Update to Picsart
Snapshot Nov 7, 2026 · 00:09 UTC · version 2.4.0
Collection source: downloaded plugin package.
Instructions updated for retention-hooks
Skill instructions — Now says: own: a cold reader of the heard script says whether it does, not you (the speech-aware-cutting skill). | **In the middle** | the result happening, before...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Oct 27, 2026 · 06:06 UTC
own. | **In the middle** | the result happening, before any setup | the shot list rewriting itself | The quality-review skill's viewer panel tests a hook on simulated viewers before anything is paid for.
Nov 7, 2026 · 00:09 UTC
own: a cold reader of the heard script says whether it does, not you (the speech-aware-cutting skill). | **In the middle** | the result happening, before any setup, which lands within the next 3 seconds | the shot list rewriting itself...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -41,7 +41,8 @@ a question, not just sound strong. - **Intensifier:** a sentence right after it that raises the stakes of the same question. - **Rehook:** a sentence that turns: "but", "except", "what nobody tells you", a second problem. - Place it at the middle even when the speaker said it earlier, as long as it stands on its own. + Place it at the middle even when the speaker said it earlier, as long as it stands on its own: + a cold reader of the heard script says whether it does, not you (the speech-aware-cutting skill). - **Payoff:** the sentence that answers the hook. **Never use the payoff as the hook**: it closes the loop before it opens. Lead with the question, end with the answer. @@ -88,7 +89,7 @@ |---|---|---| | **The problem** | a frustration the viewer has had, in their own words | "my AI film had zero close-ups" | | **POV** | the viewer's own situation, in the second person | "POV: your storyboard is all wide shots" | -| **In the middle** | the result happening, before any setup | the shot list rewriting itself | +| **In the middle** | the result happening, before any setup, which lands within the next 3 seconds | the shot list rewriting itself | | **Before and after** | the two states, joined by a hard cut | the wide still, then the close-up | | **The surprise** | something the viewer did not expect to see here | a man in his fifties vaulting a wall for his coffee | @@ -110,7 +111,8 @@ the first, for instance by ending on the problem the hook opened on, now solved. A replay then reads as one continuous video. A serial exit follows drama-series-writing instead. -The quality-review skill's viewer panel tests a hook on simulated viewers before anything is paid for. +The quality-review skill's cold watch tests a hook on the built draft: its first two pieces (to +3 s) say whether strangers who know nothing of the video keep watching. ## Check the loops
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: retention-hooks\ndescription: Keep a short video watched to the end with open loops - a hook that opens a question in the first seconds, an intensifier, a rehook at the middle and a payoff that closes them, whether the lines come from the user's footage or are written for a voice or the screen. Use when ordering the moments of a short cut from talking footage, or writing the lines a short puts on screen or in a voice.\n---\n\n# Story loops\n\nHook, body and payoff tell you where things go. They do not keep anyone watching. What keeps a\nviewer is an **open loop**: a question the video has raised and not yet answered. A short holds as\nlong as one loop is open, and sags wherever none is.\n\nA loop is two moments: the line that **opens** a question and the later one that **closes** it.\nNever open a loop the video cannot close, and never close one before the next is open. A serial\nepisode's exit question follows drama-series-writing instead.\n\n## The three loops\n\n| Loop | Opens | Where | It works when |\n|---|---|---|---|\n| **Hook** | the first question: a result, a contrast, a problem, a claim the viewer wants proved | in the first 2 s | the viewer can say what they are waiting to find out |\n| **Intensifier** | the same question, sharper: a stake, a number, a \"and it gets stranger\", the reason it is harder than it looks | before 15 s, and inside the first quarter of a short under 60 s | it builds on the hook's question instead of starting another |\n| **Rehook** | a new question, just as the first ones start to fade | near the middle, from 35% to 60% of the length | it is new: a second problem, a twist, the part the viewer did not expect, never the hook said again |\n\nThe **payoff** closes the hook's loop, at or near the end. The rehook's loop closes before or with\nit. The serial exit question above may remain open.