Update to Vidova

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -2,19 +2,29 @@
 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
-metadata:
-  vidova-guide: skills/podcast-clips
 ---
 
 # Podcast clips
 
-Vidova edits this video on a real timeline and renders it in the cloud. The full guide for short captioned clips from a long talk is on Vidova's server, so it is always current.
+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 `get_active_project`). If they are not, follow the `vidova` skill to connect the Vidova MCP server.
-2. Call `read_docs` with id `skills/podcast-clips`. Follow that guide for the whole edit.
-3. Put the person's footage in a project: `create_project`, then `upload_files`, `import_asset_url` or `begin_asset_upload`.
-4. Call `search_templates`. When one fits, use `read_template` and `apply_template`. Otherwise build the film with `patch_film`.
-5. Watch the result with `preview_timeline`. Call `check_film` on the whole film and fix what it lists.
-6. Call `render_video`, then give the person the project `url` and the finished video.
+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.