--- name: musicvideo-film-scenes description: Choose one film whose story fits the track, write a three-act story with the person, cast the roles, and find frames for every story beat in the film corpus — four frames a part, the lead alone where possible. --- # One film, a linear story, frames for every beat FlashBoards user skill, version 1.2.3 (2026-10-13). On the board, read these guides with `list_skills` and `get_skill` when the assistant exposes them; otherwise use the hosted index through an available read-only retrieval tool. Use that runtime’s actual model discovery, current page context and guarded board actions for execution. Keep native readiness, approval and cost gates; do not claim a guide was read when retrieval is unavailable. Read related guides with `get_skill({skillId:""})` or the [hosted index](https://pub-78da82d51ed14147ac554d38094b0c0b.r2.dev/user-skills/1.2.3/index.html). Reading a guide does not start or authorize a paid generation. Read `musicvideo` for the shared rules. ## Steps 1. **Story first, in three acts** (joy → turn → catastrophe or ending), one {film}, fitted to {track}: for each {act} write the beats [place + what {character} does]. Pick the story with the person, not from a previous run. 2. **Cast**: list the film's main roles in your story. {character} takes the lead; for a second main role ask the person (another of their characters, an invented face, or removed) — never a demo character. 3. **Find the film**: `search_movie_frames` with the story or the mood as `query`; show three film worlds and let the person pick. 4. **Find the frames for every beat**: `search_movie_frames` in `mode: "browse"` with the film's `filmId` (pages with `cursor`), or `mode: "text"` with the beat ("a welder at a furnace at night, sparks"). Each frame names its scene number and timecode. A film browse is shuffled, not in scene order: narrow it with `filter` (`interior`, `exterior` or `night`). `mode: "similar"` finds look-alike frames in other films only, so it gives a look, not more frames of the chosen film. No frame fits a beat → search again, browse more pages, or change the beat with the person; never draw the world yourself. 5. **Look before you choose**: `get_movie_frame_preview` for each candidate; for a quick overview `arrange_images` several of them into one sheet (each source `{previewHandle}` of the frame) and `describe_media` it with a question. 6. **Four frames per part** (each gives two shots). Prefer frames with the lead alone; a crowd is fine — the faces get replaced. ## Never - Scenes from several films — the world breaks. - Scenes whose meaning would sour the tone of the track. - Frames full of deaths for a light ending — show the disaster from afar. ## Execute through MCP or on the board Use the person's FlashBoards account; never ask for a personal provider key or run the source's local scripts. Discover `get_account`, `list_generation_models` and the tools of this client first: a published guide does not prove a feature is deployed. **Headless, no open board.** Quote with `estimate_generation_cost` (skill models: `estimate_skill_model`), then run `generate_image`, `generate_video`, `generate_audio` or `run_skill_model` with one stable `generationAttemptId` per logical attempt. Pass `maxCostUsd` only when the current operation and selected model support it; otherwise use the quoted cost and the person's explicit approval with the supported controls. Never silently ignore an unsupported spending cap; make one `get_generation` check after `retryAfterSeconds`. Pass the person's own results by `generationId`: images in `referenceGenerationIds`, `firstFrameUrl` and `endFrameUrl`, audio in `referenceAudioUrls` or `targetAudioUrl`, videos in `referenceVideoGenerationIds`. They are read on the server; signed result links do not work as public URLs. Every `generationId` a tool returns stays valid: a later read of the same result gives a different string, and both work. Film frames and gallery pictures go in by `previewHandle`: `referencePreviewHandles` of the generation tools, a `{previewHandle}` source of `arrange_images`, `crop_image` and `pad_image`, and `describe_media`. New files come from `show_media_upload_picker` as receipts. The person's character comes in as its sheet, by `generationId` or as an upload; there is no search by name. If the person names a character without the sheet, ask for it or make one with `character-sheet`; do not scan recent results for it. Free server steps: `trim_video`, `concat_videos`, `conform_video`, `replace_video_audio`, `extract_video_frame`, `extract_video_audio`, `detect_video_cuts`, `crop_image`, `pad_image`, `arrange_images`, `cut_audio_span`, `concat_audio_tracks`, `mix_audio_tracks`, `fit_audio_duration`, `add_audio_reverb`. Check every result with `describe_media` (a question about an image; `model`, `mode` and `sourceRange` only for a video) and `transcribe_media` for speech. Both checks are paid: `describe_media` costs a fraction of a cent for an image and about 2–4 ¢ for a short video (more for a long one), `transcribe_media` under 1 ¢ a minute — count the checks you plan in the price you name before the first paid step. `describe_media` is not reliable about sound: it misses effects mixed under music and can hear voices or instruments that are not there. Check speech with `transcribe_media` and ask the person to listen for effects and music. Never repay an uncertain submission; reuse an attempt ID only for the identical request. Make each new `requestId` or `generationAttemptId` unique, for example the task, the date and a short random suffix: an ID used before, even in another chat, replays that earlier request or answers `REQUEST_ID_CONFLICT`. **On the board.** Inspect with `list_board_sessions` and `get_board_snapshot` and carry the same `sessionId` and a fresh `activeBoardId` as `expectedBoardId`. Native cards: `execute_board_action` (`listNativeModels`, `setModel`), `prepare_board_generation` with ordered board items or owned outputs, then one `generate_on_board` within the authorized budget. Board media tools: `list_media_tools` → `start_media_tool` → `get_media_tool_run`. Put headless results on a board with `add_media_to_board`. Keep mandatory safety settings and the live limits of each model. Prices, timings, endpoints and "free retry" claims in the sources are historical, not FlashBoards contracts. If a step this guide needs is not available or is refused (a tool error, `audio_not_configured`, a missing model or input), keep the finished assets, tell the person which step is blocked and why, and ask how to go on. A single generation that ends `failed` is not a blocked step: submit it once more with a new `generationAttemptId` (reworded if it may have hit the content checker), and stop to ask only if it fails again. A failed attempt is not always refunded, so the retry may be paid again and `maxCostUsd` caps each request on its own: count both against the budget the person approved. Never swap in another route on your own: no image model redrawing a layout or a frame, no `describe_media` in place of the frames it should check, no clip generated only to take its sound, no picture drawn where the guide takes a film frame. ## Source and related guides - [Original Learn guide](https://flashboards-h01.vercel.app/learn/formats-and-exhibition/ai-music-video/skills/musicvideo-film-scenes.md) - Updated from the owner's skill sources of 2026-10-11. Read: `musicvideo`, `musicvideo-replace`, `filmscene-corpus`. Source experiments and demo materials are historical; use the person's own approved media.