Vidova

View saved version →

---
name: beat-sync-edit
description: "Make a beat-synced edit with Vidova, the AI video editor. Use when someone asks for an edit cut hard to a song: a fan edit, a car or bike edit, a gaming, anime or movie montage, a phonk or hype edit. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Beat-sync edit

A song and the best few seconds of every clip, cut so each hit of the song lands on something happening.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Call `detect_beats` on the song for the beats, the downbeats and the drop. Read each clip with `read_asset` and note its peak moment to a tenth of a second. Those peaks are what the edit is made of. Leave out clips where the subject is small or off screen.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Start 4 bars before the drop, where a bar lasts 4 x 60 / bpm seconds. Use 2 to 4 slower shots for the intro, then one beat each, then half a beat in the last bar. Put the best clip on the drop, and one beat or half a beat per shot after it. End on the strongest image, slowed so it still moves.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Use the song they named or uploaded. Never swap it for another.
- Every shot shows the subject of the edit.
- Put every clip's peak on a beat: rush into it, slow hard to about quarter speed on the beat, and rush out. It never stops.
- Frame 0 is the thumbnail: a bright, readable frame of the subject.
- Vary the shot lengths. An even run of equal shots reads as a metronome.
- `search_effects` and `apply_effect` put one effect on the drop. Never put effects on every cut.

View saved version →

---
name: birthday-video
description: "Make a birthday video with Vidova, the AI video editor. Use when someone asks for a birthday reel, a montage of photos and wishes, a surprise from friends or family, or a milestone age. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Birthday video

A video made for one person on their day. It works when it is clearly theirs: their name, their people, their face laughing.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Read every file with `read_asset`: the cake and the second the flames go out, the best laugh, hugs, people singing, old photos and their order, and who says which wish.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Cut the moments to the music. Find a track with `search_stock` kind music, add it with `import_stock`, and read it with `detect_beats`.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Use the name and the age from the message. Never invent them. With neither, write "Happy birthday" with no name.
- Choose the kind that fits the files: a party reel from clips of the day, through the years from old photos in order, or wishes from friends cut to their best sentence.
- Show the person's face or the cake in the first second, with their name as the biggest thing on screen.
- Give the best laughs the most time. Before the big moment, lower the music for a bar, then land the moment on a downbeat and slow it down.
- End on the person with their people, for 2 to 3 seconds, with the footage still moving.
- Every photo moves with a slow push. Text never sits on a face or on the flames.
- Make 15 to 25 seconds for a party reel, or 30 to 60 seconds for through the years or wishes.

View saved version →

---
name: event-recap-video
description: "Make an event recap with Vidova, the AI video editor. Use when someone asks for a recap or aftermovie of an event or a year: a party, a festival, a conference, a launch, a team or school year, or a community celebration. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Event recap

The people who were there watch it to see themselves, and everyone else watches to wish they had been.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Read every photo and clip with `read_asset`: who is in it, where the faces are, whether it is a stage, a crowd, a speaker or the group photo, and whether its sound matters. Leave out blurry and dark files.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Follow the order they gave. Find music with `search_stock` kind music, add it with `import_stock`, and read it with `detect_beats`. Keep a speech line or a cheer in its real sound, with captions from `transcribe_asset`.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Name the event in the first second, over faces and energy.
- A named order is a hard rule.
- Match the mood: a party or a festival is fast and upbeat, a memorial is warm and steady, a conference is clean and confident.
- A photo fills the frame with a slow push, with the faces in the upper half.
- End on everyone together, with a closing line or the next date they gave.
- Use only the names, roles, dates, places and numbers they wrote or that appear on their own pictures. Spell names exactly.

View saved version →

---
name: explainer-video
description: "Make an explainer video with Vidova, the AI video editor. Use when someone asks for an explainer: an idea, a product, a process, a lesson or a set of facts turned into a short animated story with a voiceover or on-screen words. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Explainer video

One idea made clear in under a minute, so a viewer can repeat it to a friend.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Write the one sentence the viewer should know at the end, then the script. A hook of up to 3 seconds, three to five steps of one sentence each, and a takeaway of 3 to 5 seconds. A script the person wrote is the script.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. With a recorded voice, call `transcribe_asset` for the word times and cut each scene on its sentence. Without a voice, show one short line per step. Give each step its own picture: their footage, a screen, an element from `search_elements`, or a device frame from `search_stock`.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Open on the question or the surprising fact, in the viewer's words, over a picture that already shows it.
- A step that holds two ideas becomes two steps.
- Use only facts the person gave or common knowledge. Never invent a statistic, a date, a study or a quote.
- Never use the same picture for two steps, or footage that has nothing to do with the sentence.
- Punch in on the detail the voice names, landing on the word. A caption never covers that detail.
- Make 30 to 60 seconds for social, or 60 to 120 seconds for a lesson. Use 9:16 unless they ask for YouTube, a course or a presentation.

