Properties
| Name | Type | Description |
|---|---|---|
| run_id | string | |
| kind | string | what the run researches: "short" (hooks from TikTok, Instagram and YouTube Shorts, POST /v1/research), "long" (how long-form YouTube outliers open, POST /v1/longform) or "packaging" (their titles and |
| topic | string | |
| requested | integer | |
| language | object | the language or dialect asked for, as sent, or null for any language |
| country | object | the country asked for, as an ISO 3166-1 alpha-2 code (upper-cased, UK read as GB), or null for any country |
| status | object | |
| error | object | on a failed run: why, ending with the request id |
| reserved | integer | credits held for this run when it started; what it does not use is refunded when it finishes |
| charged | integer | credits deducted from your balance for this run: what it used, never more than `reserved`; 0 while it runs, on a failed run, and on a run that found no hooks within the account's allowance of free emp |
| credits_ig | integer | Instagram provider credits used so far, including on a refunded run; what you pay is `charged` |
| credits_tt | integer | TikTok provider credits used so far, including on a refunded run; what you pay is `charged` |
| credits_yt | object | of credits_tt, the provider credits that went to YouTube Shorts (since 2026-10-01; null on older runs); already inside credits_tt, never added again; what you pay is `charged` |
| posted_within_days | object | the recency window asked for (7, 30, 90 or 365 days), or null |
| seed_hook_ids | object | the seed hooks asked for, or null |
| platforms | object | the platforms this Short form run searches and delivers from ("tiktok", "instagram", "youtube"): the ones asked for, or all three; null on a long or packaging run |
| stats | object | how a finished run went; {} until it finishes. Keys can be added; read the ones you know |
| progress | object | |
| created_at | string | |
| finished_at | object | |
| request_id | object | the X-Request-Id of the call that started it |
| conversation_id | object | the chat conversation this run belongs to, or null for a run started outside one |
| hooks | array | the main deck: clips where a person on camera is talking, ranked. Since 2026-09-29 it never holds a clip without talking; a run that found fewer talking heads than asked says so in `outcome` |
| bonus | array | always empty. Bonus (clips without a person talking) was removed on 2026-10-08; the key stays so existing clients keep working. |
| outcome | object | on a finished run that delivered fewer hooks than asked for (or none): one plain paragraph on why, what to try next, and whether an empty run was free. On a full run whose hooks under the view floor a |
| patterns | object | since 2026-10-01: up to 3 opening structures SHARED by at least two of this deck's hooks (a device, never a topic), from the delivered deck (`hooks`), grouped by `hook_type` in code since 2026-10-02 a |
| understood | object | since 2026-10-04: what the request was understood to ask, read before the first search: the subject searched and judged (hook words such as "controversial hooks about" taken out), its language and cou |
| options | object | long and packaging runs only: the options the request set (min_outlier, intro_seconds, openers, ideas); {} when it set none |
| finds | object | long and packaging runs only (since 2026-10-07): the run's results, ranked, each a real long-form YouTube video that beat its own channel's usual views (`outlier`, never under the run's min_outlier) a |
| report | object | long and packaging runs only, once done; null until then. Long: `patterns`, the opening types at least two of the finds share (hook_type, count, video_ids, template, example); `shape`, how the opening |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/hookdetector-com/json-schema/hookdetector-com-run-out-schema.json",
"title": "RunOut",
"x-generated": "2026-11-11",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/hookdetector-com-openapi.json#/components/schemas/RunOut",
"properties": {
"run_id": {
"type": "string",
"title": "Run Id"
},
"kind": {
"type": "string",
"title": "Kind",
"description": "what the run researches: \"short\" (hooks from TikTok, Instagram and YouTube Shorts, POST /v1/research), \"long\" (how long-form YouTube outliers open, POST /v1/longform) or \"packaging\" (their titles and thumbnails, POST /v1/packaging). Every run from before 2026-10-07 is short",
"default": "short"
},
"topic": {
"type": "string",
"title": "Topic"
},
"requested": {
"type": "integer",
"title": "Requested"
},
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "the language or dialect asked for, as sent, or null for any language"
},
"country": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Country",
"description": "the country asked for, as an ISO 3166-1 alpha-2 code (upper-cased, UK read as GB), or null for any country"
},
"status": {
"anyOf": [
{
