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":987,"uniquenessScore":57,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:52:41.545Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}