--- name: viral-publish description: Package a finished video for each platform before the person posts it themselves — the versions (9:16 for TikTok, Reels and Shorts; 16:9 for YouTube) with conform_video or a crop, the platform checks and AI policies from get_platform_rules, a caption and hashtags in the person's own words, and a one-screen list of what goes where; then, where this client offers social_publish, each version is drafted for the person's approval (social), otherwise the person uploads it. --- # Publish pack 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 `viral` for the shared rules. **The person's own finished video. Nothing here posts on its own: where this client offers `social_publish`, step 6 drafts each version for the person's approval (`social`); otherwise the person uploads each version themselves.** Slots: {video} — the finished video (`generationId` or a trim's `videoFinishingTaskId`) · {platforms} — where it goes · {ai} — how it was made. ## Steps 1. **Where it goes.** Ask once which platforms, unless the person said it. Default for a vertical clip: TikTok, Instagram Reels, YouTube Shorts. 2. **Check it once**: `get_platform_rules` with all those platforms, the clip's facts (`durationSeconds`, `aspectRatio`, `heightPx`, `hasAudio`) and `ai`. A `block` (a Short longer than 3 minutes) means that platform needs a cut first (`trim_video`); say the AI label each platform asks for when `ai` is not `none`, with its source and date. 3. **Versions.** One file serves every 9:16 platform. For long YouTube, make a 16:9 version from the person's own video: `conform_video` with `aspect: "16:9"` (or `"9:16"` the other way) crops exactly from the centre and keeps the sound — check the crop keeps the person in frame (`extract_video_frame` + `describe_media` "Is the whole face inside the frame?"). Only 16:9 and 9:16 are made here: a square video post is not, say so. Never generate a new video only to change the shape. 4. **Caption and hashtags** in the person's language and voice: the first line is the hook in words (under about 100 characters), then one or two lines, then 3–5 hashtags about the topic, never spam tags. TikTok and Reels: the hook line matters most; Shorts: the title is the first line. Never invent results, prices or claims the video does not make. 5. **Say it as one list**: for each platform — the file (`generationId`), the caption, the label to switch on in the upload screen before publishing (an AI label is set at upload), any warning. When `viral-score` was not run, offer it before posting. 6. **Post it, with approval.** When `social_publish` is among this client's tools, offer to draft each version to its accounts with the captions, hashtags and AI label from steps 4–5 and hand over the approval link or card (`social`; where a network has several accounts, ask which); the person approves each post there. When it is not, end with: "Upload each version yourself; FlashBoards does not post from here." ## Rules 1. Never claim a post was published, scheduled or answered unless `social_publish` status shows it; without that tool nothing here can post. 2. A crop that cuts the person out is not a version: say the platform needs a re-framed shot instead. 3. Labels and rules come with their source and date (`viral-rules`). ## 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 - Written for FlashBoards from the owner's social-publishing research of 2026-10-12 (flashboards-apps `chat/RESEARCH-SOCIAL-2026-10-12.md`); no Learn article yet. Read: `viral`, `viral-rules`, `viral-score`, `social`, `reels`, `youtube`. Source experiments and demo materials are historical; use the person's own approved media.