Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, first looks, or anything where video content is fresher or richer than text search. Covers transcripts, video/channel search, channel browsing, playlists, and within-channel search. Not for uploads
.claude/skills/zeropointrepo-youtube-full/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-23 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 294% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 19% | 0% |
Complete YouTube toolkit via TranscriptAPI.com. Everything in one skill.
If $TRANSCRIPT_API_KEY is not set, read references/auth-setup.md and follow the instructions there to get and store the key.
Every request needs two headers:
Bearer $TRANSCRIPT_API_KEYHermesAgent/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.Full OpenAPI spec: transcriptapi.com/openapi.json — consult this for the latest parameters and schemas.
httpGET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=true Authorization: Bearer $TRANSCRIPT_API_KEY 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):
json{ "video_id": "dQw4w9WgXcQ", "language": "en", "transcript": [{ "text": "...", "start": 18.0, "duration": 3.5 }], "metadata": { "title": "...", "author_name": "...", "author_url": "..." } }
http# Videos GET https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=20 Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0 # Channels GET https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=channel&limit=10 Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
| Param | Required | Default | Validation | | ------- | -------- | ------- | ------------------ | | q | yes | — | 1-200 chars | | type | no | video | video, channel | | limit | no | 20 | 1-50 |
All channel endpoints accept channel — an @handle, channel URL, or UC... channel ID. No need to resolve first.
httpGET https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TED Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Response: {"channel_id": "UC...", "resolved_from": "@TED"}
httpGET https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Returns exact viewCount and ISO published timestamps.
http# First page (100 videos) GET https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0 # Next pages GET https://transcriptapi.com/api/v2/youtube/channel/videos?continuation=TOKEN Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Provide exactly one of channel or continuation. Response includes continuation_token and has_more.
httpGET https://transcriptapi.com/api/v2/youtube/channel/search?channel=@TED&q=QUERY&limit=30 Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Accepts playlist — a YouTube playlist URL or playlist ID.
http# First page GET https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist=PL_ID Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0 # Next pages GET https://transcriptapi.com/api/v2/youtube/playlist/videos?continuation=TOKEN Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Valid ID prefixes: PL, UU, LL, FL, OL. Response includes playlist_info, results, continuation_token, has_more.
| Endpoint | Cost | | --------------- | -------- | | transcript | 1 | | search | 1 | | channel/resolve | free | | channel/latest | free | | channel/videos | 1/page | | channel/search | 1 | | playlist/videos | 1/page |
| 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 |
| 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 |
Research workflow: search → pick videos → fetch transcripts
http# 1. Search GET https://transcriptapi.com/api/v2/youtube/search?q=machine+learning+explained&limit=5 Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0 # 2. Transcript GET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_ID&format=text&include_timestamp=true&send_metadata=true Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Channel monitoring: latest (free) → transcript
http# 1. Latest uploads (free — pass @handle directly) GET https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0 # 2. Transcript of latest GET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_ID&format=text&include_timestamp=true&send_metadata=true Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Free tier: 100 credits, 300 req/min. Starter ($5/mo): 1,000 credits.
Every request in this file as a ready-to-run one-liner: references/curl-examples.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | fail→pass | 11,950 | 6,464 | -46% | 1 | 1 | 0% | 2,279 | 3,235 | +42% | 0 | 0 | — |
case-01 | fail→fail | 11,193 | 8,317 | -26% | 1 | 1 | 0% | 2,520 | 2,451 | -3% | 0 | 0 | — |
case-02 | fail→fail | 4,290 | 7,726 | +80% | 1 | 1 | 0% | 598 | 2,432 | +307% | 0 | 0 | — |
case-03 | fail→fail | 13,020 | 6,709 | -48% | 1 | 1 | 0% | 1,983 | 2,356 | +19% | 0 | 0 | — |
case-04 | fail→pass | 10,196 | 5,119 | -50% | 1 | 1 | 0% | 1,527 | 2,883 | +89% | 0 | 0 | — |
case-05 | fail→pass | 9,639 | 2,795 | -71% | 1 | 1 | 0% | 1,492 | 2,435 | +63% | 0 | 0 | — |
case-06 | pass→pass | 10,567 | 2,754 | -74% | 1 | 1 | 0% | 1,607 | 2,412 | +50% | 0 | 0 | — |
case-07 | fail→pass | 4,416 | 3,222 | -27% | 1 | 1 | 0% | 643 | 2,531 | +294% | 0 | 0 | — |
case-08 | pass→pass | 5,028 | 2,047 | -59% | 1 | 1 | 0% | 738 | 2,217 | +200% | 0 | 0 | — |
case-09 | fail→pass | 12,723 | 3,359 | -74% | 1 | 1 | 0% | 2,123 | 2,533 | +19% | 0 | 0 | — |
case-10 | fail→pass | 10,098 | 3,283 | -67% | 1 | 1 | 0% | 1,623 | 2,577 | +59% | 0 | 0 | — |
case-11 | fail→pass | 9,676 | 2,282 | -76% | 1 | 1 | 0% | 1,499 | 2,322 | +55% | 0 | 0 | — |
case-12 | pass→pass | 9,411 | 3,352 | -64% | 1 | 1 | 0% | 1,471 | 2,616 | +78% | 0 | 0 | — |
case-13 | fail→pass | 10,973 | 1,902 | -83% | 1 | 1 | 0% | 1,643 | 2,218 | +35% | 0 | 0 | — |
case-14 | fail→pass | 5,574 | 1,956 | -65% | 1 | 1 | 0% | 836 | 2,316 | +177% | 0 | 0 | — |
case-15 | pass→pass | 5,925 | 1,904 | -68% | 1 | 1 | 0% | 981 | 2,318 | +136% | 0 | 0 | — |
case-16 | fail→pass | 11,462 | 2,309 | -80% | 1 | 1 | 0% | 1,780 | 2,316 | +30% | 0 | 0 | — |
case-17 | pass→pass | 7,264 | 2,271 | -69% | 1 | 1 | 0% | 1,135 | 2,350 | +107% | 0 | 0 | — |
case-18 | fail→pass | 7,054 | 1,858 | -74% | 1 | 1 | 0% | 906 | 2,265 | +150% | 0 | 0 | — |
case-19 | pass→pass | 4,068 | 1,809 | -56% | 1 | 1 | 0% | 579 | 2,220 | +283% | 0 | 0 | — |
case-20 | fail→pass | 2,707 | 2,068 | -24% | 1 | 1 | 0% | 355 | 2,268 | +539% | 0 | 0 | — |
case-21 | fail→fail | 12,289 | 7,694 | -37% | 1 | 1 | 0% | 2,096 | 3,394 | +62% | 0 | 0 | — |
case-22 | fail→pass | 8,719 | 5,648 | -35% | 1 | 1 | 0% | 1,512 | 2,951 | +95% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 20 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +57 percentage points is the difference between those two pass rates over the 20 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.