[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXXGFMK7MB5YA50A1X5ATY":3,"skill-same:01M6BXXGFMK7MB5YA50A1X5ATY":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":31,"publishedAt":56,"linkOnly":57,"markdownContent":58,"markdownBody":59,"frontMatter":60,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":12,"ownerDescription":68,"updatedAt":69,"install":70,"resources":83},"01M6BXXGFMK7MB5YA50A1X5ATY","ad-story-loops",null,"Plan the question-and-payoff structure of an ad, promo, product demo or social marketing video so viewers keep watching for a reason and leave with the message: reveals written first, one central question, earned surprise, consequence, closure. Use when a brief asks for retention, hooks, open loops, story loops, curiosity gaps, rehooks, cliffhangers or a series of episodes, or when a cut loses viewers. Pairs with commercial-beat-sheet, explainer-storyboard, motion-ad, ugc-video and script-video, which own the beats and the look.","nodetool-ai\u002Fnodetool","nodetool-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F164873569?v=4","01M6BXPFDW36K9K1MR8ZH63HG2","nodetool.ai","01M6BXPFJ893XM219GQN60B0WK",635,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fad-story-loops\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55],"loops","ad","ad story loops","Story","when","product","beat-sheet","closure","which","retention","consequence","structure","message","social","hooks","question","explainer","marketing","plan","open","Video","first","brief","demo","2026-11-10 10:12:30",false,"---\nname: ad-story-loops\ndescription: \"Plan the question-and-payoff structure of an ad, promo, product demo or social marketing video so viewers keep watching for a reason and leave with the message: reveals written first, one central question, earned surprise, consequence, closure. Use when a brief asks for retention, hooks, open loops, story loops, curiosity gaps, rehooks, cliffhangers or a series of episodes, or when a cut loses viewers. Pairs with commercial-beat-sheet, explainer-storyboard, motion-ad, ugc-video and script-video, which own the beats and the look.\"\n---\n\n# Story loops for ads and marketing video\n\nA story loop is one question the viewer wants answered and the payoff that\nanswers it. This skill produces the **loop map**: which questions the piece\nopens, where each one pays off, and what each payoff changes. Write it before\nthe beat sheet and store it on the board. It decides the order of\ninformation, not the look and not the runtime split.\n\nThe board skill still owns the beats and timecodes: `commercial-beat-sheet`\nfor a spot, `explainer-storyboard` for an explainer, `motion-ad` for a\nsound-off feed ad, `ugc-video` for a creator ad, `script-video` when the\nvoiceover sets the timing. Load the one that fits, plan the loops here, then\nfill its beats in the loop map's order.\n\n## The rule\n\nEvery question the ad opens earns a meaningful answer, and every answer\nchanges what the viewer understands about the product or the problem. A\nreveal that changes nothing is noise. A question that never pays off is bait,\nand the viewer learns not to trust the next one.\n\n## What the evidence supports\n\nUsers bring creator frameworks (Kallaway's Story Loops and Dopamine Ladder,\nPaterson's TAVIN, open loops, the Pixar Story Spine). Use them as writing\nheuristics. None is a validated formula, and \"dopamine\" is not a measurement\nanyone can make on an ad. What controlled research does support:\n\n- Curiosity about a specific, answerable question makes people wait for the\n  answer and remember it better (Loewenstein 1994, Kang et al. 2009, Gruber\n  et al. 2014).\n- Cliffhanger endings raise the stated wish to see the next installment, but\n  not enjoyment or suspense (Media Psychology, 2023). Unfinished stories are\n  not more memorable: a 2025 meta-analysis found no general recall advantage\n  for interrupted tasks.\n- Knowing an outcome can raise enjoyment (Leavitt and Christenfeld 2011).\n  Viewers value how and why something happens, not only what happens, so a\n  piece does not need constant surprise.\n- Absorption in a character's situation (narrative transportation) moves\n  attitudes. Curiosity alone does not carry an ad.\n\nSo: frame claims as questions where it helps, vary the kind and timing of\npayoffs, keep the causal chain readable, and close the central question.