"type": "string",
"enum": [
"queued",
"running",
"done",
"failed"
]
},
{
"type": "string"
}
],
"title": "Status"
},
"error": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Error",
"description": "on a failed run: why, ending with the request id"
},
"reserved": {
"type": "integer",
"title": "Reserved",
"description": "credits held for this run when it started; what it does not use is refunded when it finishes"
},
"charged": {
"type": "integer",
"title": "Charged",
"description": "credits deducted from your balance for this run: what it used, never more than `reserved`; 0 while it runs, on a failed run, and on a run that found no hooks within the account's allowance of free empty runs (three a day, 500 credits in all; `outcome` says which)"
},
"credits_ig": {
"type": "integer",
"title": "Credits Ig",
"description": "Instagram provider credits used so far, including on a refunded run; what you pay is `charged`"
},
"credits_tt": {
"type": "integer",
"title": "Credits Tt",
"description": "TikTok provider credits used so far, including on a refunded run; what you pay is `charged`"
},
"credits_yt": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credits Yt",
"description": "of credits_tt, the provider credits that went to YouTube Shorts (since 2026-10-01; null on older runs); already inside credits_tt, never added again; what you pay is `charged`"
},
"posted_within_days": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Posted Within Days",
"description": "the recency window asked for (7, 30, 90 or 365 days), or null"
},
"seed_hook_ids": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Seed Hook Ids",
"description": "the seed hooks asked for, or null"
},
"platforms": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Platforms",
"description": "the platforms this Short form run searches and delivers from (\"tiktok\", \"instagram\", \"youtube\"): the ones asked for, or all three; null on a long or packaging run"
},
"stats": {
"$ref": "#/$defs/RunStats",
"description": "how a finished run went; {} until it finishes. Keys can be added; read the ones you know"
},
"progress": {
"$ref": "#/$defs/ProgressOut"
},
"created_at": {
"type": "string",
"title": "Created At"
},
"finished_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Finished At"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Request Id",
"description": "the X-Request-Id of the call that started it"
},
"conversation_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Conversation Id",
"description": "the chat conversation this run belongs to, or null for a run started outside one"
},
"hooks": {
"items": {
"$ref": "#/$defs/HookOut"
},
"type": "array",
"title": "Hooks",
"description": "the main deck: clips where a person on camera is talking, ranked. Since 2026-09-29 it never holds a clip without talking; a run that found fewer talking heads than asked says so in `outcome`"
},
"bonus": {
"items": {
"$ref": "#/$defs/HookOut"
},
"type": "array",
"title": "Bonus",
"description": "always empty. Bonus (clips without a person talking) was removed on 2026-10-08; the key stays so existing clients keep working.",
"default": []
},
"outcome": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Outcome",
"description": "on a finished run that delivered fewer hooks than asked for (or none): one plain paragraph on why, what to try next, and whether an empty run was free. On a full run whose hooks under the view floor are there because the country filter set most clips aside: that one sentence, with no advice. On a run that asked for a kind of opening, one more sentence: how many hooks open that way. null on any other run"
},
"patterns": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/PatternOut"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Patterns",
"description": "since 2026-10-01: up to 3 opening structures SHARED by at least two of this deck's hooks (a device, never a topic), from the delivered deck (`hooks`), grouped by `hook_type` in code since 2026-10-02 and computed before the run is marked done, in the deck's language, the most shared first and then by the summed virality of their hooks: each `name`, `template` (the structure with {placeholders}), `why` and `hook_ids` (the delivered hooks using it) with `count` (always 2 or more). One cheap model call names the groups; null on older runs, when the call failed on a deck without hook types, and when no structure is shared (then `stats.patterns_note` says so in one line)."
},
"understood": {
"anyOf": [
{
"$ref": "#/$defs/UnderstoodOut"
},
{
"type": "null"
}
],
"description": "since 2026-10-04: what the request was understood to ask, read before the first search: the subject searched and judged (hook words such as \"controversial hooks about\" taken out), its language and country, its core and audience, the neighbours searched beside it, the kinds of opening asked (styles, style_other) and the content asked (wants). Null on older runs and until it is read."
