Update to vidIQ

{
  "description": "Judge YouTube trends by urgency, durability, saturation, and accessibility to smaller channels using live vidIQ data. Use when asked 'what's trending on YouTube today', 'trending topics in [niche] this week', 'is this trend worth a video', or 'should I jump on this now or is it too late'. Classifies topics as urgent, durable, mature, or misleading.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 456
    },
    {
      "relative_path": "references/discovery-evidence.md",
      "size_in_bytes": 1213
    },
    {
      "relative_path": "references/live-surface-notes.md",
      "size_in_bytes": 2014
    }
  ],
  "name": "vidiq-trend-radar",
  "skill_md_contents": "---\nname: vidiq-trend-radar\ndescription: Judge YouTube trends by urgency, durability, saturation, and accessibility to smaller channels using live vidIQ data. Use when asked 'what's trending on YouTube today', 'trending topics in [niche] this week', 'is this trend worth a video', or 'should I jump on this now or is it too late'. Classifies topics as urgent, durable, mature, or misleading.\n---\n\n# vidIQ Trend Radar\n\nRead [Live surface notes](references/live-surface-notes.md) first, even when using only supplied evidence.\n\nSeparate current velocity, channel-relative breakout, durable demand, and creator accessibility.\nRecommend timing from evidence and production lead time. Switch to `vidiq-youtube-seo` for keyword\nvolume and tags, and to `vidiq-next-video-planner` for a ranked next-video choice.\n\n## Gather a bounded evidence set\n\nRead [Discovery evidence](references/discovery-evidence.md) before evaluating trend examples,\nincluding supplied results.\n\n1. Define niche, audience, region/language, format, and horizon; use a bounded research\n   plan. Before a saved-watchlist scan, exclude self, known siblings, and unrelated channels from\n   analysis, disclose uncertainty, and leave the list unchanged.\n2. Use `vidiq_trend_categories` only when its taxonomy can narrow outliers through\n   `trendCategories`; those slugs are not inputs to `vidiq_trending_videos`.\n3. Use `vidiq_trending_videos` for absolute velocity with required `videoFormat: long` or\n   `short`, `videoTitleLanguage`, and a relevant `channelCountry`. Creator country is not\n   audience geography. Use `vidiq_outliers` separately for channel-relative performance, with\n   explicit supported `contentType`/`language`; omission defaults to English. Outliers rejects\n   non-English Shorts, narrows non-English `all` to long-form, and caps non-English discovery at\n   six months. Neither discovery tool provides a live-only lane; disclose unsupported coverage.\n4. Apply the shared relevance/independence rule to inspected titles and images. Match transferable\n   viewer motivation for cross-niche searches. Use semantic `requireAllTitleTerms: false` where\n   declared, with strict matching as supporting evidence.\n5. Use `vidiq_keyword_research` for search durability. Seed `research` gives demand context;\n   `rising` accepts supported trend windows/categories and ignores `keyword`; narrow it to a phrase\n   only with `includeKeyword` where declared (whole words or adjacent phrases).\n   Search demand alone does not prove format fit.\n6. Use `vidiq_video_stats` on finalists with required age-appropriate `granularity`; prefer\n   `hourly` for recent trends and explicit ISO `from`/`to` bounds. Analyze historical `vph`,\n   not cumulative views. Use comparable windows, allowing younger videos less than a full day\n   of history. Normalize outlier epoch seconds and other ISO dates to a common timezone.\n7. When accessibility matters, use `vidiq_channel_search` with `breakoutChannel: true`.\n   Apply `subscriberCountMin` only for a requested or justified cohort boundary; disclose the\n   reason and flag tiny-base growth as uncertain instead of excluding new creators by default.\n\n## Classify from evidence\n\nThe labels are reporting aids, not fixed thresholds or deadlines. Leave unsupported cases\nunclassified and state what observation could change the recommendation.\n\n| Class | Evidence and response |\n| --- | --- |\n| **Urgent** | Relevant independent examples exceed positive comparable baselines with measured rising velocity. Act soon only if production fits the opportunity window. |\n| **Durable** | Recurring need supported by relevant content over time and search demand; normal production timing can fit. |\n| **Mature** | Measured plateau or decay across relevant examples with established demand. Differentiate or pass; age alone is insufficient. |\n| **Misleading** | Evidence on relevance, independence, or sustained demand contradicts the apparent opportunity. State the contradiction; the topic itself need not be worthless. |\n\nFor urgency, use at least two timestamped non-null historical VPH observations per qualifying\nexample. Report baseline source, comparable format/age scope, window, and contrary movement.\nOne VPH snapshot, total views, or age cannot establish acceleration. Missing historical VPH or\npositive comparable baselines leaves urgency unconfirmed.\n\nClaim measured search-demand growth only for the same keyword with current value, positive\nbaseline, comparable market/window, and usable freshness timestamp. Prefer returned\n`searchDemandGrowthPct` with that context; related keywords, upstream ranking, or raw growth are\nnot substitutes. Stable demand may support durable fit without positive growth.\n\nHigh channel concentration plus declining VPH is a warning, not proof of a misleading trend.\nShow cohort size, concentration denominator, sampling limits, and corroborating contradictions.\n\n## Deliver\n\nReturn relevant opportunities with velocity, relative breakout, search durability, accessibility,\nclass, timing, production fit, and confidence. State the evidence date, actual filters, strongest\ncounterevidence, and next reassessment signal. Offer an original format/angle; keep timing a\nreasoned estimate rather than a guaranteed trend half-life.\n"
}