[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY0BGVZGA4F46ZY8AA6D41":3,"skill-same:01M6BY0BGVZGA4F46ZY8AA6D41":78},{"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":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":12,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6BY0BGVZGA4F46ZY8AA6D41","logo-reveal",null,"Animate a brand mark on a NodeTool timeline — stroke draw-on, mask wipe, staggered build, wordmark type, an idle loop, and landing the settle on a sound logo. Use for an intro sting, a sign-off, an end card, a splash, or a loader loop. Not for designing the mark itself.","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\u002Flogo-reveal\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"logo","logo reveal","reveal","settle","timeline","draw-on","for","splash","mask","mark","card","type","end","build","use","landing","intro","brand","nodetool","animate","loop","2026-11-10 10:12:30",false,"---\nname: logo-reveal\ndescription: Animate a brand mark on a NodeTool timeline — stroke draw-on, mask wipe, staggered build, wordmark type, an idle loop, and landing the settle on a sound logo. Use for an intro sting, a sign-off, an end card, a splash, or a loader loop. Not for designing the mark itself.\n---\n\n# Logo Reveal → the sting\n\nOne idea per logo. Draw it, build it, or wipe it — never all three. The whole\nreveal runs 800–2500ms and ends on the clean mark, held.\n\n`motion-graphics` is the build loop; `timeline-edit-ops` carries the op\ncontract. `motion-direction` decides which personality the sting belongs to;\na logo is usually the one place a piece is allowed its overshoot.\n\n## The same three patterns, in code\n\n**Draw-on** — a path element and `el.draw()`, which is `enter({from: {trimEnd: 0}})`:\n\n```js\n\u002F\u002F fragment\nconst mark = s.path([[\"M\", -40, 30], [\"L\", 0, -30], [\"L\", 40, 30]], { stroke: \"#111111\" });\nmark.draw({ dur: 1.1, ease: \"cubic-bezier(0.65,0,0.35,1)\" });\n```\n\n**Wordmark stagger** — `by` and `staggerMs` on `el.enter()`, per character for\na short mark:\n\n```js\n\u002F\u002F fragment\nconst wordmark = s.text(\"Northwind\", { size: 64, weight: 700 });\nwordmark.enter({ from: { scale: 0.9, opacity: 0 }, dur: 0.38, by: \"character\", staggerMs: 45 });\n```\n\n**Lockup row** — mark beside wordmark, one flex container (`frame-composition`\ncovers the container vocabulary in full):\n\n```js\n\u002F\u002F fragment\ns.row([mark, wordmark], { gap: 16, align: \"center\" });\n```\n\nReveal the container first if the mark and wordmark should feel like one\nbuild, or stagger the row's own children through `s.stagger()` for a build-on\nthat still keeps its lockup spacing.\n\n## Pick one technique\n\n| Technique | Best for | How, on the timeline |\n|---|---|---|\n| Stroke draw-on | Line marks, monograms, signatures | A `path` shape clip, `trimStart`\u002F`trimEnd` animated |\n| Mask wipe | Filled shapes, gradient marks | `wipe` preset, or a `set_mask` rect whose `mask.width` (or `x`) a document `styleTracks` entry animates |\n| Build-on | Multi-part marks, grids | One clip per part, in a group, `delayMs` staggered |\n| Wordmark | Logotypes | A text clip with a per-character or per-word `stagger` |\n| Idle loop | Loaders, ambient splash | `breathe` or `rotate` as a `loop` |\n| Scale settle | Anything, when in doubt | `pop` with a small `overshoot` |\n\n## Stroke draw-on\n\n`trimStart` and `trimEnd` stroke only a sub-range of a path, 0..1. Drawing is\n`trimEnd` running 0 to 1 with the stroke visible and the fill arriving after:\n\n```json\n{\"op\": \"add_shape_clip\", \"shape\": {\"kind\": \"path\", \"d\": \"M0.1 0.7 L0.3 0.2 L0.5 0.7\",\n \"stroke\": \"#111111\", \"strokeWidthPx\": 6, \"lineCap\": \"round\",\n \"trimStart\": 0, \"trimEnd\": 0}, \"durationMs\": 2000}\n```\n\n```json\n{\"op\": \"animate_clip\", \"target\": \"Path\", \"animations\": [\n  {\"role\": \"in\", \"preset\": \"custom\", \"durationMs\": 1100,\n   \"easing\": \"cubic-bezier(0.65,0,0.35,1)\",\n   \"curves\": [{\"property\": \"trimEnd\", \"keyframes\": [\n     {\"t\": 0, \"value\": 0}, {\"t\": 1, \"value\": 1}]}]}]}\n```\n\nBoth trim channels fold as **replace**: one animation drives one of them, and two\noverlapping in time means the later wins and the earlier is discarded, reported\nas `replace_curves_overlap`. Draw with `trimEnd` alone; use `trimStart` chasing\nit only for a stroke that draws and erases, and put the two in separate windows.