← vidIQCONTENT HISTORY

Update to vidIQ

Snapshot Sep 30, 2026 · 23:18 UTC · version 9.0.0

Collection source: not recorded for this historical snapshot. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED · RULE-BASED ANALYSIS

Supporting file metadata differs

Newly listed paths: agents/openai.yaml. This compares saved file lists, not package contents; a different collection source can change the list.

Observed in package metadata. These changes alone do not establish a new customer-facing feature.

Supporting files

Before

[{"relative_path":"references/discovery-evidence.md","size_in_bytes":849},{"relative_path":"references/job-lifecycle.md","size_in_bytes":724},{"relative_path":"references/live-surface-notes.md","size_in_bytes":2014}]

After

[{"relative_path":"agents/openai.yaml","size_in_bytes":447},{"relative_path":"references/discovery-evidence.md","size_in_bytes":849},{"relative_path":"references/job-lifecycle.md","size_in_bytes":724},{"relative_path":"references/live-su...

Compare saved observations

Download comparison JSON
Full technical diff · 1 changed fields

changed /included_files

BEFORE
[
  {
    "relative_path": "references/discovery-evidence.md",
    "size_in_bytes": 849
  },
  {
    "relative_path": "references/job-lifecycle.md",
    "size_in_bytes": 724
  },
  {
    "relative_path": "references/live-surface-notes.md",
    "size_in_bytes": 2014
  }
]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 447
  },
  {
    "relative_path": "references/discovery-evidence.md",
    "size_in_bytes": 849
  },
  {
    "relative_path": "references/job-lifecycle.md",
    "size_in_bytes": 724
  },
  {
    "relative_path": "references/live-surface-notes.md",
    "size_in_bytes": 2014
  }
]
Full snapshot data
{
  "name": "vidiq-shorts-inspiration",
  "description": "Study Instagram Reels or TikTok to develop original YouTube Shorts concepts. Use for cross-platform hook, pacing, format, and payoff research.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 447
    },
    {
      "relative_path": "references/discovery-evidence.md",
      "size_in_bytes": 849
    },
    {
      "relative_path": "references/job-lifecycle.md",
      "size_in_bytes": 724
    },
    {
      "relative_path": "references/live-surface-notes.md",
      "size_in_bytes": 2014
    }
  ],
  "skill_md_contents": "---\nname: vidiq-shorts-inspiration\ndescription: Study Instagram Reels or TikTok to develop original YouTube Shorts concepts. Use for cross-platform hook, pacing, format, and payoff research.\n---\n\n# vidIQ Shorts Inspiration\n\nRead [Live surface notes](references/live-surface-notes.md) first, even when using only supplied evidence.\n\nStudy Instagram Reels or TikTok examples and adapt their abstract mechanisms into original\nYouTube Shorts concepts. Transfer hypotheses need evidence from the target platform.\n\n## Research a bounded sample\n\n1. Establish the source platform, target audience, niche, region, and production constraints.\n2. Search with `vidiq_instagram_tiktok_outlier_search`, building `audienceQuery` from the supplied\n   audience. Ask when context is vague rather than inferring sensitive traits. Set `embeddingType`\n   (`concept`, `hook`, or `format`) and `query`. Date bounds require full ISO 8601 datetimes with\n   timezone, not date-only strings.\n3. Read [Discovery evidence](references/discovery-evidence.md) when evaluating source examples,\n   including supplied results. Search only relevant concept, hook, or format lanes. Apply its\n   minimum separately per platform before claiming a recurring pattern.\n4. Use `vidiq_watch_shortform_content` on strong examples within scope. Verify the source and\n   pass full public URLs, expanding Instagram shortcodes into full reel\n   URLs; bare IDs, shortcodes, and TikTok short links are invalid. Preserve, poll, and recover\n   jobs using [Job lifecycle](references/job-lifecycle.md); read it before a watch call.\n5. Compare hook, pacing, on-screen text, reveal, payoff, duration, and production complexity\n   from actually watched content or completed watch results. Covers, captions, URLs, and pending\n   or failed watches cannot establish moving-image details. Mark missing visual evidence;\n   use caption/title-only findings when that is all available.\n6. For needed Instagram creator context or shortcode verification, selectively use\n   `vidiq_ig_accounts_from_outliers`, `vidiq_ig_profile`, or `vidiq_ig_profile_reels`.\n   Match the target shortcode in returned reels; never assume the first result is the target.\n\n## Verify transfer to Shorts\n\nUse `vidiq_outliers` with `contentType: short` or `vidiq_trending_videos` with\n`videoFormat: short` where the requested language is supported. Outliers rejects non-English\nShorts; use a supported alternative or disclose the gap. YouTube search with\n`type: [\"video\"]` and `videoDuration: short` means under four minutes, not verified Shorts.\nCheck actual format before counting candidates; `vidiq_channel_videos` requires\n`videoFormat: short`.\n\nUse semantic mechanism searches primarily (`requireAllTitleTerms: false` when declared), with\nstrict phrases as supporting evidence. Apply the same relevance gate to YouTube results; a\nbounded search cannot establish that nobody has adopted a mechanism.\n\nExplain which viewer motivation transfers and how opening, reveal, and payoff need adapting.\nCheck dependencies on platform-specific audio, trends, interface, and audience context against\nrelevant watched target examples. Without that evidence, label transfer a hypothesis.\n\n## Deliver original adaptations\n\nReturn the requested patterns/adaptations with source evidence grouped by platform, target-platform\nsupport, production notes, confidence, and contradictions. Keep incomparable platform scores\nseparate. State actual watch status and material coverage limits.\n\nChange subject, wording, examples, visuals, and payoff; use original or appropriately licensed\nfootage/audio, preserving required attribution. Do not copy or reupload source clips. Additional\ngeneration requires a request and relevant source and likeness rights. Voice cloning also\nrequires explicit speaker consent.\n"
}

SHA-256: 607a9e10e3578b975c39c9fe6fedee7c3bdcb5d645cacd4a76bc16dc7d5e4705