\n\nScale them to the length:\n\n- **Under 20 s:** the hook and the intensifier. There is no middle to sag; the payoff comes at once.\n- **20–30 s:** all three when the material has a second question; otherwise the hook and the\n intensifier, and say so.\n- **Over 30 s:** all three. Without a rehook the middle loses the viewer.\n\n## Choosing them from footage\n\nWhen the lines come from what people said (a reel, a short, highlights), the loops are chosen, not\nwritten. From the pool of moments:\n\n- **Hook:** the sentence that raises the question the rest answers: a surprising result, a strong\n claim, a problem said plainly. A moment the watch rated `hook` is a candidate; it must still open\n a question, not just sound strong.\n- **Intensifier:** a sentence right after it that raises the stakes of the same question.\n- **Rehook:** a sentence that turns: \"but\", \"except\", \"what nobody tells you\", a second problem.\n Place it at the middle even when the speaker said it earlier, as long as it stands on its own.\n- **Payoff:** the sentence that answers the hook. **Never use the payoff as the hook**: it closes\n the loop before it opens. Lead with the question, end with the answer.\n\nClean sentence edges still come first. A loop never justifies a clip cut mid-sentence.\n\n## Writing them\n\nWhen the lines are written, for the screen or for a voice:\n\n- **Hook:** show the result and hold back how it was made, so the rest of the video answers\n \"how?\".\n- **Intensifier:** the first line after the hook makes the question sharper, with a stake.\n- **Rehook:** the line nearest the middle opens what comes next instead of describing what was:\n the harder request, the step the viewer did not expect.\n- **Payoff:** the last result answers the hook. The call to action comes after it, never instead.\n\nThe writing's own rules still hold: no hype words, nothing the footage does not show.\n\n## The hook\n\nThe hook buys the next two seconds. A viewer stops for something they already feel, never for a\nproduct. Four rules, each one checkable on the hook's frames and words:\n\n1. **Open on a moment or a problem the viewer already feels.** A frustration they have had, a\n result in the middle of happening, a \"before\" they recognise. Never a product shot, or a\n character posed and lit, with a slogan over it: the product comes in as the answer, once the\n viewer has a reason to want one. Giving that reason is the hook's job. If a viewer could not say\n why they should care, it is not a hook yet.\n2. **The words sound like a creator talking.** \"I\" or \"you\", in plain words, the way you would\n tell a friend: \"every shot in my film was a wide\". Never a tagline: no two short lines that\n mirror each other (\"Rough notes in. A pitch deck out.\"), no claim about the product, and no brand\n name in the first second. Read the line aloud, and rewrite it if it sounds like a commercial.\n Sometimes use no words at all. When the picture alone raises the question, let it.\n3. **One promise.** The picture, the words and the payoff promise the same thing. Before\n building, write it as one sentence: \"The viewer sees ___, reads ___, and by the end gets ___.\"\n If one blank pulls a different way, change it. The payoff keeps the promise exactly; a hook\n that promises more than the video shows is bait.\n4. **Native, not produced.** It looks like something a person posted: the real screen, the real\n footage, framed the way a phone frames it. Save the polish for the result.\n\nChoose the opener from what the material holds:\n\n| Opener | It opens on | For example |\n|---|---|---|\n| **The problem** | a frustration the viewer has had, in their own words | \"my AI film had zero close-ups\" |\n| **POV** | the viewer's own situation, in the second person | \"POV: your storyboard is all wide shots\" |\n| **In the middle** | the result happening, before any setup | the shot list rewriting itself |\n| **Before and after** | the two states, joined by a hard cut | the wide still, then the close-up |\n| **The surprise** | something the viewer did not expect to see here | a man in his fifties vaulting a wall for his coffee |\n\n### Ad tells\n\nAny one of these makes a short read as an ad, and the viewer scrolls past it:\n\n- the first frame is a product, or a character posed and lit like a commercial, with words over it;\n- a slogan: two lines that mirror each other, a benefit claim, a rhyme;\n- a brand, a logo or an app name in the first second;\n- a feature named before the viewer has a reason to want it (\"New:\", \"Introducing\");\n- words that grade the product (amazing, effortless, game-changing), a \"!