\n\nStagger several strokes by stepping each path clip's `delayMs` by the\nclip-to-clip stagger in `motion-principles`, in the order a hand would draw\nthem.\n\n`add_shape_clip` stores a path's `d` without parsing it. A `d` the renderer\ncannot parse reports `shape_path_invalid` (an error) from `validate_timeline`,\nand an unknown `kind` reports `unknown_shape_kind`. Either draws nothing — a\nmark that vanished is usually one of those two.\n\n## Mask wipe\n\nFor a filled mark, reveal rather than draw. `{\"role\": \"in\", \"preset\": \"wipe\",\n\"durationMs\": 700, \"params\": {\"direction\": \"left\", \"softness\": 0.05}}` sweeps a\nfeathered edge across the layer. `softness` 0 is a hard edge, which reads as\ngraphic; 0.1 reads as light passing over.\n\nA `custom` curve driving `wipeProgress` needs a `mask` on the same animation —\n`{direction, softness}` — because a wipe with no edge to run against cannot be\ninferred. `wipeProgress` folds as **min**, so two wipes on one layer keep the\ntighter one.\n\n## Build-on\n\nOne clip per part, each on its own overlay track, all parented to one group with\n`add_group`. Reveal the container first, then accents, then the wordmark last so\nthe eye lands on the name.\n\n```json\n{\"op\": \"animate_clip\", \"target\": \"Mark part 2\", \"animations\": [\n  {\"role\": \"in\", \"preset\": \"pop\", \"durationMs\": 500, \"delayMs\": 80,\n   \"params\": {\"overshoot\": 1.12}}]}\n```\n\nStep by the clip-to-clip stagger in `motion-principles`, as the 80ms\n`delayMs` on the second part does. Then animate the **group** for anything that moves the whole\nassembly — one `fade` out on the group beats three chances for the parts to\ndrift apart. The group's opacity multiplies into each child.\n\nWhen the parts already have animations, `{\"op\": \"stagger_animations\",\n\"clip_ids\": [\"mark-id\", \"wordmark-id\", \"tagline-id\"], \"offset_ms\": 80}`\nadds delay in that order without moving their media. Use clip IDs, with at\nleast two, and give every selected clip an animation first. The first keeps\nits delay. For a repeating field of identical marks, the document's\n`repeater` sets copy count, position step, and time step on one clip. Use a\nrepeater for a pattern, and separate clips for parts that need distinct art.\n\nKeep a follower aligned by storing `animationLinks` on its clip when it should\nread the mark's position, scale, rotation, or opacity. A link follows the\nsource's authored animation and does not chain through other links. Put the mark and the wordmark in a flex row (`layout: {display: \"flex\",\nflexDirection: \"row\", gap, alignItems: \"center\"}` on a group clip, both as\nits real children via `parentId`) so the wordmark's position follows the\nmark's changing box; a backing plate is a third child with `flexItem:\n{position: \"absolute\", inset: 0}` behind the wordmark. These are document\nfields, so read and write the full document with `get_timeline` and\n`set_timeline_document`.\n`set_clip_params` refuses `repeater`, `animationLinks`, and `layout`.\n\n## Wordmark\n\nA text clip with a stagger. Per character for a short mark, per word for a\nlockup with a tagline:\n\n```json\n{\"role\": \"in\", \"preset\": \"pop\", \"durationMs\": 380,\n \"stagger\": {\"unit\": \"character\", \"offsetMs\": 45, \"from\": \"start\"}}\n```\n\nWork the span out — `durationMs + offsetMs × (units − 1)` — and compare it\nagainst the clip. A span that does not fit is compressed silently, and a\ncompressed wordmark is the reason a reveal \"does not look staggered\".\n`stagger_compressed` is the warning.\n\nSet the family to a bundled one — `Inter`, `Space Grotesk`, `Bebas Neue`,\n`Playfair Display`, `Lora`, `JetBrains Mono` — or the render and the editor\nresolve it differently and the lockup's width changes under you.\n\n## What not to do to a mark\n\nScale, opacity, rotation about the mark's own anchor, and position are safe.\n`scaleX` and `scaleY` on their own are not: `squash` distorts the geometry, and a\ndistorted logo is a brand problem rather than a taste one. Keep motion out of the\nclearspace — a support element sliding through the mark's margin cheapens it.