View saved version →

---
name: family-video
description: "Make a family video with Vidova, the AI video editor. Use when someone asks for a family edit from the person's own clips and photos: a summer, a holiday, a year with the kids, a tribute, a wedding or an anniversary. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Family video

The person's own clips of people they love, cut to music, made to be shared in the family chat.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Read every clip and photo with `read_asset`: the moment with the most feeling and its time, where the faces are, whether its sound is worth keeping, and whether it is dark, shaky or soft.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Cut to the music. Find a track with `search_stock` kind music, add it with `import_stock`, and read it with `detect_beats`. Grade every clip to one look.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Use fewer, better moments, and leave out the soft, dark and shaky clips. A 25 second edit of eight good moments beats 60 seconds of everything.
- Make 20 to 40 seconds for sharing, or up to 60 seconds for a tribute.
- Open on the best moment, already happening, with people in frame 0.
- Cut every two beats in the lively parts. A hug or a sentence gets a whole bar. A wedding or a tribute is slower.
- Lower the music once for 1 to 2 seconds under a real sound, such as a laugh, then bring it back on a downbeat.
- End on the warmest wide shot for 3 seconds or more, still moving, with the music fading out with the picture.
- Use the names, places and years they wrote. Never invent them. Never darken a face, and keep text off faces.

View saved version →

---
name: get-started
description: "Get started with Vidova and make a first edit. Use right after the plugin is set up, or when someone asks how to start with Vidova."
license: MIT
---

# Get started with Vidova

Help the person get a finished video from their own footage. Keep it short.

## Steps

1. Call `whoami` to confirm the Vidova account is connected.
2. Ask what video they want, and ask them to attach their clips or photos in this chat, up to 512 MB each.
3. When they attach files, make a project with `create_project`, bring the files in with `import_attached_files`, and call `wait_for_asset` with every Asset ID.
4. Call `start_routine` with routine `edit_prep` and their request word for word, then call `wait_for_jobs` until it is done and follow its handoff.
5. Watch the result with `preview_timeline`. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
6. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

If they have a file over 512 MB, or their files are on another device, call `create_upload_link` and give them its link.

View saved version →

---
name: motion-graphics
description: "Make a motion graphics piece with Vidova, the AI video editor. Use when someone asks for animated type, shapes, numbers and logos for a launch, an announcement, a promo, stats or a brand sting, with or without footage. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Motion graphics

Type, shapes, colour and numbers that move to music, with each scene one idea read in a second.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Find what it announces, the one fact that matters and the call to action. Bring in their logo with `search_logo` and `import_logo`, or use `remove_background` on a logo that sits on a box.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Call `search_elements` and `import_element` for titles, charts, counters and maps. Write a component with `replace_component` when no element fits. Find music with `search_stock` kind music, add it with `import_stock`, and start every scene on a downbeat from `detect_beats`.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Make 12 to 25 seconds, with 5 to 8 scenes of 1.5 to 3 seconds. Each scene says one thing in five words or fewer.
- The hook is on frame 0 and already moving. Never an empty background, a black frame or a logo first.
- Build to the strongest fact. End on the name or logo with one line and the call to action, for 2 to 3 seconds, still moving.
- Set the design before you write: a background, an ink and one accent colour, and one type family unless the brand names its own.
- Keep side margins of 80 px on a 1080 wide frame, and nothing smaller than 44 px.
- A logo alone is enough. Do not fill the piece with unrelated photos from the person's library.
- Use their real words and numbers. Never invent a feature, a price or a number.