\", or a price;\n- a call to action before the payoff, or one that interrupts it;\n- a voice that announces from a script instead of telling;\n- studio polish on the opener: perfect light, a seamless backdrop, a staged lifestyle shot;\n- more to read in the first 2 s than one short line.\n\n**The ending loops back.** When the video ends without a call to action, its last frame leads into\nthe first, for instance by ending on the problem the hook opened on, now solved. A replay then\nreads as one continuous video. A serial exit follows drama-series-writing instead.\n\nThe quality-review skill's viewer panel tests a hook on simulated viewers before anything is paid for.\n\n## Check the loops\n\nBefore the plan goes to the user, list each loop in one line: what it opens, the second it opens,\nthe second it closes. Then read it back:\n\n- Does a loop open in the first 2 s?\n- Is some loop open at every second until the payoff, or is there a stretch where the viewer has\n nothing left to wait for?\n- Does every loop close? A serial exit question may stay open.\n- Does the hook break none of the four rules above, and use none of the ad tells?\n\nA missing loop is a note, not a block: when the material has no second question, build without a\nrehook and say so in one line.\n"
"---\nname: retention-hooks\ndescription: Keep a short video watched to the end with open loops - a hook that opens a question in the first seconds, an intensifier, a rehook at the middle and a payoff that closes them, whether the lines come from the user's footage or are written for a voice or the screen. Use when ordering the moments of a short cut from talking footage, or writing the lines a short puts on screen or in a voice.\n---\n\n# Story loops\n\nHook, body and payoff tell you where things go. They do not keep anyone watching. What keeps a\nviewer is an **open loop**: a question the video has raised and not yet answered. A short holds as\nlong as one loop is open, and sags wherever none is.\n\nA loop is two moments: the line that **opens** a question and the later one that **closes** it.\nNever open a loop the video cannot close, and never close one before the next is open. A serial\nepisode's exit question follows drama-series-writing instead.\n\n## The three loops\n\n| Loop | Opens | Where | It works when |\n|---|---|---|---|\n| **Hook** | the first question: a result, a contrast, a problem, a claim the viewer wants proved | in the first 2 s | the viewer can say what they are waiting to find out |\n| **Intensifier** | the same question, sharper: a stake, a number, a \"and it gets stranger\", the reason it is harder than it looks | before 15 s, and inside the first quarter of a short under 60 s | it builds on the hook's question instead of starting another |\n| **Rehook** | a new question, just as the first ones start to fade | near the middle, from 35% to 60% of the length | it is new: a second problem, a twist, the part the viewer did not expect, never the hook said again |\n\nThe **payoff** closes the hook's loop, at or near the end. The rehook's loop closes before or with\nit. The serial exit question above may remain open.\n\nScale them to the length:\n\n- **Under 20 s:** the hook and the intensifier. There is no middle to sag; the payoff comes at once.\n- **20–30 s:** all three when the material has a second question; otherwise the hook and the\n intensifier, and say so.\n- **Over 30 s:** all three. Without a rehook the middle loses the viewer.\n\n## Choosing them from footage\n\nWhen the lines come from what people said (a reel, a short, highlights), the loops are chosen, not\nwritten. From the pool of moments:\n\n- **Hook:** the sentence that raises the question the rest answers: a surprising result, a strong\n claim, a problem said plainly. A moment the watch rated `hook` is a candidate; it must still open\n a question, not just sound strong.\n- **Intensifier:** a sentence right after it that raises the stakes of the same question.\n- **Rehook:** a sentence that turns: \"but\", \"except\", \"what nobody tells you\", a second problem.\n Place it at the middle even when the speaker said it earlier, as long as it stands on its own:\n a cold reader of the heard script says whether it does, not you (the speech-aware-cutting skill).