},
"options": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Options",
"description": "long and packaging runs only: the options the request set (min_outlier, intro_seconds, openers, ideas); {} when it set none"
},
"finds": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/FindOut"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Finds",
"description": "long and packaging runs only (since 2026-10-07): the run's results, ranked, each a real long-form YouTube video that beat its own channel's usual views (`outlier`, never under the run's min_outlier) and was posted in 2023 or later. On a long run each carries the video's opening as it was said (`hook`, `intro`) and why it holds; on a packaging run, what its title and thumbnail do together. When the topic was a video's address the one find is that video, whatever its outlier. [] until the run is done: while it runs, the finds written so far are in `progress.items`, as cards"
},
"report": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Report",
"description": "long and packaging runs only, once done; null until then. Long: `patterns`, the opening types at least two of the finds share (hook_type, count, video_ids, template, example); `shape`, how the openings are built, counted from the finds (videos, mapped, hook_seconds, how long the hook runs, and hook_words as medians, beats: each beat with the count of openings using it and the median second it starts_at, and sequence: the order of beats most of them share); and `openers` (hook, then, hook_type, based_on: openings WRITTEN for the subject from those structures, always labelled by `openers_label`, \"Written by Hook Detector from the structure of these real openings\", and never counted as a find). Packaging: `title_patterns` and `thumbnail_patterns` (each name, template or description, why, video_ids, count: what at least two of the packages share), `ideas` (title, thumbnail, thumbnail_text, pattern, based_on: packages WRITTEN for the subject from those patterns, always labelled by `ideas_label`, \"Written by Hook Detector from the patterns in these real packages\", and never counted as a find; an idea over 70 characters, with more than 5 words on its thumbnail, or one that repeats a real title is dropped), `numbers` (the packages counted: title_chars and title_words as medians, titles_with_number, titles_with_question, titles_cut_on_phone (with phone_title_chars, the approximate length a phone cuts a title at), thumbnails_with_text and thumbnail_words over the `analysed` ones, and the title_devices, thumbnail_devices and emotions that repeat, each name and count; and age_cohorts: the same counts for packages posted in the last split_days days (recent) and for older ones, with the undated counted apart) and `playbook_note` (one line when the patterns could not be written). Both kinds: `landscape`, the subject at a glance, counted from the videos the run held against their own channel (videos, channels, bar, outliers and their share, strong, breakouts, small_channel_outliers, recent_outliers, median_views, and beat_2x, beat_5x and beat_10x: how many beat their channel by that much whatever bar the run asked for); null when none was measured"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"run_id",
"topic",
"requested",
"status",
"error",
"reserved",
"charged",
"credits_ig",
"credits_tt",
"stats",
"progress",
"created_at",
"finished_at",
"request_id",
"conversation_id",
"hooks"
],
"$defs": {
"FindOut": {
"properties": {
"find_id": {
"type": "string",
"format": "uuid",
"title": "Find Id",
"description": "the id to keep, reject or read it by; absent on an item of `progress.items`"
},
"run_id": {
"type": "string",
"format": "uuid",
"title": "Run Id",
"description": "the run that found it"
},
"kind": {
"type": "string",
"enum": [
"long",
"packaging"
],
"title": "Kind",
"description": "long or packaging"
},
"rank": {
"type": "integer",
"title": "Rank",
"description": "its place in the run, from 1: the strongest outlier first"
},
"verdict": {
"type": [
"string",
"null"
],
"enum": [
"keep",
"reject",
null
],
"title": "Verdict",
"description": "keep, reject or null"
},
"video_id": {
"type": "string",
"title": "Video Id",
"description": "the YouTube video id"
},
"platform": {
"type": "string",
"title": "Platform",
"description": "always \"youtube\""
},
"title": {
"type": "string",
"title": "Title",
"description": "the video's title as YouTube shows it, word for word (runs of spaces read as one)"
},
"channel": {
"type": [
"string",
"null"
],
"title": "Channel",
"description": "the channel's name"
},
"channel_handle": {