\nNever write \"dopamine\" or \"addictive\" into a brief, a report or ad copy as if\nit were a result.\n\n## Write the reveals first\n\n1. **List the true reveals.** One to three facts from the brief or the\n   product page that would make a viewer say \"oh\": a number, a before and\n   after, a mechanism, a trade-off solved. Each must be a confirmed fact. A\n   reveal the brief cannot support is `[CLIENT INPUT NEEDED]`, never invented.\n2. **Name the expectation each reveal overturns.** A surprise only lands when\n   the viewer already holds the expectation it breaks. \"The robot lifts 200\n   kg\" means little. Show it straining at a small box first, and the jump\n   becomes the payoff. The fact stays the same. The setup gives it meaning.\n3. **Work backward to the setup.** For each reveal, write the minimum the\n   viewer must see or know first: the old way, the cost, the failed attempt,\n   the competitor default. That setup is what the early beats show.\n4. **Pick the central question.** One question the whole piece answers, in\n   the viewer's words: \"Can one photo really become a usable ad?\" Everything\n   else is a nested loop under it.\n\n## The seven stages\n\nEach loop moves through stages 2 to 6. A piece runs stage 1 once, repeats\n2 to 6 per loop, and ends on 7. This sequence is a synthesis of the\nframeworks above, not a validated model.\n\n| Stage | Job | On screen |\n|---|---|---|\n| 1. Relevance | Who or what matters, and why to this viewer | The person, the problem or the stake, mid-action |\n| 2. Prediction | A clear, answerable question | The setup the reveal will overturn. A line that names the doubt |\n| 3. Development | Evidence, a choice, or a complication | The attempt, the mechanism, the obstacle |\n| 4. Payoff | The answer, or a real advance on it | The reveal, shown rather than claimed |\n| 5. Consequence | What changed and why it matters | The result in use. The trade-off now solved |\n| 6. Next question | Open a new loop only when another is warranted | A new doubt the payoff created |\n| 7. Satisfaction | Enough closure to earn trust | The central question answered, then the CTA |\n\nConsequence is the stage that separates an ad from a trick: the twist has to\nchange the viewer's picture of the product. Satisfaction is the stage the\nendless-loop model drops. Stop reopening questions and finish.\n\n## Loop budget\n\nStarting points for feed and pre-roll ads, not research results. Adjust to\nthe platform and the product.\n\n| Runtime | Loops | First payoff by |\n|---|---|---|\n| 6–15s | The central question only | ~55% of runtime |\n| 30s | Central question plus one nested loop | ~45% |\n| 60s | Central question plus two nested loops | ~40% |\n| 90s and longer | Central question plus up to four, each closed before the next opens | ~30% |\n\nA payoff held too long frustrates rather than holds. Never have more than two\nloops open at once, and never open a loop in the last 15% of a piece unless it\nis a series hook (below).\n\n## Mapping onto the board skills\n\nFill the board skill's beats in the loop map's order. Typical fits:\n\n| Board skill | Relevance + question | Development | Payoff + consequence | Satisfaction |\n|---|---|---|---|---|\n| `commercial-beat-sheet` | Hook, brand landing | Problem | Solution\u002FUSP, proof | CTA, reiteration, closing echo of the hook |\n| `explainer-storyboard` | Problem, stakes | Shift | Mechanism beats, the aha, outcome\u002Fproof | CTA, sign-off |\n| `motion-ad` | Hook headline over the product in context | Before state, the tap | Before becomes after, proof line | End card |\n| `ugc-video` | Hook to camera | The thing happening physically | The result on the creator | Verdict to camera |\n\n`commercial-beat-sheet`'s \"close every loop you open\" and its hook archetypes\nstill apply. Choose the archetype that sets up the strongest reveal: Result\nFirst and Cost Reveal open a \"how?\" loop, In Media Res Failure and Cold\nContradiction open a \"what went wrong?\" loop.\n\n## Hooks that open a loop, and hooks that only bait\n\nA loop-opening hook names a specific doubt the viewer can hold: \"We tried to\nmake a full product ad from one photo without editing a frame.\" The viewer\nknows the challenge and can predict an outcome.\n\nBait withholds the subject itself: \"You won't believe what happened\", a\nblurred product, a \"wait for it\" with no stake. It raises a question the\nviewer has no reason to care about, and the payoff cannot change their\nunderstanding of anything.