\n- **Payoff:** the sentence that answers the hook. **Never use the payoff as the hook**: it closes\n the loop before it opens. Lead with the question, end with the answer.\n\nClean sentence edges still come first. A loop never justifies a clip cut mid-sentence.\n\n## Writing them\n\nWhen the lines are written, for the screen or for a voice:\n\n- **Hook:** show the result and hold back how it was made, so the rest of the video answers\n \"how?\".\n- **Intensifier:** the first line after the hook makes the question sharper, with a stake.\n- **Rehook:** the line nearest the middle opens what comes next instead of describing what was:\n the harder request, the step the viewer did not expect.\n- **Payoff:** the last result answers the hook. The call to action comes after it, never instead.\n\nThe writing's own rules still hold: no hype words, nothing the footage does not show.\n\n## The hook\n\nThe hook buys the next two seconds. A viewer stops for something they already feel, never for a\nproduct. Four rules, each one checkable on the hook's frames and words:\n\n1. **Open on a moment or a problem the viewer already feels.** A frustration they have had, a\n result in the middle of happening, a \"before\" they recognise. Never a product shot, or a\n character posed and lit, with a slogan over it: the product comes in as the answer, once the\n viewer has a reason to want one. Giving that reason is the hook's job. If a viewer could not say\n why they should care, it is not a hook yet.\n2. **The words sound like a creator talking.** \"I\" or \"you\", in plain words, the way you would\n tell a friend: \"every shot in my film was a wide\". Never a tagline: no two short lines that\n mirror each other (\"Rough notes in. A pitch deck out.\"), no claim about the product, and no brand\n name in the first second. Read the line aloud, and rewrite it if it sounds like a commercial.\n Sometimes use no words at all. When the picture alone raises the question, let it.\n3. **One promise.** The picture, the words and the payoff promise the same thing. Before\n building, write it as one sentence: \"The viewer sees ___, reads ___, and by the end gets ___.\"\n If one blank pulls a different way, change it. The payoff keeps the promise exactly; a hook\n that promises more than the video shows is bait.\n4. **Native, not produced.** It looks like something a person posted: the real screen, the real\n footage, framed the way a phone frames it. Save the polish for the result.\n\nChoose the opener from what the material holds:\n\n| Opener | It opens on | For example |\n|---|---|---|\n| **The problem** | a frustration the viewer has had, in their own words | \"my AI film had zero close-ups\" |\n| **POV** | the viewer's own situation, in the second person | \"POV: your storyboard is all wide shots\" |\n| **In the middle** | the result happening, before any setup, which lands within the next 3 seconds | the shot list rewriting itself |\n| **Before and after** | the two states, joined by a hard cut | the wide still, then the close-up |\n| **The surprise** | something the viewer did not expect to see here | a man in his fifties vaulting a wall for his coffee |\n\n### Ad tells\n\nAny one of these makes a short read as an ad, and the viewer scrolls past it:\n\n- the first frame is a product, or a character posed and lit like a commercial, with words over it;\n- a slogan: two lines that mirror each other, a benefit claim, a rhyme;\n- a brand, a logo or an app name in the first second;\n- a feature named before the viewer has a reason to want it (\"New:\", \"Introducing\");\n- words that grade the product (amazing, effortless, game-changing), a \"!\", or a price;\n- a call to action before the payoff, or one that interrupts it;\n- a voice that announces from a script instead of telling;\n- studio polish on the opener: perfect light, a seamless backdrop, a staged lifestyle shot;\n- more to read in the first 2 s than one short line.\n\n**The ending loops back.** When the video ends without a call to action, its last frame leads into\nthe first, for instance by ending on the problem the hook opened on, now solved. A replay then\nreads as one continuous video. A serial exit follows drama-series-writing instead.\n\nThe quality-review skill's cold watch tests a hook on the built draft: its first two pieces (to\n3 s) say whether strangers who know nothing of the video keep watching.\n\n## Check the loops\n\nBefore the plan goes to the user, list each loop in one line: what it opens, the second it opens,\nthe second it closes. Then read it back:\n\n- Does a loop open in the first 2 s?\n- Is some loop open at every second until the payoff, or is there a stretch where the viewer has\n nothing left to wait for?\n- Does every loop close? A serial exit question may stay open.\n- Does the hook break none of the four rules above, and use none of the ad tells?\n\nA missing loop is a note, not a block: when the material has no second question, build without a\nrehook and say so in one line.\n"