"type": [
"string",
"null"
],
"title": "Channel Handle",
"description": "the channel's @handle, without the @"
},
"watch_url": {
"type": "string",
"title": "Watch Url",
"description": "where to watch it"
},
"player_url": {
"type": "string",
"title": "Player Url",
"description": "an iframe src that plays it (16:9)"
},
"thumbnail_url": {
"type": "string",
"title": "Thumbnail Url",
"description": "the video's thumbnail on YouTube's image host; `thumbnail_urls` lists every size, best first, and a size a video lacks answers 404"
},
"views": {
"type": "integer",
"title": "Views",
"description": "views when the run read it"
},
"likes": {
"type": [
"integer",
"null"
],
"title": "Likes",
"description": "likes, when YouTube gave them"
},
"comments": {
"type": [
"integer",
"null"
],
"title": "Comments",
"description": "comments, when YouTube gave them"
},
"age_days": {
"type": [
"number",
"null"
],
"title": "Age Days",
"description": "days since it was posted, when the run read it"
},
"views_per_day": {
"type": [
"number",
"null"
],
"title": "Views Per Day",
"description": "views divided by age_days"
},
"baseline_videos": {
"type": [
"integer",
"null"
],
"title": "Baseline Videos",
"description": "how many recent uploads the channel's usual was measured on"
},
"found_by": {
"type": [
"string",
"null"
],
"title": "Found By",
"description": "the search that surfaced it"
},
"duration_s": {
"type": [
"integer",
"null"
],
"title": "Duration S",
"description": "length in seconds; always over 180"
},
"posted_at": {
"type": [
"string",
"null"
],
"title": "Posted At",
"description": "when it was posted (ISO 8601). Exact when `posted_exact` is true; otherwise the latest it can be, from YouTube's \"3 months ago\", and never before 2023 either way"
},
"posted_exact": {
"type": "boolean",
"title": "Posted Exact",
"description": "whether posted_at is the real timestamp"
},
"channel_median_views": {
"type": [
"integer",
"null"
],
"title": "Channel Median Views",
"description": "the channel's usual: the median views of its recent long-form uploads"
},
"outlier": {
"type": [
"number",
"null"
],
"title": "Outlier",
"description": "views divided by channel_median_views: 28.2 means 28 times what this channel normally gets"
},
"outlier_score": {
"type": "integer",
"title": "Outlier Score",
"description": "the video on one fixed scale, 0 to 100: the outlier, its reach, how fresh it is and how hard its viewers reacted, placed between two fixed anchors. Nothing else a run found moves it, so finds from different runs rank together; it moves only with the video's own numbers and age"
},
"channel_size": {
"type": [
"string",
"null"
],
"enum": [
"small",
"medium",
"large",
null
],
"title": "Channel Size",
"description": "the channel by what its uploads usually get (channel_median_views): small, medium or large"
},
"seen_before": {
"type": "boolean",
"title": "Seen Before",
"description": "true when an earlier run of yours on this tab already found this video; a keep or reject made then is already on it"
},
"analysis_from_earlier_read": {
"type": "boolean",
"title": "Analysis From Earlier Read",
"description": "true when the opening or the package analysis is the one an earlier run of yours wrote for this video; the numbers are this run's"
},
"channel_id": {
"type": [
"string",
"null"
],
"title": "Channel Id",
"description": "the channel's YouTube id (UC...)"
},
"thumbnail_urls": {
"items": {
"type": "string"
},
"type": "array",
"title": "Thumbnail Urls",
"description": "every thumbnail size, best first; a size a video lacks answers 404"
},
"score": {
"type": [
"number",
"null"
],
"title": "Score",
"description": "the ranking score outlier_score is scaled from"
},
"hook_lines": {
"type": "integer",
"title": "Hook Lines",
"description": "long: how many lines of `intro` the hook reaches, counted from line 1; the last may be only partly the hook, `hook_words` counts exactly"
},
"hook_end_s": {
"type": "number",
"title": "Hook End S",
"description": "long: the second the hook ends, to a tenth, never null. Inside a line it is estimated at the opening's own pace"
},
"hook_start_s": {
"type": "number",
"title": "Hook Start S",
"description": "long: the second the hook starts: 0 or close to it, later when a sponsor read or a greeting came first"
},
"hook_words": {
"type": "integer",
"title": "Hook Words",
"description": "long: the hook's length in words"
},
"auto_captions": {
"type": "boolean",
"title": "Auto Captions",
"description": "long: true when the opening carries almost no punctuation (auto captions): its sentences are not marked and names may be misheard"
},
