cut-spec
Use before every set_cuts call. How a cut spec is built - removals, pause trimming, bleeps, blur boxes, zooms and cutaways - in source seconds, with media named by assetId only.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-06
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- cut-spec
- description
- Use before every set_cuts call. How a cut spec is built - removals, pause trimming, bleeps, blur boxes, zooms and cutaways - in source seconds, with media named by assetId only.
03 SKILL.md 正文
<!-- Created by The Angelo Umali. -->
Cut spec
A cut spec describes the full edit as changes to one joined source. set_cuts replaces the whole spec, so always send every
field you want to keep. To change part of a stored spec, start from read_spec (kind: "cuts") and send it back with
only that part changed.
Shape
schemaVersion: 1,sourceAssetId(the joined source fromingest),durationS, andfpsas a rational ({ num: 30000, den: 1001 }, never29.97: frame identity depends on it).removals: spans{ at, end, reason }in source seconds,endafterat. Media is named byassetIdonly; a spec with a path in it is rejected.- A removal that comes from
propose_cutscarriesfromCandidatewith the candidate id. Only ids the user approved pass; never reuse a rejected one. pin: truekeeps a removal exactly where you put it. Without it the engine snaps each edge up to 0.15 s to the quietest point nearby, which is almost always what you want.
Pauses
- Prefer
trimPausesover hand-written pause removals:{ thresholdDb, minS, keepS, exclude }. A start point isthresholdDb: -35,minS: 0.6,keepS: 0.15. - Put deliberate beats (after a punchline, before a reveal) in
exclude. set_cutsreportskeptSbefore pause trimming; the rendered edit will be a little shorter.
Other fields
bleeps: swears to mask,{ at, end, x, y }. Place them from the words of an isolated window around the swear, not from long-form transcript times, which drift by about half a second.blurBoxes: on the 1080×1920 grid, inside the frame. Blur other people's private details (their faces in photos, names, addresses, phone numbers, emails). Do not blur the creator's own family or home unless the user asks, and then exactly as asked. A blur box sits still on the frame, so its span must not overlap azoomswindow: the picture would slide under it.zooms: a preset (snap,push,reveal,through-out,through-in,portal,lean) over a span.leanis a restrained 5 % push for where the face is already close. Jump cuts already get an alternating punch-in; add zooms for emphasis only. Every preset is animated: whenget_capabilitiesreportszoomExpr: false, leavezoomsempty and let the jump-cut punch-ins carry the emphasis.cutaways: a title card{ title, sub?, style? }over a span, for a chapter change.faceCamRangesandmatteRanges: spans where the speaker's face is the subject. A house-theme cue withdepth: "behind"draws under the person only inside amatteRangeswindow, so give every behind cue one that covers it. Learning kinds have nodepth: their text always stays in front.focus: rack focus{ at, end, amount }(1–40 px of blur on the room behind him) where he turns inward. Each focus window is matted for you; nomatteRangesneeded.grade:"house"(the default) or"learning"for the v2 Live Motion look.follow:"speaker"frames every kept second without areframeswindow on whoever is speaking (learning theme).blurFaces: the user's answer to "are other people's faces blurred?":"others"blurs every face but the creator's, a guest's even while they speak (the camera still follows them), following every reframe and zoom, and the covers too;"none"leaves them. Ask before the first render: a learning edit of footage with anyone besides the creator does not render without it.places:[{ name, lon, lat }]for places the footage visits that its own GPS cannot prove (ask the user); each needs arouteMappin. Never home.reframes: for a square or landscape source,{ at, end, cx, cy?, scale? }windows that crop a 9:16 slice of the picture (cx/cyare shares of the picture bandframe_facesreports). Cover every kept span, move only on a cut.music: an original bed under his voice,{ bpm?, sections: [{ at, kind, energy? }] }withkindone ofcold,intro,chapterandoutro; sections start at 0 and are in source seconds.
Before you call set_cuts
- Every span sits inside
0 … durationS, and removals do not cut a word in half (checkread_transcriptwithformat: "words"around each edge). - The opening line is the hook you agreed with the user.
- Then call
validate_specand fix whatever it reports.
Hands to next: a stored CutSpec version → style-rules, then cues (the cue sheet) and captions.
04 同仓库更多 Skills
v2-vlog
Use for every edit whose project theme is "learning" (v2 Live Motion), before the cut spec, before the first cue and before calling the edit finished. The rules, the technique menu, the brand and the bar a learning-vlog edit must clear.
style-rules
Use before choosing any card, caption look, sound or intro, and whenever the user's style rules or a style preset seem to conflict with what the edit needs.
reels
Use before set_reel, when choosing or changing the Reels cut, or when set_reel reports dropped cues.
qc-gates
Use when render_master has finished, before any export, or when qc_master or check_motion reports a failed check.
edit-director
Use at the start of every edit, before choosing an opening or hook, before calling the edit finished, and whenever you are unsure what comes next in turning a project's clips into a short-form edit with the studio tools.
cues
Use before list_cue_kinds, add_cue, update_cue or remove_cue, and when a cue fails its anchor or width check, overlaps another card, or the screen feels crowded.