Full snapshot data
{
"description": "Keep a short video watched to the end with open loops - a hook that opens a question in the first seconds, an intensifier, a rehook at the middle and a payoff that closes them, whether the lines come from the user's footage or are written for a voice or the screen. Use when ordering the moments of a short cut from talking footage, or writing the lines a short puts on screen or in a voice.",
"included_files": [],
"name": "retention-hooks",
"skill_md_contents": "---\nname: retention-hooks\ndescription: Keep a short video watched to the end with open loops - a hook that opens a question in the first seconds, an intensifier, a rehook at the middle and a payoff that closes them, whether the lines come from the user's footage or are written for a voice or the screen. Use when ordering the moments of a short cut from talking footage, or writing the lines a short puts on screen or in a voice.\n---\n\n# Story loops\n\nHook, body and payoff tell you where things go. They do not keep anyone watching. What keeps a\nviewer is an **open loop**: a question the video has raised and not yet answered. A short holds as\nlong as one loop is open, and sags wherever none is.\n\nA loop is two moments: the line that **opens** a question and the later one that **closes** it.\nNever open a loop the video cannot close, and never close one before the next is open. A serial\nepisode's exit question follows drama-series-writing instead.\n\n## The three loops\n\n| Loop | Opens | Where | It works when |\n|---|---|---|---|\n| **Hook** | the first question: a result, a contrast, a problem, a claim the viewer wants proved | in the first 2 s | the viewer can say what they are waiting to find out |\n| **Intensifier** | the same question, sharper: a stake, a number, a \"and it gets stranger\", the reason it is harder than it looks | before 15 s, and inside the first quarter of a short under 60 s | it builds on the hook's question instead of starting another |\n| **Rehook** | a new question, just as the first ones start to fade | near the middle, from 35% to 60% of the length | it is new: a second problem, a twist, the part the viewer did not expect, never the hook said again |\n\nThe **payoff** closes the hook's loop, at or near the end. The rehook's loop closes before or with\nit. The serial exit question above may remain open.\n\nScale them to the length:\n\n- **Under 20 s:** the hook and the intensifier. There is no middle to sag; the payoff comes at once.\n- **20–30 s:** all three when the material has a second question; otherwise the hook and the\n intensifier, and say so.\n- **Over 30 s:** all three. Without a rehook the middle loses the viewer.\n\n## Choosing them from footage\n\nWhen the lines come from what people said (a reel, a short, highlights), the loops are chosen, not\nwritten. From the pool of moments:\n\n- **Hook:** the sentence that raises the question the rest answers: a surprising result, a strong\n claim, a problem said plainly. A moment the watch rated `hook` is a candidate; it must still open\n a question, not just sound strong.\n- **Intensifier:** a sentence right after it that raises the stakes of the same question.\n- **Rehook:** a sentence that turns: \"but\", \"except\", \"what nobody tells you\", a second problem.\n Place it at the middle even when the speaker said it earlier, as long as it stands on its own:\n a cold reader of the heard script says whether it does, not you (the speech-aware-cutting skill).\n- **Payoff:** the sentence that answers the hook. **Never use the payoff as the hook**: it closes\n the loop before it opens. Lead with the question, end with the answer.\n\nClean sentence edges still come first. A loop never justifies a clip cut mid-sentence.\n\n## Writing them\n\nWhen the lines are written, for the screen or for a voice:\n\n- **Hook:** show the result and hold back how it was made, so the rest of the video answers\n \"how?\".\n- **Intensifier:** the first line after the hook makes the question sharper, with a stake.