"about_subject": {
"type": [
"string",
"null"
],
"enum": [
"yes",
"partly",
null
],
"title": "About Subject",
"description": "long: whether the video is about the run's subject, read from its title and opening in the call that analyses it: yes, or partly (the subject is one part of it, or it covers a neighbouring subject). Null when the question was not asked (a channel or video link) or not answered. A video the model answers \"no\" for is never delivered"
},
"hook_type_other": {
"type": [
"string",
"null"
],
"title": "Hook Type Other",
"description": "long: the device in words when hook_type is \"other\""
},
"title_device_other": {
"type": [
"string",
"null"
],
"title": "Title Device Other",
"description": "packaging: the device in words when title_device is \"other\""
},
"multiple": {
"type": [
"number",
"null"
],
"title": "Multiple",
"description": "views over channel_median_views, one decimal: 12.4 means 12.4 times what this channel normally gets (the number 1of10 and vidIQ show). Null when the channel was not measured"
},
"multiple_band": {
"type": [
"string",
"null"
],
"enum": [
"10x",
"5x",
"2x",
"under 2x",
null
],
"title": "Multiple Band",
"description": "the multiple's band: 10x (10 or more), 5x (5 to under 10), 2x (2 to under 5), under 2x (a video asked for by its address, or a bar set under 2); null with no multiple"
},
"content_type": {
"type": [
"string",
"null"
],
"enum": [
"long",
"short",
null
],
"title": "Content Type",
"description": "the kind of video: long (long-form) or short (a YouTube Short)"
},
"outlier_tier": {
"type": [
"string",
"null"
],
"enum": [
"outlier",
"strong",
"breakout",
null
],
"title": "Outlier Tier",
"description": "outlier (under 5 times the channel's usual), strong (5 to 10) or breakout (10 or more)"
},
"likes_per_1k": {
"type": [
"number",
"null"
],
"title": "Likes Per 1K",
"description": "likes for every 1,000 views"
},
"comments_per_1k": {
"type": [
"number",
"null"
],
"title": "Comments Per 1K",
"description": "comments for every 1,000 views"
},
"style_match": {
"type": [
"boolean",
"null"
],
"title": "Style Match",
"description": "when the request asked for a kind of opening or title: whether this one is that kind. Null when it asked for none"
},
"angle": {
"type": [
"string",
"null"
],
"title": "Angle",
"description": "the specific angle the video takes on the subject"
},
"format": {
"type": [
"string",
"null"
],
"title": "Format",
"description": "long: the kind of video, one of talking_head, voiceover, vlog, tutorial, interview, documentary, challenge, review, story, other"
},
"opens_with": {
"type": [
"string",
"null"
],
"title": "Opens With",
"description": "long: how the first seconds begin, one of cold_open, greeting, teaser, question, sponsor, other"
},
"thumbnail_checked": {
"type": "boolean",
"title": "Thumbnail Checked",
"description": "packaging: true when thumbnail_url is the size YouTube really served and the analysis looked at"
},
"thumbnail_sha256": {
"type": "string",
"title": "Thumbnail Sha256",
"description": "packaging: a digest of the picture the analysis looked at; a later run reuses the analysis only while YouTube serves the same picture"
},
"analysed_at": {
"type": "string",
"title": "Analysed At",
"description": "packaging: when the thumbnail was looked at (ISO 8601); a reused analysis keeps its own date"
},
"title_chars": {
"type": "integer",
"title": "Title Chars",
"description": "packaging: the title's length in characters"
},
"cut_on_phone": {
"type": "boolean",
"title": "Cut On Phone",
"description": "packaging: true when the title is longer than 60 characters, where a phone roughly cuts a title. Approximate: YouTube publishes no limit, and the cut moves with the screen, the font and the letters (about 58 to 62)"
},
"thumbnail_text_role": {
"type": [
"string",
"null"
],
"title": "Thumbnail Text Role",
"description": "packaging: how the words on the thumbnail stand to the title, one of repeats_title, adds_to_title, contrasts_title, no_text. Counted in code from `title_overlap` where that can be (repeats_title at 0.7 or more, adds_to_title under 0.3); between, the model's reading"
},
"title_overlap": {
"type": [
"number",
"null"
],
"title": "Title Overlap",
"description": "packaging: the share of the thumbnail's words that are also in the title, 0 to 1, counted in code. null when the thumbnail has no words, or its words are in a script the title does not use"
},
"on_subject": {
"type": [
"string",
"null"
],
"enum": [
"yes",
"partly",
"no",
null
],
"title": "On Subject",
