Mira Premiere
The user's Premiere Pro is the edit bay. The tools that reach it:
adobe_status — is it there, which app, the open project, the active sequence.
adobe_command — typed timeline steps, each with a JSON input:
get_timeline — tracks with every clip (start, end, name, mediaPath, enabled, selected), fps,
frame size, in/out and the playhead. Read it before every change and after it.
assemble_edit {name?, clips, width?, height?} — a NEW sequence matched to the first clip's
footage, reframed when asked (1080x1920 for 9:16), the whole cut plan placed gaplessly, every
clip fitted to the frame. The plan is the argument: once you have the in/out times, call it.
apply_cut_plan {clips, at?} — the same plan onto the active sequence, from at or its end.
apply_cuts {cuts:[{s,e}], mode} — remove sequence ranges on every unlocked track; ripple
closes the gaps, lift leaves them.
switch_multicam {segments:[{s,e,track}]} — inside each range only that video track stays on.
add_markers, create_subclips, import_captions {path|url}, set_sequence_format,
fit_all_video {punch?}, open_sequence, set_playhead, save_project.
- Sound:
audio_gaps, recompact_audio {track, min_pause, max_pause} (pauses clamped, picture
follows), music_bed {url|path, track} (trimmed, tiled, faded, ducked in one call),
duck_music, set_audio_level, audio_fade.
- Titles and delivery:
import_mogrt {url|path} (returns its text fields), set_mogrt_text,
export_sequence (H.264 mp4 of the sequence, vertical when the sequence is).
adobe_beat_markers {track, clip} — tempo, bars and drops of the music clip as sequence markers.
adobe_contact_sheet (up to 12 frames with timecodes) and adobe_export_frame at time.
adobe_import_generation — a finished Mira generation (b-roll, music, a voice) into the project.
adobe_place_element — Mira Elements media and sounds (no templates in Premiere).
adobe_execute_script — ExtendScript for anything the commands do not cover.
A clip in a cut plan is {source, in, out, track?, punch?, marker?}: source is a mediaPath from
get_timeline, a project item name or a local file; url instead of source downloads it first;
in and out are SOURCE seconds; track is the 0-based video track (linked audio follows).
The words come from Mira, not from Premiere: transcribe_video (word timestamps, speakers, an .srt)
and analyze_transcript (clean_cut silences and multicam speaker turns are free; clipper,
seo and chapters cost a flat fee). Footage that lives only on the user's disk goes up first with
create_upload (kind video); only clients with file access can do that.
Not connected (adobe_status.connected == false): say how to switch the bridge on in the Mira panel
(Bridge MCP → Connect) and stop. Do not retry in a loop.
When to use
- A podcast, interview or talking head: silences out, fluffs out, one take per line, captions.
- Two or more cameras of one conversation: the angle follows whoever speaks.
- Highlights for Reels, TikTok or Shorts from a long recording, reframed to 9:16.
- A rough cut assembled from a list of shots, or a b-roll montage cut to a track.
Doctrine
Name the job before the first cut. Cleanup keeps every line and only removes air and fluffs.
Highlight keeps whole thoughts and drops the rest. Reorder moves whole answers. A target script
rebuilds a given text from takes. The cut points differ for each; ask when the brief is unclear.
Speech is cut on sentences, never on a clock. Every cut point in talking footage comes from the
transcript: a sentence or phrase boundary, with the breath going to the line that follows it.
Without a transcript, keep takes whole. Beat-driven cutting is for b-roll and music only.
One take per line. When a speaker repeats a line, keep the last complete take unless an earlier
one carries something the last lacks. Never splice half of one take to half of another into a
sentence nobody said.
Lock the voice first. Cut the dialogue, play it through, then lay b-roll, then titles, then
music, then captions. Anything placed before the voice is locked drifts out of sync on the next
trim.
Every seam has a reason. Cut on action, a jump cut only in a run of three or more, a hold for a
number or a quote, a match or a wipe by an object. Most seams are plain cuts; transitions are rare.
Look at the timeline, not at the tool's answer. After every change: get_timeline again (the
user may have edited between turns) and an adobe_contact_sheet at the cuts you made. A successful
call is not proof of a good edit.
The numbers (air, pauses, fillers, pace, loudness, the transition ladder) are in
references/editing.md. Read it before the first cut.
Workflow
adobe_status → adobe_command get_timeline. Say what is there: sequences, tracks, length.
- Ask the job and the platform (see Interview), one question at a time.
- Speech:
create_upload the source if needed → transcribe_video → analyze_transcript clean_cut (or multicam, clipper) → choose the cut points on sentence boundaries from the
words, not only the silences.
- Cleanup of the active sequence:
apply_cuts with ripple. A new reel or a reordered cut:
assemble_edit with the plan (width 1080, height 1920 for vertical).