\n\nA mid-piece rehook (\"it looked professional, until we noticed one detail\")\nworks only when the detail pays off within a few seconds and matters to the\nbuyer. Do not script a reversal the product's real story does not contain.\n\n## People, not only questions\n\nProduct facts alone rarely move anyone. Give the viewer someone whose goal\nthey understand, the creator, the customer, the team, and show what the\nproduct changes for them. Keep two things apart when writing:\n\n- **Character commitment**: how much the person on screen wants the outcome.\n- **Audience investment**: whether the viewer cares. It comes from\n  recognising the problem as theirs and seeing what is at stake.\n\nA large on-screen sacrifice does nothing if the viewer does not know why it\nmatters. Put the stake in stage 1, in the viewer's terms.\n\n## Series and episodic content\n\nFor a run of marketing videos (a launch week, a build-in-public series, a\nhow-we-made-it set), each episode closes its own central question, then\nopens the next episode's question in the last beat. Cliffhangers raise intent\nto watch the next one. They do not make this one better, and an ad that ends\nunresolved leaves the buyer without the answer the CTA depends on. Use an\nopen ending only when a next episode exists and is scheduled, and still pay\noff the episode's own question first.\n\nAcross episodes, repeat what the viewer can rely on: the same presenter, the\nsame format, answers that arrive. Loyalty to a creator or brand comes from\nconsistent value, expertise and trust, not from escalating suspense.\n\n## Store the loop map on the board\n\nThe loop map lives on the storyboard so a later pass, or a variant, can read\nit:\n\n- Put the whole map in the board `brief` with `create_storyboard` or\n  `edit_storyboard` `set_board {brief}`, under a `LOOP MAP` heading.\n- Tag each shot's loop job in its `notes` field (`add_shot` or `update_shot`):\n  `L1 open: can one photo make a usable ad?`, `L1 payoff`, `L1 consequence`,\n  `central close`. `notes` never enters a render prompt, so it costs nothing\n  in the picture.\n\n```text\nLOOP MAP\nCENTRAL: \u003Cthe question the whole piece answers, in the viewer's words>\nREVEALS: \u003C1–3 confirmed facts, each with its source>\nL1  expectation: \u003Cwhat the viewer assumes>\n    question:    \u003Cthe doubt the shot names>\n    opens:       \u003Ctimecode, shot slug>\n    payoff:      \u003Ctimecode, shot slug, what is shown>\n    consequence: \u003Cwhat the viewer now understands differently>\nL2 ...\nCLOSE: \u003Ctimecode, shot slug, how the central question is answered>\nOPEN AT END: \u003Cnone, or the next episode's question>\n```\n\nThe shot text the renderer reads (`action`, `motion`) still follows the\nchosen model's prompting skill. The loop map changes what each shot shows and\nin which order, not how the prompt is worded.\n\n## Review the cut against the map\n\nAfter assembly, check each loop on the real frames:\n`preview_timeline_frame {timeline_id, times_ms, sheet: true}` at every\nquestion and payoff timecode in the map, then `view_image` on the sheet.\n\n- Is the expectation visible before the reveal? A reveal with no setup on\n  screen is a non-sequitur.\n- Does each payoff arrive by its planned timecode, and is it shown rather\n  than claimed in a super?\n- Is the consequence on screen, the product in use after the reveal?\n- Does the question read muted? On a sound-off feed ad the question is a\n  headline (`caption-titles`), not only voiceover.\n- Is the central question answered before the CTA, and is nothing left open\n  that the brief did not ask to leave open?\n\nName each failure against its loop (`L2 payoff has no setup`), fix the\nboard or the cut, and preview the same timecodes again.\n\n## Worked example: a 45-second product demo\n\nThe central question: can one product photo become a usable, editable ad?\n\n| Time | Stage | Shot |\n|---|---|---|\n| 0–5s | Relevance, L1 question | \"We tried making a full product ad from one photo, without editing a frame.\" The photo on screen |\n| 5–13s | Development, L2 opened | Generation starts. \"It looked surprisingly professional, until we noticed one detail.