View saved version →

---
name: music-video
description: "Make a music video with Vidova, the AI video editor. Use when someone asks for a music video, a visualizer, a lyric video or a song teaser for the person's own song, from their clips, generated shots or both. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Music video

Pictures that move with a song. The song is the script: its sections set the cut rate, its hits set where the picture turns, and its words set what appears.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Call `detect_beats` on the song for the beats, the downbeats and the sections, and `transcribe_asset` for the lyrics with word times. Read each clip with `read_asset`: its best seconds, where the faces are, and whether someone sings on camera.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Cut to the sections. For a lyric video, put one phrase at a time on the vocal. For a visualizer, `search_elements` has audio bars that follow the song.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Make a teaser of 15 to 30 seconds unless they ask for the whole song. A teaser starts a bar or two before the hook, not at the slow intro.
- Pick one visual world for the film: one place, one light, one colour story.
- Verse: one cut per bar, on the downbeat. Build: a cut every two beats. Chorus or drop: the best shots, cut on the beats. Breakdown: one long shot, slowed, that keeps moving. Outro: the strongest image, a face or the brightest light.
- Vary the shot lengths by section. When every shot has the same length, the edit reads as a metronome.
- When someone sings on camera, keep that clip at normal speed and line it up with the vocal.
- Take the artist and the title from the message or the file name. Never invent an artist, and never replace their song.

View saved version →

---
name: podcast-clips
description: "Make short captioned clips from a long talk with Vidova, the AI video editor. Use when someone asks for clips from a podcast, an interview, a panel, a talking head, a livestream or a webinar, cut into vertical shorts or a YouTube cut. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Podcast clips

One idea from a long conversation, cut so a stranger with the sound off stops, understands and watches to the end.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Call `read_transcript` for the whole conversation, using `transcribe_asset` first when there is no transcript. Find the moments that work alone: a surprising claim, a story with a turn, a strong opinion, a number, a joke that lands. Use `read_analysis_range` with kind transcript for the word times of each moment.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Reframe around the face with `track_faces`, and use `detect_scenes` to find camera changes in the source. Add captions: `search_elements` has caption styles, and `patch_transcript` fixes misheard names and numbers.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Make three clips of 20 to 45 seconds unless they ask for another number, each from a different moment. `create_branch` keeps each clip as its own version.
- A clip starts on the first word of a sentence that makes sense alone and ends on a full stop. Never cut a person mid-sentence.
- Open on the sharpest line of the clip. Cut the ums and false starts with the word times.
- A cut every 3 to 7 seconds, on a sentence start, with a punch-in on the face, reads as a second camera. With two speakers, cut to whoever speaks.
- On a vertical clip, reframe the recording around the face. Never a small window in the middle of a black or blurred frame.
- Captions sit under the chin and never cover the mouth.
- Take speaker names from the message or the recording. Never guess a name.

View saved version →

---
name: product-ad-video
description: "Make a short product ad with Vidova, the AI video editor. Use when someone asks for a product ad, a UGC-style ad, a launch or drop video, or a promo with a price or offer, from product footage or photos, for Reels, TikTok, Shorts or a store page. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Product ad

One product, one promise, one action, in the time it takes to scroll past.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Read each file with `read_asset`: the best angle, the moment of use, where the product sits in the frame. Use `remove_background` on a logo that sits on a box.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Cut on the downbeats of the music. Find a track with `search_stock` kind music, add it with `import_stock`, and read its beats with `detect_beats`.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Show the product in use, or its best detail, in the first second. No logo first and no black frame.
- A 15 second ad has four parts: the hook to 1 s, the reason to 9 s (the problem and the fix, or three details, one idea per shot), the peak to 12 s with the offer said once, and the product still moving with the brand and the action to the end. Scale this to 6 or 30 seconds.
- Use 8 to 10 shots in 15 seconds, with lengths that follow the beat.
- Use only the person's facts. Never invent a feature, a price, a claim or a review. Add no medical or performance claim unless they wrote it.
- Keep the product's true colours, and keep it the sharpest thing in the frame. Text never sits on the product or on a face.
- Use 9:16 for Reels, TikTok and Stories unless they say otherwise, 1:1 or 4:5 for a feed, and 16:9 for YouTube or a website. For an app or a website, `search_stock` has device frames.