- Several cameras:
switch_multicam with the speaker turns mapped to tracks; hold an angle at least
two seconds unless the reaction is the point.
adobe_contact_sheet at each cut (cut-0.2, cut, cut+0.2) and at the start; fix what jumps.
- Speech pauses:
audio_gaps, then recompact_audio (0.25-1.0 s by default). B-roll with
adobe_import_generation; montage cuts on the bars from adobe_beat_markers. Music last:
music_bed with the track (from add_soundtrack or generate_audio), ducked under the voice.
Titles with import_mogrt + set_mogrt_text, captions with import_captions, chapters with
add_markers.
export_sequence when the user wants the file (saved to ~/Movies/Mira unless they name a path),
then look at it. save_project only when the user asks.
Interview
Ask only what the brief leaves open:
- The job: cleanup, highlights, reorder or a given script.
- The platform and shape: 16:9 long form, or 9:16 for Reels, TikTok or Shorts, and the length.
- What must stay: lines, names, a call to action, the speakers' order.
- Music: none, the user's track, or one made with Mira.
- Captions: none, a caption track, or burned in.
Checklist
- Every speech cut sits on a sentence or phrase boundary; no word is clipped.
- No more than the allowed air at the head and tail of each line; pauses within the ranges.
- One take per repeated line; no spliced sentences.
- The hook lands in the first two seconds of a short.
- Music sits under the voice, not on top of it; the mix is checked at the loudest line.
- A contact sheet at every cut has been looked at; nothing is black between clips.
- The project is saved only when the user asked.
AI Film Studio. An Editor cut opens as a sequence with film_edit_open_in_app, takes come in with film_open_in_app, adobe_command export_sequence with film_project_id returns the edit to the project's bin - see film-studio.md in mira-generate.
1---2name: mira-premiere3description: >-4 Edit in the user's own Premiere Pro through the Mira MCP: read the timeline, cut talking footage on5 whole sentences from a transcript, take out silences, switch multicam angles by speaker, assemble a6 rough cut or a vertical reel from a cut plan in one call, mark chapters, add captions, then check7 the result frame by frame. Use it when the user says "edit this in Premiere", "смонтируй в8 премьере", "вырежи паузы", "собери рилс из интервью", "make a rough cut", "cut the podcast", or when9 adobe_status reports a connected Premiere Pro. Requires the Mira for Adobe panel with the bridge10 switched on. NOT for motion design (mira-after-effects) or for generating new footage11 (mira-generate).12license: MIT13metadata:14 source: https://skillmd.com/skills/global-ai-group-inc/mira-premiere15 version: "0.2.0"16---1718# Mira Premiere1920The user's Premiere Pro is the edit bay. The tools that reach it:2122- `adobe_status` — is it there, which app, the open project, the active sequence.23- `adobe_command` — typed timeline steps, each with a JSON input:24 - `get_timeline` — tracks with every clip (start, end, name, mediaPath, enabled, selected), fps,25 frame size, in/out and the playhead. Read it before every change and after it.26 - `assemble_edit {name?, clips, width?, height?}` — a NEW sequence matched to the first clip's27 footage, reframed when asked (1080x1920 for 9:16), the whole cut plan placed gaplessly, every28 clip fitted to the frame. The plan is the argument: once you have the in/out times, call it.29 - `apply_cut_plan {clips, at?}` — the same plan onto the active sequence, from `at` or its end.30 - `apply_cuts {cuts:[{s,e}], mode}` — remove sequence ranges on every unlocked track; `ripple`31 closes the gaps, `lift` leaves them.32 - `switch_multicam {segments:[{s,e,track}]}` — inside each range only that video track stays on.33 - `add_markers`, `create_subclips`, `import_captions {path|url}`, `set_sequence_format`,34 `fit_all_video {punch?}`, `open_sequence`, `set_playhead`, `save_project`.35 - Sound: `audio_gaps`, `recompact_audio {track, min_pause, max_pause}` (pauses clamped, picture36 follows), `music_bed {url|path, track}` (trimmed, tiled, faded, ducked in one call),37 `duck_music`, `set_audio_level`, `audio_fade`.38 - Titles and delivery: `import_mogrt {url|path}` (returns its text fields), `set_mogrt_text`,39 `export_sequence` (H.264 mp4 of the sequence, vertical when the sequence is).40- `adobe_beat_markers {track, clip}` — tempo, bars and drops of the music clip as sequence markers.41- `adobe_contact_sheet` (up to 12 frames with timecodes) and `adobe_export_frame` at `time`.42- `adobe_import_generation` — a finished Mira generation (b-roll, music, a voice) into the project.43- `adobe_place_element` — Mira Elements media and sounds (no templates in Premiere).44- `adobe_execute_script` — ExtendScript for anything the commands do not cover.4546A clip in a cut plan is `{source, in, out, track?, punch?, marker?