\" |\n| 13–22s | L2 payoff | The generated ad has changed the product's logo. It looks good and is commercially unusable |\n| 22–34s | Consequence, L3 question | \"So we kept the product untouched and generated only the motion graphics around it.\" The product stays fixed while the graphics move |\n| 34–45s | L1 and L3 payoff, satisfaction | The finished ad beside its editable timeline. The question is answered, the trade-off shown, then the CTA |\n\nEach reveal changes the viewer's understanding of the problem: the obvious\nmethod fails for a reason a buyer cares about, and the fix is the product's\nreal mechanism.\n\n## When the piece is done\n\n`ad-creative-testing` designs the matched variants that show whether a loop\nstructure actually beats a direct version for this product and audience.\nRetention alone is not the result. A cut people finish but do not understand\nor act on has entertained the wrong audience.\n","# Story loops for ads and marketing video\n\nA story loop is one question the viewer wants answered and the payoff that\nanswers it. This skill produces the **loop map**: which questions the piece\nopens, where each one pays off, and what each payoff changes. Write it before\nthe beat sheet and store it on the board. It decides the order of\ninformation, not the look and not the runtime split.\n\nThe board skill still owns the beats and timecodes: `commercial-beat-sheet`\nfor a spot, `explainer-storyboard` for an explainer, `motion-ad` for a\nsound-off feed ad, `ugc-video` for a creator ad, `script-video` when the\nvoiceover sets the timing. Load the one that fits, plan the loops here, then\nfill its beats in the loop map's order.\n\n## The rule\n\nEvery question the ad opens earns a meaningful answer, and every answer\nchanges what the viewer understands about the product or the problem. A\nreveal that changes nothing is noise. A question that never pays off is bait,\nand the viewer learns not to trust the next one.\n\n## What the evidence supports\n\nUsers bring creator frameworks (Kallaway's Story Loops and Dopamine Ladder,\nPaterson's TAVIN, open loops, the Pixar Story Spine). Use them as writing\nheuristics. None is a validated formula, and \"dopamine\" is not a measurement\nanyone can make on an ad. What controlled research does support:\n\n- Curiosity about a specific, answerable question makes people wait for the\n  answer and remember it better (Loewenstein 1994, Kang et al. 2009, Gruber\n  et al. 2014).\n- Cliffhanger endings raise the stated wish to see the next installment, but\n  not enjoyment or suspense (Media Psychology, 2023). Unfinished stories are\n  not more memorable: a 2025 meta-analysis found no general recall advantage\n  for interrupted tasks.\n- Knowing an outcome can raise enjoyment (Leavitt and Christenfeld 2011).\n  Viewers value how and why something happens, not only what happens, so a\n  piece does not need constant surprise.\n- Absorption in a character's situation (narrative transportation) moves\n  attitudes. Curiosity alone does not carry an ad.\n\nSo: frame claims as questions where it helps, vary the kind and timing of\npayoffs, keep the causal chain readable, and close the central question.\nNever write \"dopamine\" or \"addictive\" into a brief, a report or ad copy as if\nit were a result.\n\n## Write the reveals first\n\n1. **List the true reveals.** One to three facts from the brief or the\n   product page that would make a viewer say \"oh\": a number, a before and\n   after, a mechanism, a trade-off solved. Each must be a confirmed fact. A\n   reveal the brief cannot support is `[CLIENT INPUT NEEDED]`, never invented.\n2. **Name the expectation each reveal overturns.** A surprise only lands when\n   the viewer already holds the expectation it breaks. \"The robot lifts 200\n   kg\" means little. Show it straining at a small box first, and the jump\n   becomes the payoff. The fact stays the same. The setup gives it meaning.\n3. **Work backward to the setup.** For each reveal, write the minimum the\n   viewer must see or know first: the old way, the cost, the failed attempt,\n   the competitor default. That setup is what the early beats show.\n4. **Pick the central question.** One question the whole piece answers, in\n   the viewer's words: \"Can one photo really become a usable ad?\" Everything\n   else is a nested loop under it.\n\n## The seven stages\n\nEach loop moves through stages 2 to 6. A piece runs stage 1 once, repeats\n2 to 6 per loop, and ends on 7. This sequence is a synthesis of the\nframeworks above, not a validated model.