Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when YouTube is relevant: pasted video links or IDs, @handles, quick video lookups, summaries, channel latest uploads, topic search, or any request involving YouTube content — even if YouTube is not mentioned explicitly. Covers transcripts, search, and channel latest. Not for uploads or account management.
.claude/skills/zeropointrepo-yt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -42% | 0% |
Quick YouTube lookup via TranscriptAPI.com.
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
httpGET https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=10 Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
| Param | Default | Values | | ------- | ------- | ---------------------- | | q | — | 1-200 chars (required) | | type | video | video, channel | | limit | 20 | 1-50 |
httpGET https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Returns last 15 videos with exact view counts and publish dates. Accepts @handle, channel URL, or UC... ID.
httpGET https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TED Authorization: Bearer $TRANSCRIPT_API_KEY User-Agent: YourAgent/1.0
Use to convert @handle to UC... channel ID.
| 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 | No captions or resource doesn't exist | | 408 | Timeout | Retry once |
Free tier: 100 credits. Search and transcript cost 1 credit. Channel latest and resolve are free.
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-01 | fail→fail | 12,067 | 9,810 | -19% | 1 | 1 | 0% | 2,615 | 1,486 | -43% | 0 | 0 | — |
case-02 | fail→pass | 8,502 | 8,039 | -5% | 1 | 1 | 0% | 1,317 | 1,425 | +8% | 0 | 0 | — |
case-03 | fail→fail | 3,609 | 12,856 | +256% | 1 | 1 | 0% | 479 | 2,243 | +368% | 0 | 0 | — |
case-04 | pass→pass | 8,442 | 4,936 | -42% | 1 | 1 | 0% | 1,504 | 1,687 | +12% | 0 | 0 | — |
case-05 | pass→pass | 12,360 | 8,603 | -30% | 1 | 1 | 0% | 2,262 | 2,287 | +1% | 0 | 0 | — |
case-06 | pass→pass | 2,096 | 1,486 | -29% | 1 | 1 | 0% | 316 | 983 | +211% | 0 | 0 | — |
case-07 | pass→pass | 10,823 | 7,376 | -32% | 1 | 1 | 0% | 1,805 | 2,006 | +11% | 0 | 0 | — |
case-08 | pass→pass | 14,780 | 4,076 | -72% | 1 | 1 | 0% | 2,445 | 1,390 | -43% | 0 | 0 | — |
case-09 | pass→pass | 9,969 | 4,136 | -59% | 1 | 1 | 0% | 1,759 | 1,424 | -19% | 0 | 0 | — |
case-10 | pass→pass | 11,616 | 3,739 | -68% | 1 | 1 | 0% | 2,222 | 1,473 | -34% | 0 | 0 | — |
case-11 | fail→pass | 10,748 | 2,193 | -80% | 1 | 1 | 0% | 1,794 | 1,145 | -36% | 0 | 0 | — |
case-12 | pass→pass | 10,008 | 3,710 | -63% | 1 | 1 | 0% | 1,799 | 1,474 | -18% | 0 | 0 | — |
case-13 | fail→pass | 7,106 | 2,940 | -59% | 1 | 1 | 0% | 1,181 | 1,211 | +3% | 0 | 0 | — |
case-14 | fail→pass | 7,147 | 1,772 | -75% | 1 | 1 | 0% | 902 | 977 | +8% | 0 | 0 | — |
case-15 | pass→pass | 8,165 | 1,874 | -77% | 1 | 1 | 0% | 1,230 | 1,032 | -16% | 0 | 0 | — |
case-16 | fail→pass | 9,715 | 2,247 | -77% | 1 | 1 | 0% | 1,726 | 1,000 | -42% | 0 | 0 | — |
case-17 | fail→pass | 7,637 | 2,058 | -73% | 1 | 1 | 0% | 1,166 | 1,030 | -12% | 0 | 0 | — |
case-18 | fail→pass | 8,322 | 1,582 | -81% | 1 | 1 | 0% | 1,372 | 998 | -27% | 0 | 0 | — |
case-19 | pass→pass | 8,339 | 2,672 | -68% | 1 | 1 | 0% | 1,357 | 1,154 | -15% | 0 | 0 | — |
case-20 | pass→pass | 7,343 | 2,825 | -62% | 1 | 1 | 0% | 1,235 | 1,138 | -8% | 0 | 0 | — |
case-21 | fail→pass | 2,261 | 1,260 | -44% | 1 | 1 | 0% | 302 | 916 | +203% | 0 | 0 | — |
case-22 | fail→pass | 7,018 | 1,752 | -75% | 1 | 1 | 0% | 1,010 | 971 | -4% | 0 | 0 | — |
case-23 | fail→pass | 7,420 | 2,037 | -73% | 1 | 1 | 0% | 1,179 | 995 | -16% | 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 21 counted toward the lift figure. The other 2 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 +43 percentage points is the difference between those two pass rates over the 21 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.