--- name: youtube-checkup description: What works on a YouTube channel and why, from its public numbers — growth over a window, its most popular and latest videos with breakout scores, how fast its videos usually gather views — read as three findings and three actions; vidIQ calls paid per call, private Studio analytics stay in YouTube Studio. --- # What works on your channel 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 `youtube` for the shared rules. **Public numbers only.** FlashBoards reads what anyone can see on YouTube; the channel's private analytics (retention, traffic sources, audience, revenue, impressions and thumbnail click-through rate) stay in YouTube Studio. Slots: {channel} — the @handle, channel URL or channel id · {format} — long or short videos. ## The price first Every step below is one `vidiq_research` call with a new `requestId`. Each call is paid by the person (5 vidIQ credits; the tool description names the price) and charged only when vidIQ answers; the same question within 12 hours comes back `cached: true` at no charge. A check-up is three or four calls: name the total once before the first. ## Three calls, one optional 1. **The channel** — `tool: "channel_stats"`, `input: {channelId: "{channel}"}` (a handle like `@name` works): subscribers, total views, videos, and growth over the last 30 days (`from` and `to` change the window). 2. **Its best or its latest** — `tool: "channel_videos"`, `input: {channelId, videoFormat: "long" | "short", popular: true}` for the most popular videos with their breakout scores; `popular: false` for the latest uploads. One call: popular for "what works", latest for "how is it going now". 3. **Its usual** — `tool: "channel_performance_trends"`, `input: {channelId}`: how many views its videos usually have at each age after publishing (median and spread). A video is a breakout against this curve, not against the biggest channel in the niche. 4. **Optional, the niche** — `tool: "outliers"` with the channel's topic as `keyword` (not the channel): formats that break out beyond this channel. ## Read it and say it - **Breakouts**: name each with what it beats ("4× its usual 20K at one week"); copy the numbers from the answer, never round a multiplier into "went viral". - **What the top videos share**: format, length, title pattern, how they open. Thumbnails are not returned: say so if asked. - **The trend**: growth over the window, and whether the latest uploads run above or below the usual curve. - Then three findings, one line each, and three actions: what to make next, how to title it, what to stop. - Offer the next step: `youtube-packaging` for the next video's titles and thumbnail, `youtube` to make the episode, `viral-works` for what breaks out in the niche on Shorts, Reels and TikTok. ## Rules 1. Public data only. When the person asks for retention, traffic sources, audience, revenue or click-through rate, say these are in YouTube Studio (Analytics) and read them together if they paste them. 2. A number comes with what it is measured against; never promise views. 3. One call per question; never page through every video of the channel. 4. When a call answers `VIDIQ_PAYMENT_REQUIRED`, say the balance cannot cover it; do not look the numbers up another way. ## 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 YouTube router (flashboards-apps `.claude/skills/youtube` and `chat/modes/_common.md`, "YouTube with vidIQ"); no Learn article yet. Read: `youtube`, `youtube-packaging`, `viral-works`, `avatar-podcast`. Source experiments and demo materials are historical; use the person's own approved media.