\n\n## Landing on a sound logo\n\nDecide the audio first. A sound logo that does not exist yet is a 1–3 s\neffects brief — source, action, space — on ElevenLabs sound effects\n(`elevenlabs-audio-prompting`) or a `TrackType: SFX` prompt on Stable Audio\n(`stable-audio-prompting`); a 30-second request for a hit is a hit followed by\nroom tone. Then `detect_audio_events` on the sting reports `onsets.times` in\n**seconds**; multiply by 1000. Time the reveal so the mark reaches full opacity\nand scale on that millisecond:\n\n`delayMs` on the `in` animation = onset ms − the clip's `startMs` −\n`durationMs`. Then add the accent on the hit itself, as a separate emphasis:\n`{\"role\": \"emphasis\", \"preset\": \"pulse\", \"durationMs\": 220, \"delayMs\": \u003Conset −\nstartMs>, \"params\": {\"intensity\": 0.04}}`.\n\nA settle that floats free of the sound reads as cheap even when both are good.\n`snap_to_beats` is the blunt version when the whole end card has to sit on the\ngrid.\n\nFor a mark that should stay on beat if the sequence tempo changes, put a\n`beat: {index, scope: \"sequence\", offsetMs?}` anchor on its animation in the\nfull document. The index is one-based and `delayMs` adds to it. The\n`animate_clip` tool input does not accept `beat`. Keep the stored animation's\n`id`, `role`, `preset`, and `durationMs` when adding it. If the sound logo's measured\nonset is the source of truth, keep the absolute delay or use\n`bake_audio_animation` for audio-driven motion instead.\n\n## Idle loop\n\nFor a loader or a splash that waits, a `loop` at low amplitude: `breathe` with\n`intensity` 0.02–0.04, or `rotate` on a mark that is radially symmetric. Set\n`durationMs` to the cycle, 2000–4000ms, and remember a cycle longer than the clip\nshows a fragment of the motion.\n\nNever loop a wordmark somebody is reading.\n\n## Hold the end frame\n\nThe last thing on screen is the static mark. Leave the end hold\n`motion-principles` sets (at least 1000ms) after the reveal completes with\nnothing animating — an end card that cuts the instant it\nsettles reads as a mistake. On a 2500ms clip with a 1100ms draw and a 220ms\naccent, that is satisfied; check it rather than assuming.\n\n## Start from a rig when it fits\n\n`list_compositions` and `get_composition` show the shipped `logo-sting` rig and\nits parameters. `insert_composition` places it as a group with fresh clip IDs.\nInspect those IDs before changing its timing or staggering its parts. Use the\n`title-slam` or `word-cards` examples for a typographic reveal; they are\nstarting documents rather than tool presets.\n\n## Check it\n\n- `validate_timeline`: `replace_curves_overlap` on the trims, `stagger_compressed`\n  on the wordmark, `animation_exceeds_clip` on a reveal longer than its clip,\n  `shape_path_invalid` or `unknown_shape_kind` on a mark that draws nothing.\n- `preview_timeline_frame` at the midpoint of the draw, a held moment, and the\n  last frame. The midpoint is where a half-drawn path or a stroke that never\n  closes shows up; the last frame is where you confirm the mark is clean and\n  complete.\n- Then `render_timeline`, because a sting is judged at speed.\n","# Logo Reveal → the sting\n\nOne idea per logo. Draw it, build it, or wipe it — never all three. The whole\nreveal runs 800–2500ms and ends on the clean mark, held.\n\n`motion-graphics` is the build loop; `timeline-edit-ops` carries the op\ncontract. `motion-direction` decides which personality the sting belongs to;\na logo is usually the one place a piece is allowed its overshoot.\n\n## The same three patterns, in code\n\n**Draw-on** — a path element and `el.draw()`, which is `enter({from: {trimEnd: 0}})`:\n\n```js\n\u002F\u002F fragment\nconst mark = s.path([[\"M\", -40, 30], [\"L\", 0, -30], [\"L\", 40, 30]], { stroke: \"#111111\" });\nmark.draw({ dur: 1.1, ease: \"cubic-bezier(0.65,0,0.35,1)\" });\n```\n\n**Wordmark stagger** — `by` and `staggerMs` on `el.enter()`, per character for\na short mark:\n\n```js\n\u002F\u002F fragment\nconst wordmark = s.text(\"Northwind\", { size: 64, weight: 700 });\nwordmark.enter({ from: { scale: 0.9, opacity: 0 }, dur: 0.38, by: \"character\", staggerMs: 45 });\n```\n\n**Lockup row** — mark beside wordmark, one flex container (`frame-composition`\ncovers the container vocabulary in full):\n\n```js\n\u002F\u002F fragment\ns.row([mark, wordmark], { gap: 16, align: \"center\" });\n```\n\nReveal the container first if the mark and wordmark should feel like one\nbuild, or stagger the row's own children through `s.stagger()` for a build-on\nthat still keeps its lockup spacing.