Clipmaster
Turn any long video (YouTube URL or direct video URL) into scored, captioned, ready-to-publish vertical clips using the ClipMaster API. Use when the user wants to clip a video, repurpose long-form content into Shorts/Reels/TikToks, extract the best moments from a podcast/webinar/stream, or export clips in 9:16, 1:1, or 16:9.From its SKILL.md
npx -y skills add clipmasterapp/skills --skill clipmasterAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.8 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it
ClipMaster — video → scored vertical clips
ClipMaster (https://clipmasterapp.com) transcribes a long video, finds the strongest moments with AI, scores each candidate, and renders captioned vertical clips. This skill drives it end-to-end over the public API.
Setup (once)
- The user needs a ClipMaster account on the Pro or Business plan (API access is plan-gated).
- Create an API key at https://clipmasterapp.com/api-keys — keys start with
cm_, shown once. - Expect the key in the
CLIPMASTER_API_KEYenvironment variable. If it is not set, ask the user for it — never guess or hardcode one. - Every request:
Authorization: Bearer $CLIPMASTER_API_KEY, base URLhttps://clipmasterapp.com. - Jobs need a
projectId. Ask the user for one from their dashboard (Projects page). A project pins the playbook / industry overlay / output template so clips match their brand.
All responses use the envelope { "ok": true, "data": ... } or { "ok": false, "error": "..." }.
Workflow: clip a video
1. Create clips (one call does import + transcribe + score)
curl -X POST https://clipmasterapp.com/api/clip \
-H "Authorization: Bearer $CLIPMASTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"projectId": "<project-id>",
"source": "url",
"sourceUrl": "https://www.youtube.com/watch?v=...",
"count": 8,
"minDurationSec": 15,
"maxDurationSec": 60
}'
Fields:
source:"youtube"or"url"withsourceUrl(YouTube link or direct video URL), or"upload"with astorageKeyfrom a prior in-app upload.count: 1–20 clip candidates (default 8).minDurationSec5–120 /maxDurationSec10–180.transcribeOnly: true→ returns just the transcript (useful for show notes, chapters, quotes).
The call is synchronous and can take a few minutes for long videos — use a generous HTTP
timeout (≥ 10 min). The response's data.clips array contains candidates, each with
id, title, startSec, endSec, a virality score, and reasoning explaining why the
moment was chosen. Present the top candidates to the user with scores and reasoning.
2. (Optional) Adjust a clip
curl -X PATCH https://clipmasterapp.com/api/clip \
-H "Authorization: Bearer $CLIPMASTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"clipId": "<clip-id>", "title": "New hook title", "startSec": 512.4, "endSec": 561.0, "captionPreset": "karaoke"}'
captionPreset: karaoke | word-pop | line | minimal.
3. Export
curl -X PATCH https://clipmasterapp.com/api/clip \
-H "Authorization: Bearer $CLIPMASTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"clipId": "<clip-id>", "formats": ["9:16"]}'
Formats: "9:16" (Shorts/Reels/TikTok), "1:1", "16:9". Exports render asynchronously.
4. Poll until ready, then download
curl -H "Authorization: Bearer $CLIPMASTER_API_KEY" \
"https://clipmasterapp.com/api/clip?clipId=<clip-id>"
Response: data.exports[] with format, status (queued | rendering | ready | failed),
and — when ready — a time-limited downloadUrl (valid 1 hour). Poll every 15–30 s.
Download promptly once ready.
Choosing a playbook (when creating projects for the user)
| Content | playbook id |
|---|---|
| Podcast / interview | podcasts_interviews |
| Solo opinion / expert take | talking_head |
| Webinar / event recording | webinar_event |
| Tutorial / course | education_training |
| Product demo / SaaS walkthrough | software_product_demo |
| Marketing / SEO / AI-search content | marketing_seo_geo |
| Gaming footage | gaming_gameplay |
| Livestream VOD | livestream_vod |
Errors & limits
401— missing/invalid/revoked key. Ask the user to checkCLIPMASTER_API_KEY.402— insufficient credits. Tell the user to top up at https://clipmasterapp.com/pricing.403— key valid but plan lacks API access (needs Pro or Business).422— import/transcription failed (bad URL, private video, unsupported source). Report theerrormessage verbatim.429— rate limit (20 clip jobs/hour). Wait and retry; don't hammer.- Never loop retries on 4xx other than 429. Clip jobs spend the user's credits — confirm before batch-processing many videos.
Rights reminder
Only clip videos the user owns or has permission to repurpose. If asked to clip someone else's content, remind the user they need the creator's permission.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most video audio skills give in ~1.2k tokens
Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07
- Read individual rule files for detailed explanationsin 21 of 622, across 10 files
- Render final videoin 13 of 622, across 6 files
- Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
- Use this skill when dealing with Remotion codein 11 of 622, across 4 files
- Save generated audio to a WAV filein 11 of 622, across 4 files
- Handle conversion errors gracefullyin 10 of 622, across 6 files
- Add captions to videos alwaysin 10 of 622, across 4 files
- Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
- Do not skip pipeline layersin 9 of 622, across 3 files
- Do not make one tool do everythingin 9 of 622, across 3 files
- Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
- Never ask the user to paste their full API keyin 9 of 622, across 3 files
Said here and by no other author read
- Ask the user for a project ID
- Send clip creation requests to the API
- Use a ten-minute HTTP timeout
- Present top clip candidates to the user
- Adjust clips using PATCH requests
- Poll the API for export status
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.