\n\n| Stage | Job | On screen |\n|---|---|---|\n| 1. Relevance | Who or what matters, and why to this viewer | The person, the problem or the stake, mid-action |\n| 2. Prediction | A clear, answerable question | The setup the reveal will overturn. A line that names the doubt |\n| 3. Development | Evidence, a choice, or a complication | The attempt, the mechanism, the obstacle |\n| 4. Payoff | The answer, or a real advance on it | The reveal, shown rather than claimed |\n| 5. Consequence | What changed and why it matters | The result in use. The trade-off now solved |\n| 6. Next question | Open a new loop only when another is warranted | A new doubt the payoff created |\n| 7. Satisfaction | Enough closure to earn trust | The central question answered, then the CTA |\n\nConsequence is the stage that separates an ad from a trick: the twist has to\nchange the viewer's picture of the product. Satisfaction is the stage the\nendless-loop model drops. Stop reopening questions and finish.\n\n## Loop budget\n\nStarting points for feed and pre-roll ads, not research results. Adjust to\nthe platform and the product.\n\n| Runtime | Loops | First payoff by |\n|---|---|---|\n| 6–15s | The central question only | ~55% of runtime |\n| 30s | Central question plus one nested loop | ~45% |\n| 60s | Central question plus two nested loops | ~40% |\n| 90s and longer | Central question plus up to four, each closed before the next opens | ~30% |\n\nA payoff held too long frustrates rather than holds. Never have more than two\nloops open at once, and never open a loop in the last 15% of a piece unless it\nis a series hook (below).\n\n## Mapping onto the board skills\n\nFill the board skill's beats in the loop map's order. Typical fits:\n\n| Board skill | Relevance + question | Development | Payoff + consequence | Satisfaction |\n|---|---|---|---|---|\n| `commercial-beat-sheet` | Hook, brand landing | Problem | Solution\u002FUSP, proof | CTA, reiteration, closing echo of the hook |\n| `explainer-storyboard` | Problem, stakes | Shift | Mechanism beats, the aha, outcome\u002Fproof | CTA, sign-off |\n| `motion-ad` | Hook headline over the product in context | Before state, the tap | Before becomes after, proof line | End card |\n| `ugc-video` | Hook to camera | The thing happening physically | The result on the creator | Verdict to camera |\n\n`commercial-beat-sheet`'s \"close every loop you open\" and its hook archetypes\nstill apply. Choose the archetype that sets up the strongest reveal: Result\nFirst and Cost Reveal open a \"how?\" loop, In Media Res Failure and Cold\nContradiction open a \"what went wrong?\" loop.\n\n## Hooks that open a loop, and hooks that only bait\n\nA loop-opening hook names a specific doubt the viewer can hold: \"We tried to\nmake a full product ad from one photo without editing a frame.\" The viewer\nknows the challenge and can predict an outcome.\n\nBait withholds the subject itself: \"You won't believe what happened\", a\nblurred product, a \"wait for it\" with no stake. It raises a question the\nviewer has no reason to care about, and the payoff cannot change their\nunderstanding of anything.\n\nA mid-piece rehook (\"it looked professional, until we noticed one detail\")\nworks only when the detail pays off within a few seconds and matters to the\nbuyer. Do not script a reversal the product's real story does not contain.\n\n## People, not only questions\n\nProduct facts alone rarely move anyone. Give the viewer someone whose goal\nthey understand, the creator, the customer, the team, and show what the\nproduct changes for them. Keep two things apart when writing:\n\n- **Character commitment**: how much the person on screen wants the outcome.\n- **Audience investment**: whether the viewer cares. It comes from\n  recognising the problem as theirs and seeing what is at stake.\n\nA large on-screen sacrifice does nothing if the viewer does not know why it\nmatters. Put the stake in stage 1, in the viewer's terms.\n\n## Series and episodic content\n\nFor a run of marketing videos (a launch week, a build-in-public series, a\nhow-we-made-it set), each episode closes its own central question, then\nopens the next episode's question in the last beat. Cliffhangers raise intent\nto watch the next one. They do not make this one better, and an ad that ends\nunresolved leaves the buyer without the answer the CTA depends on. Use an\nopen ending only when a next episode exists and is scheduled, and still pay\noff the episode's own question first.