"description": "packaging: whether the look, told the run's subject, judged the package to be about it: yes, or partly (it covers the subject as one part of something broader). A package judged no is never delivered. null when the run was on a channel's or a video's address, when the look gave no usable verdict, or when the analysis is one an earlier run wrote (its subject may have been another)"
},
"thumbnail_faces": {
"type": [
"integer",
"null"
],
"title": "Thumbnail Faces",
"description": "packaging: how many faces the thumbnail shows"
},
"thumbnail_colors": {
"type": [
"string",
"null"
],
"title": "Thumbnail Colors",
"description": "packaging: the colours that carry the frame"
},
"why": {
"type": [
"string",
"null"
],
"title": "Why",
"description": "one line naming the outlier in words"
},
"language": {
"type": [
"string",
"null"
],
"title": "Language",
"description": "the language spoken, as YouTube names the caption track"
},
"analysed": {
"type": "boolean",
"title": "Analysed",
"description": "false when the model could not analyse it: the find is still real, its analysis fields are null"
},
"hook": {
"type": "string",
"title": "Hook",
"description": "long: the hook, verbatim: the lines of `intro` the analysis marks as the hook, cut at the last sentence end that keeps it inside 25 seconds and 60 words, a leading sponsor read or greeting left out. The whole opening is `intro_text`"
},
"hook_seconds": {
"type": [
"number",
"null"
],
"title": "Hook Seconds",
"description": "long: the second the hook ends; the same number as `hook_end_s`, kept for older readers"
},
"intro": {
"items": {
"type": "object"
},
"type": "array",
"title": "Intro",
"description": "long: the opening as it was said, cut by the transcript's own clock: lines of n (from 1), t (start second, null when the transcript had no clock) and text"
},
"intro_text": {
"type": "string",
"title": "Intro Text",
"description": "long: the same words as one string"
},
"intro_seconds": {
"type": "integer",
"title": "Intro Seconds",
"description": "long: how much of the opening was read"
},
"hook_type": {
"type": [
"string",
"null"
],
"title": "Hook Type",
"description": "long: since 2026-10-02: the device the opening uses, one of curiosity_gap, contrarian_claim, specific_number, identity_callout, stakes_threat, promise_payoff, pattern_interrupt, story_open, question, direct_command, other (then `hook_type_other` names it in two to five words). Null on older hooks and when the write-up gave none. A client should treat an unknown value as other."
},
"mechanism": {
"type": [
"string",
"null"
],
"title": "Mechanism",
"description": "long: why the opening holds a viewer, quoting it word for word"
},
"promise": {
"type": [
"string",
"null"
],
"title": "Promise",
"description": "what the viewer is told they will get"
},
"open_loop": {
"type": [
"string",
"null"
],
"title": "Open Loop",
"description": "long: the question the opening leaves unanswered"
},
"title_link": {
"type": [
"string",
"null"
],
"title": "Title Link",
"description": "long: how the first lines pay off the title"
},
"beats": {
"items": {
"type": "object"
},
"type": "array",
"title": "Beats",
"description": "long: the opening in consecutive parts: from and to (line numbers of `intro`), beat (one of hook, stakes, proof, credibility, context, promise, preview, story, payoff, cta, other) and does"
},
"template": {
"type": [
"string",
"null"
],
"title": "Template",
"description": "long: the hook as a fill-in structure with {placeholders}"
},
"steal_it": {
"type": [
"string",
"null"
],
"title": "Steal It",
"description": "how another niche reuses the move"
},
"audience": {
"type": [
"string",
"null"
],
"title": "Audience",
"description": "the viewer it is made for"
},
"title_device": {
"type": [
"string",
"null"
],
"title": "Title Device",
"description": "packaging: the title's device, one of curiosity_gap, contrarian_claim, specific_number, how_to, listicle, challenge, story, question, warning, comparison, authority, timeliness, identity_callout, other"
},
"title_template": {
"type": [
"string",
"null"
],
"title": "Title Template",
"description": "packaging: the title as a fill-in structure with {placeholders}"
},
"thumbnail_text": {
"type": [
"string",
"null"
],
"title": "Thumbnail Text",
"description": "packaging: the words printed on the thumbnail, as a vision model read them; null when none"
},
"thumbnail_subject": {
# --- truncated at 32 KB (87 KB total) ---
# Full source: https://artifacts.apis.io/hookdetector-com/json-schema/hookdetector-com-run-out-schema.json
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/hookdetector-com-run-out"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.