Update to vidIQ

{
  "description": "Rank what an authorized YouTube creator should publish next from their own analytics plus live search demand, audience requests, trends, and competitor gaps. Use when asked 'what should my next video be', 'what should I post on YouTube to grow', or 'rank these ideas for my channel'. Needs the creator's own channel; for ideas from breakout videos in any niche use vidiq-video-ideas.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 465
    },
    {
      "relative_path": "references/discovery-evidence.md",
      "size_in_bytes": 1213
    },
    {
      "relative_path": "references/job-lifecycle.md",
      "size_in_bytes": 724
    },
    {
      "relative_path": "references/live-surface-notes.md",
      "size_in_bytes": 2014
    }
  ],
  "name": "vidiq-next-video-planner",
  "skill_md_contents": "---\nname: vidiq-next-video-planner\ndescription: Rank what an authorized YouTube creator should publish next from their own analytics plus live search demand, audience requests, trends, and competitor gaps. Use when asked 'what should my next video be', 'what should I post on YouTube to grow', or 'rank these ideas for my channel'. Needs the creator's own channel; for ideas from breakout videos in any niche use vidiq-video-ideas.\n---\n\n# vidIQ Next Video Planner\n\nRead [Live surface notes](references/live-surface-notes.md) first, even when using only supplied evidence.\n\nRank next-video opportunities from channel fit, competitors, demand, and timing. Keep this workflow\nread-only: no generation, packaging scoring, refinement, or mutations. Switch to\n`vidiq-video-ideas` for open-ended idea discovery and to `vidiq-packaging-studio` to package a\nchosen idea.\n\n## Scope and channel fit\n\n1. Use supplied audience, format, language/market, horizon, constraints, and goal. Ask one compact\n   question only for gaps affecting tool inputs or ranking.\n2. Use a capped evidence plan: start with one call per relevant lane and expand only for facts\n   that could change the decision.\n3. Resolve the intended authorized channel with `vidiq_user_channels`. For recent channel fit,\n   use `vidiq_channel_videos` with `popular: false` and matching `videoFormat: long`, `short`,\n   or `live`.\n4. Request `vidiq_channel_analytics` with explicit dates, `dimensions: [\"video\"]`, and\n   `filters: \"video==ID1,ID2\"` for those IDs in batches of at most 150. Set `maxResults` to cover\n   the batch within live limits and join by video ID. Missing rows are unknown; a mixed-format\n   top-N report cannot define recent same-format fit. Compare sensible publication ages and\n   label the upload set a sample. If private analytics are declined, disclose that missing lane.\n\n## Research useful evidence lanes\n\nRead [Discovery evidence](references/discovery-evidence.md) when discovering or evaluating\ncandidate opportunities, including supplied examples.\n\n- **Competitors:** use `vidiq_list_competitors` when useful. Exclude self, known siblings, and\n  unrelated channels from the analysis cohort; disclose uncertain ownership/fit and leave the\n  saved list unchanged. Otherwise use `vidiq_similar_channels` with canonical `channelId` and\n  optional `size`/`sort`. Manual `niche` mode has separate filters, no `subNiches` field, and\n  ranking preferences that require checking returned fit.\n- **Outliers:** gate the format/language combination before `vidiq_outliers`. Shorts are restricted\n  to English; outliers and trending have no live-only lane. For non-English outliers, `all` narrows\n  to long-form and discovery is capped at six months. Pass supported `contentType` and `language`;\n  never silently substitute English or another format. Cluster premises, audience needs, and\n  payoffs. Treat absent matches as a sampling limit, not proof of an unclaimed opportunity.\n- **Search demand:** use `vidiq_keyword_research` with `mode: \"research\"`, seed `keyword`, and\n  optional supported `country`. For momentum, `rising` uses `period` and `language`; discover\n  `availableTopics` before supplying a `topic`. It ignores `keyword` and `country`; where declared,\n  `includeKeyword` narrows results to a whole word or adjacent phrase.\n  Keep measured demand/growth separate from scores or ranking; missing, stale, or\n  nonpositive baselines cannot establish relative growth.\n- **Audience requests:** `vidiq_comment_insights` with `mode: \"discover\"` and the `niche` returns\n  recurring viewer requests and pain points across the niche as an asynchronous job; read\n  [Job lifecycle](references/job-lifecycle.md) and poll `vidiq_job_poll`. `mode: \"validate\"` with\n  `idea` tests a finalist. It is one lane, not a verdict, and the Claude.ai directory connector\n  does not expose it.\n- **Timing:** `vidiq_trending_videos` measures absolute velocity in the confirmed format and\n  market. `vidiq_video_stats` on a finalist can test acceleration/decay; choose required\n  `granularity: hourly`, `daily`, or `monthly` to match its age/window. Normalize epoch-second\n  outlier dates and ISO timestamps before age comparisons. Do not equate velocity with\n  channel-relative outlier performance.\n\nApply the shared relevance/independence rule to every discovery lane. For cross-niche mechanisms,\nmatch viewer motivation and use semantic `requireAllTitleTerms: false`; strict matching is\nsupporting evidence only on tools declaring that field. Inspect actual images or mark visual\nfindings provisional.\n\n## Decide and deliver\n\nCompare up to three supported opportunities, or the requested count, on channel fit, competitive\nopportunity, demand, timing, originality, and feasibility. Use ordinal judgments; do not sum\nincompatible metrics. Prefer corroborating evidence types and state what could change the choice.\n\nReturn the shortlist and strongest supported brief with evidence scope/dates, confidence, and\ncounterevidence. Use original framing, examples, and expression. If evidence cannot support a\nchoice, state the gap; do not force a winner.\n"
}