\n\nAcross episodes, repeat what the viewer can rely on: the same presenter, the\nsame format, answers that arrive. Loyalty to a creator or brand comes from\nconsistent value, expertise and trust, not from escalating suspense.\n\n## Store the loop map on the board\n\nThe loop map lives on the storyboard so a later pass, or a variant, can read\nit:\n\n- Put the whole map in the board `brief` with `create_storyboard` or\n  `edit_storyboard` `set_board {brief}`, under a `LOOP MAP` heading.\n- Tag each shot's loop job in its `notes` field (`add_shot` or `update_shot`):\n  `L1 open: can one photo make a usable ad?`, `L1 payoff`, `L1 consequence`,\n  `central close`. `notes` never enters a render prompt, so it costs nothing\n  in the picture.\n\n```text\nLOOP MAP\nCENTRAL: \u003Cthe question the whole piece answers, in the viewer's words>\nREVEALS: \u003C1–3 confirmed facts, each with its source>\nL1  expectation: \u003Cwhat the viewer assumes>\n    question:    \u003Cthe doubt the shot names>\n    opens:       \u003Ctimecode, shot slug>\n    payoff:      \u003Ctimecode, shot slug, what is shown>\n    consequence: \u003Cwhat the viewer now understands differently>\nL2 ...\nCLOSE: \u003Ctimecode, shot slug, how the central question is answered>\nOPEN AT END: \u003Cnone, or the next episode's question>\n```\n\nThe shot text the renderer reads (`action`, `motion`) still follows the\nchosen model's prompting skill. The loop map changes what each shot shows and\nin which order, not how the prompt is worded.\n\n## Review the cut against the map\n\nAfter assembly, check each loop on the real frames:\n`preview_timeline_frame {timeline_id, times_ms, sheet: true}` at every\nquestion and payoff timecode in the map, then `view_image` on the sheet.\n\n- Is the expectation visible before the reveal? A reveal with no setup on\n  screen is a non-sequitur.\n- Does each payoff arrive by its planned timecode, and is it shown rather\n  than claimed in a super?\n- Is the consequence on screen, the product in use after the reveal?\n- Does the question read muted? On a sound-off feed ad the question is a\n  headline (`caption-titles`), not only voiceover.\n- Is the central question answered before the CTA, and is nothing left open\n  that the brief did not ask to leave open?\n\nName each failure against its loop (`L2 payoff has no setup`), fix the\nboard or the cut, and preview the same timecodes again.\n\n## Worked example: a 45-second product demo\n\nThe central question: can one product photo become a usable, editable ad?\n\n| Time | Stage | Shot |\n|---|---|---|\n| 0–5s | Relevance, L1 question | \"We tried making a full product ad from one photo, without editing a frame.\" The photo on screen |\n| 5–13s | Development, L2 opened | Generation starts. \"It looked surprisingly professional, until we noticed one detail.\" |\n| 13–22s | L2 payoff | The generated ad has changed the product's logo. It looks good and is commercially unusable |\n| 22–34s | Consequence, L3 question | \"So we kept the product untouched and generated only the motion graphics around it.\" The product stays fixed while the graphics move |\n| 34–45s | L1 and L3 payoff, satisfaction | The finished ad beside its editable timeline. The question is answered, the trade-off shown, then the CTA |\n\nEach reveal changes the viewer's understanding of the problem: the obvious\nmethod fails for a reason a buyer cares about, and the fix is the product's\nreal mechanism.\n\n## When the piece is done\n\n`ad-creative-testing` designs the matched variants that show whether a loop\nstructure actually beats a direct version for this product and audience.\nRetention alone is not the result. A cut people finish but do not understand\nor act on has entertained the wrong audience.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fad-story-loops",91,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool","https:\u002F\u002Fnodetool.ai\u002F","https:\u002F\u002Fgithub.com\u002Fnodetool-ai","No-code AI development","2026-11-15 03:27:49",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add nodetool-ai\u002Fnodetool --skill ad-story-loops",{"tool":76,"command":77},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill ad-story-loops",{"tool":79,"command":80},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill ad-story-loops","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fad-story-loops\u002FSKILL.md",true,[],[85,94,127,154,169,183],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":93},"01M742MX3Y2ZYK884ZXTRFKB9P","humanizer","Rewrite AI-sounding text so it reads like the writer without changing what it says.