View saved version →

---
name: sports-highlights
description: "Make a sports or fitness video with Vidova, the AI video editor. Use when someone asks for match highlights, a player edit, a game day video, a training or gym reel, a race or a season recap. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Sports and fitness

Sport is moments: the release, the strike, the finish, the last rep. A good edit finds the exact frame of each one and lands it on the song's hit.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Find each clip's peak to a tenth of a second with `read_asset`, `read_analysis_range` and `preview_frame`. Use `pin_moment` to keep it. Read the song with `detect_beats`.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Build each moment in three shots: the approach rushing in, the peak on a downbeat easing to about quarter speed, then the replay from another angle.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Open as the brief says. When it says nothing, open on the best moment or on the athlete's face.
- Keep the real sound of the strike or the net on the moment. Let the music dip for half a second before it, then come back on the next downbeat.
- End on the finish: the celebration, the touch at the wall, the last rep or a face, slowed so it still moves.
- Commit to the slow part. A timid slow-down reads as a stutter. Keep the action moving and never freeze it.
- Never crop a head or the ball out of the frame, and never warp a body.
- Use only their names, numbers, scores, teams and times. Never invent a score or a statistic.

View saved version →

---
name: travel-recap-video
description: "Make a travel recap with Vidova, the AI video editor. Use when someone asks for a trip video from the person's clips: a holiday, a road trip, a city break or a honeymoon, with the places on a map or in titles, cut to the beat. Vidova cuts, captions, animates, adds music and renders the video in the cloud."
license: MIT
---

# Travel recap

A trip told in under a minute, so the person relives it and their friends want to go.

## Steps

1. Check that the Vidova tools are available, for example with `get_active_project`. If they are not, ask the person to connect the Vidova plugin and sign in.
2. Make a project with `create_project`. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Work out where they went, in what order and when, from the message, the file names and what `read_asset` shows (landmarks, signs, food, dates). For each clip, note the place, the moment, and whether its sound is worth keeping.
4. Call `search_templates`. When a template fits, use `read_template` and `apply_template`, then adjust it with `patch_film`. When none fits, build the film with `patch_film`.
5. Cut on the downbeats. Find a track with `search_stock` kind music, add it with `import_stock`, and read it with `detect_beats`. `search_elements` has maps and route graphics for the stops.
6. Watch the result with `preview_timeline`, and with `preview_range` across the moments that move. Call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Call `render_video`, wait for it with `wait_for_jobs`, then give the person the project `url` and the link to the finished video.

## What makes it work

- The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
- Build a journey: leaving, getting there, the best days, the last evening.
- Open on the most striking shot, already moving, with the place name or the start of the route.
- Speed up toward the best days. Hold the last evening for 3 to 4 seconds while it keeps moving.
- Name each place once, on the first shot of its section. Text stays off landmarks and faces.
- Keep the real sound where it adds something: waves, a street musician, a laugh.
- Make 20 to 45 seconds for a short, or 60 to 90 seconds for a 16:9 film. Never invent a place.

View saved version →

---
name: vidova
description: "Edit videos with Vidova, an AI video editor with a real timeline. Cut clips, add captions, music, voiceover, motion graphics and effects, and render in the cloud. Use when someone wants a video made or edited from their footage, photos or an idea."
license: MIT
---

# Vidova

Vidova is an AI video editor. Its MCP server gives you the editor's tools: projects, uploads, the timeline, templates, effects, captions, music, previews and cloud renders. The person sees every change in the web editor at https://editor.vidova.ai.

## Connect

This plugin brings the Vidova tools with it. The person signs in with a Vidova account when ChatGPT asks.

## How to edit

1. Start with `get_active_project`, or pick a project with `list_projects` and `open_project`, or make one with `create_project`.
2. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.
3. Read the footage with `read_asset`, `read_transcript` and `search_footage`. Watch an existing film with `preview_timeline` before you suggest or make edits.
4. Call `search_templates`. When a template fits, `read_template` shows its slots and `apply_template` builds the film. Refine it with `patch_film`. When none fits, build the film with `patch_film`.
5. Find graphics and captions with `search_elements`, effects with `search_effects`, and music, sound effects and device frames with `search_stock`.
6. Before you render, call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.
7. Render with `render_video` and wait for it with `wait_for_jobs`. Give the person the project `url` and the link to the finished video.

Pass the project's id as `projectId` on every project tool. Another session on the same account can open a different project between your calls.

Vidova works on the footage the person provides. Use their facts, names and numbers, and never invent them. Follow their brief: their order, song, length, format and rules come first. The skills in this plugin cover the common kinds of edit, such as `product-ad-video`, `podcast-clips` and `beat-sync-edit`.