\n- **Rehook:** the line nearest the middle opens what comes next instead of describing what was:\n the harder request, the step the viewer did not expect.\n- **Payoff:** the last result answers the hook. The call to action comes after it, never instead.\n\nThe writing's own rules still hold: no hype words, nothing the footage does not show.\n\n## The hook\n\nThe hook buys the next two seconds. A viewer stops for something they already feel, never for a\nproduct. Four rules, each one checkable on the hook's frames and words:\n\n1. **Open on a moment or a problem the viewer already feels.** A frustration they have had, a\n result in the middle of happening, a \"before\" they recognise. Never a product shot, or a\n character posed and lit, with a slogan over it: the product comes in as the answer, once the\n viewer has a reason to want one. Giving that reason is the hook's job. If a viewer could not say\n why they should care, it is not a hook yet.\n2. **The words sound like a creator talking.** \"I\" or \"you\", in plain words, the way you would\n tell a friend: \"every shot in my film was a wide\". Never a tagline: no two short lines that\n mirror each other (\"Rough notes in. A pitch deck out.\"), no claim about the product, and no brand\n name in the first second. Read the line aloud, and rewrite it if it sounds like a commercial.\n Sometimes use no words at all. When the picture alone raises the question, let it.\n3. **One promise.** The picture, the words and the payoff promise the same thing. Before\n building, write it as one sentence: \"The viewer sees ___, reads ___, and by the end gets ___.\"\n If one blank pulls a different way, change it. The payoff keeps the promise exactly; a hook\n that promises more than the video shows is bait.\n4. **Native, not produced.** It looks like something a person posted: the real screen, the real\n footage, framed the way a phone frames it. Save the polish for the result.\n\nChoose the opener from what the material holds:\n\n| Opener | It opens on | For example |\n|---|---|---|\n| **The problem** | a frustration the viewer has had, in their own words | \"my AI film had zero close-ups\" |\n| **POV** | the viewer's own situation, in the second person | \"POV: your storyboard is all wide shots\" |\n| **In the middle** | the result happening, before any setup, which lands within the next 3 seconds | the shot list rewriting itself |\n| **Before and after** | the two states, joined by a hard cut | the wide still, then the close-up |\n| **The surprise** | something the viewer did not expect to see here | a man in his fifties vaulting a wall for his coffee |\n\n### Ad tells\n\nAny one of these makes a short read as an ad, and the viewer scrolls past it:\n\n- the first frame is a product, or a character posed and lit like a commercial, with words over it;\n- a slogan: two lines that mirror each other, a benefit claim, a rhyme;\n- a brand, a logo or an app name in the first second;\n- a feature named before the viewer has a reason to want it (\"New:\", \"Introducing\");\n- words that grade the product (amazing, effortless, game-changing), a \"!\", or a price;\n- a call to action before the payoff, or one that interrupts it;\n- a voice that announces from a script instead of telling;\n- studio polish on the opener: perfect light, a seamless backdrop, a staged lifestyle shot;\n- more to read in the first 2 s than one short line.\n\n**The ending loops back.** When the video ends without a call to action, its last frame leads into\nthe first, for instance by ending on the problem the hook opened on, now solved. A replay then\nreads as one continuous video. A serial exit follows drama-series-writing instead.\n\nThe quality-review skill's cold watch tests a hook on the built draft: its first two pieces (to\n3 s) say whether strangers who know nothing of the video keep watching.\n\n## Check the loops\n\nBefore the plan goes to the user, list each loop in one line: what it opens, the second it opens,\nthe second it closes. Then read it back:\n\n- Does a loop open in the first 2 s?\n- Is some loop open at every second until the payoff, or is there a stretch where the viewer has\n nothing left to wait for?\n- Does every loop close? A serial exit question may stay open.\n- Does the hook break none of the four rules above, and use none of the ad tells?\n\nA missing loop is a note, not a block: when the material has no second question, build without a\nrehook and say so in one line.\n"
}SHA-256 of public snapshot: 010633096099022c7293cd532e04ac8a56c14b12ceb00ebf658c5b33146ce01a