\nUse when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line\nclosers, staged openers, forced triads, dashes everywhere, inflated claims, sales\nlanguage, stock AI words, bold labels, or filler.","MIT","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhumanizer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":106,"publishedAt":56},"01M6BY4D93R0Q9400ZHJ04DXP1","nodetool","Use the NodeTool MCP server to build, validate, run, and debug visual AI workflows, and to work with assets, collections, and jobs. Use when the user mentions NodeTool or asks for a workflow graph, a node, or a media generation run on their NodeTool server.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fplugins\u002Fchatgpt\u002Fnodetool\u002Fskills\u002Fnodetool\u002FSKILL.md",[100,103],{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":104,"categoryName":105,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师",[96,107,108,109,36,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126],"MCP","Media","workflows","generation","media generation","with","visual","use","collections","for","node","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":56},"01M6BY4AEB05ZPBRVD078ATR2H","wan-2-6-prompting","Prompt Alibaba's Wan 2.6 video — text-to-video with a global style line plus timing-bracketed shots, and image-to-video that describes only what changes over time. Covers the shot-mode switch per provider, the prompt budget, negative prompts, motion intensity wording, audio input and prompt expansion. Use whenever the model id names a Wan 2.6 video route (alibaba\u002Fwan-2.6\u002Ftext-to-video, alibaba\u002Fwan-2.6\u002Fimage-to-video, wan-video\u002Fwan-2.6-t2v, wan-video\u002Fwan-2.6-i2v, wan-video\u002Fwan2.6-i2v-flash) on generate_video, animate_image or a TextToVideo node. Not for Wan 2.5 or 2.7, or the Wan 2.6 image routes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fwan-2-6-prompting\u002FSKILL.md",[133],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,139,140,141,117,142,143,144,145,146,147,148,149,150,151,152,153,52],"prompting","wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget","generate","text","image","animate","model","Audio",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":162,"publishedAt":56},"01M6BY47T4748ZG5ZMTAR97ZWZ","video-workflow","Build a reusable NodeTool video workflow for batches or repeated inputs. For a single finished piece, use a storyboard skill.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-workflow\u002FSKILL.md",[160,161],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},[126,163,52,164,165,166,167,114,168,96,116],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":56},"01M6BY4587N2SYN315SXGEMZC3","video-clone","Analyze a reference video and recreate its shot structure with a new product or cast in NodeTool.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-clone\u002FSKILL.md",[175],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[177,178,52,112,179,180,96,181,37,43,182],"clone","video clone","cast","new","analyze","reference",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":56},"01M6BY4257C2KQYYMD9EK6DK8E","video-audio-continuity","Keep sound continuous across a multi-scene piece cut from generated video — why one clip per scene hard-cuts the audio at every boundary, when to write all the scenes into a single generation instead, the sound-design vocabulary that survives a provider's copyright filter, and how to check the length, the aspect ratio and the mix of what came back. Use when a piece has more than one scene and the video model writes its own audio (Seedance 2, Veo 3, MiniMax H3, Kling 2.6 and later), or when a cut's sound drops out at the shot changes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-audio-continuity\u002FSKILL.md",[189],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[191,52,153,192,193,194,195,196,197,198,199,200,201,36,202,203,152,204,205,206,207],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]