}`: `source` is a `mediaPath` from47`get_timeline`, a project item name or a local file; `url` instead of `source` downloads it first;48`in` and `out` are SOURCE seconds; `track` is the 0-based video track (linked audio follows).4950The words come from Mira, not from Premiere: `transcribe_video` (word timestamps, speakers, an .srt)51and `analyze_transcript` (`clean_cut` silences and `multicam` speaker turns are free; `clipper`,52`seo` and `chapters` cost a flat fee). Footage that lives only on the user's disk goes up first with53`create_upload` (kind `video`); only clients with file access can do that.5455Not connected (`adobe_status.connected == false`): say how to switch the bridge on in the Mira panel56(Bridge MCP → Connect) and stop. Do not retry in a loop.5758## When to use5960- A podcast, interview or talking head: silences out, fluffs out, one take per line, captions.61- Two or more cameras of one conversation: the angle follows whoever speaks.62- Highlights for Reels, TikTok or Shorts from a long recording, reframed to 9:16.63- A rough cut assembled from a list of shots, or a b-roll montage cut to a track.6465## Doctrine6667**Name the job before the first cut.** Cleanup keeps every line and only removes air and fluffs.68Highlight keeps whole thoughts and drops the rest. Reorder moves whole answers. A target script69rebuilds a given text from takes. The cut points differ for each; ask when the brief is unclear.7071**Speech is cut on sentences, never on a clock.** Every cut point in talking footage comes from the72transcript: a sentence or phrase boundary, with the breath going to the line that follows it.73Without a transcript, keep takes whole. Beat-driven cutting is for b-roll and music only.7475**One take per line.** When a speaker repeats a line, keep the last complete take unless an earlier76one carries something the last lacks. Never splice half of one take to half of another into a77sentence nobody said.7879**Lock the voice first.** Cut the dialogue, play it through, then lay b-roll, then titles, then80music, then captions. Anything placed before the voice is locked drifts out of sync on the next81trim.8283**Every seam has a reason.** Cut on action, a jump cut only in a run of three or more, a hold for a84number or a quote, a match or a wipe by an object. Most seams are plain cuts; transitions are rare.8586**Look at the timeline, not at the tool's answer.** After every change: `get_timeline` again (the87user may have edited between turns) and an `adobe_contact_sheet` at the cuts you made. A successful88call is not proof of a good edit.8990The numbers (air, pauses, fillers, pace, loudness, the transition ladder) are in91`references/editing.md`. Read it before the first cut.9293## Workflow94951. `adobe_status` → `adobe_command get_timeline`. Say what is there: sequences, tracks, length.962. Ask the job and the platform (see Interview), one question at a time.973. Speech: `create_upload` the source if needed → `transcribe_video` → `analyze_transcript98 clean_cut` (or `multicam`, `clipper`) → choose the cut points on sentence boundaries from the99 words, not only the silences.1004. Cleanup of the active sequence: `apply_cuts` with `ripple`. A new reel or a reordered cut:101 `assemble_edit` with the plan (`width` 1080, `height` 1920 for vertical).1025. Several cameras: `switch_multicam` with the speaker turns mapped to tracks; hold an angle at least103 two seconds unless the reaction is the point.1046. `adobe_contact_sheet` at each cut (cut-0.2, cut, cut+0.2) and at the start; fix what jumps.1057. Speech pauses: `audio_gaps`, then `recompact_audio` (0.25-1.0 s by default). B-roll with106 `adobe_import_generation`; montage cuts on the bars from `adobe_beat_markers`. Music last:107 `music_bed` with the track (from `add_soundtrack` or `generate_audio`), ducked under the voice.108 Titles with `import_mogrt` + `set_mogrt_text`, captions with `import_captions`, chapters with109 `add_markers`.1108. `export_sequence` when the user wants the file (saved to ~/Movies/Mira unless they name a path),111 then look at it. `save_project` only when the user asks.112113## Interview114115Ask only what the brief leaves open:1161171. The job: cleanup, highlights, reorder or a given script.1182. The platform and shape: 16:9 long form, or 9:16 for Reels, TikTok or Shorts, and the length.1193. What must stay: lines, names, a call to action, the speakers' order.1204. Music: none, the user's track, or one made with Mira.1215. Captions: none, a caption track, or burned in.122123## Checklist124125- Every speech cut sits on a sentence or phrase boundary; no word is clipped.126- No more than the allowed air at the head and tail of each line; pauses within the ranges.127- One take per repeated line; no spliced sentences.128- The hook lands in the first two seconds of a short.129- Music sits under the voice, not on top of it; the mix is checked at the loudest line.130- A contact sheet at every cut has been looked at; nothing is black between clips.131- The project is saved only when the user asked.132133**AI Film Studio.** An Editor cut opens as a sequence with `film_edit_open_in_app`, takes come in with `film_open_in_app`, `adobe_command export_sequence` with `film_project_id` returns the edit to the project's bin - see `film-studio.md` in `mira-generate`.