--- name: filmscene-corpus description: Read the scene to remake as data from its clip — the cut times, the camera setups, the lines with their times and speakers, the parts of up to 15 s that end on a cut, and the acting shot by shot. --- # The scene as data 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 `filmscene` for the shared rules. ## Get the scene - **Find it**: `search_movie_frames` with `query` = what happens; each frame names the film, the scene number and the timecode. The person then brings the clip of that scene: `show_media_upload_picker` gives a video receipt (`{videoReceipt}` in every video tool). Cut it to the scene once with `trim_video` and work relative to its start. Without the clip, stop here and ask for it: cuts, lines and times cannot be read from corpus frames or guessed. - **Cuts**: `detect_video_cuts` → the cut times and the scenes between them. A soft cut may need a lower `threshold`. - **Setups**: `extract_video_frame` from the middle of every scene; frames that show the same angle are one setup (A, B, C…). `arrange_images` them into one sheet and `describe_media` it ("which frames show the same camera angle?"). - **Lines**: `extract_video_audio`, then `transcribe_media` → the words with times and the speaker of each segment. A segment can hold two speakers — split it at the gap between their words. - **Roles**: map each speaker to the person's cast ({character A} replaces , {character B} replaces ) and carry that mapping into setups, speakers and voices. ## Parts - **At most 15 s, ending on a cut.** Sum the shots from the start; if a part runs a little over, trim the head before the first line rather than the tail. - The generation length is a whole number of seconds; when the part is shorter (12.9 s), generate 13 s and trim in the edit. ## Acting Take one frame a second of the part (`extract_video_frame`), `arrange_images` them into a sheet (`columns: 4`), and write what each person does — gaze, head, mouth, nods — shot by shot (`describe_media` on the sheet with a question about it). It goes into `action` and `acting` of the prompt. ## 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-film-scene/skills/filmscene-corpus.md) - Updated from the owner's skill sources of 2026-10-11. Read: `filmscene`, `filmscene-setups`, `filmscene-shots`. Source experiments and demo materials are historical; use the person's own approved media.