\n\n## Pick one technique\n\n| Technique | Best for | How, on the timeline |\n|---|---|---|\n| Stroke draw-on | Line marks, monograms, signatures | A `path` shape clip, `trimStart`\u002F`trimEnd` animated |\n| Mask wipe | Filled shapes, gradient marks | `wipe` preset, or a `set_mask` rect whose `mask.width` (or `x`) a document `styleTracks` entry animates |\n| Build-on | Multi-part marks, grids | One clip per part, in a group, `delayMs` staggered |\n| Wordmark | Logotypes | A text clip with a per-character or per-word `stagger` |\n| Idle loop | Loaders, ambient splash | `breathe` or `rotate` as a `loop` |\n| Scale settle | Anything, when in doubt | `pop` with a small `overshoot` |\n\n## Stroke draw-on\n\n`trimStart` and `trimEnd` stroke only a sub-range of a path, 0..1. Drawing is\n`trimEnd` running 0 to 1 with the stroke visible and the fill arriving after:\n\n```json\n{\"op\": \"add_shape_clip\", \"shape\": {\"kind\": \"path\", \"d\": \"M0.1 0.7 L0.3 0.2 L0.5 0.7\",\n \"stroke\": \"#111111\", \"strokeWidthPx\": 6, \"lineCap\": \"round\",\n \"trimStart\": 0, \"trimEnd\": 0}, \"durationMs\": 2000}\n```\n\n```json\n{\"op\": \"animate_clip\", \"target\": \"Path\", \"animations\": [\n  {\"role\": \"in\", \"preset\": \"custom\", \"durationMs\": 1100,\n   \"easing\": \"cubic-bezier(0.65,0,0.35,1)\",\n   \"curves\": [{\"property\": \"trimEnd\", \"keyframes\": [\n     {\"t\": 0, \"value\": 0}, {\"t\": 1, \"value\": 1}]}]}]}\n```\n\nBoth trim channels fold as **replace**: one animation drives one of them, and two\noverlapping in time means the later wins and the earlier is discarded, reported\nas `replace_curves_overlap`. Draw with `trimEnd` alone; use `trimStart` chasing\nit only for a stroke that draws and erases, and put the two in separate windows.\n\nStagger several strokes by stepping each path clip's `delayMs` by the\nclip-to-clip stagger in `motion-principles`, in the order a hand would draw\nthem.\n\n`add_shape_clip` stores a path's `d` without parsing it. A `d` the renderer\ncannot parse reports `shape_path_invalid` (an error) from `validate_timeline`,\nand an unknown `kind` reports `unknown_shape_kind`. Either draws nothing — a\nmark that vanished is usually one of those two.\n\n## Mask wipe\n\nFor a filled mark, reveal rather than draw. `{\"role\": \"in\", \"preset\": \"wipe\",\n\"durationMs\": 700, \"params\": {\"direction\": \"left\", \"softness\": 0.05}}` sweeps a\nfeathered edge across the layer. `softness` 0 is a hard edge, which reads as\ngraphic; 0.1 reads as light passing over.\n\nA `custom` curve driving `wipeProgress` needs a `mask` on the same animation —\n`{direction, softness}` — because a wipe with no edge to run against cannot be\ninferred. `wipeProgress` folds as **min**, so two wipes on one layer keep the\ntighter one.\n\n## Build-on\n\nOne clip per part, each on its own overlay track, all parented to one group with\n`add_group`. Reveal the container first, then accents, then the wordmark last so\nthe eye lands on the name.\n\n```json\n{\"op\": \"animate_clip\", \"target\": \"Mark part 2\", \"animations\": [\n  {\"role\": \"in\", \"preset\": \"pop\", \"durationMs\": 500, \"delayMs\": 80,\n   \"params\": {\"overshoot\": 1.12}}]}\n```\n\nStep by the clip-to-clip stagger in `motion-principles`, as the 80ms\n`delayMs` on the second part does. Then animate the **group** for anything that moves the whole\nassembly — one `fade` out on the group beats three chances for the parts to\ndrift apart. The group's opacity multiplies into each child.\n\nWhen the parts already have animations, `{\"op\": \"stagger_animations\",\n\"clip_ids\": [\"mark-id\", \"wordmark-id\", \"tagline-id\"], \"offset_ms\": 80}`\nadds delay in that order without moving their media. Use clip IDs, with at\nleast two, and give every selected clip an animation first. The first keeps\nits delay. For a repeating field of identical marks, the document's\n`repeater` sets copy count, position step, and time step on one clip. Use a\nrepeater for a pattern, and separate clips for parts that need distinct art.\n\nKeep a follower aligned by storing `animationLinks` on its clip when it should\nread the mark's position, scale, rotation, or opacity. A link follows the\nsource's authored animation and does not chain through other links. Put the mark and the wordmark in a flex row (`layout: {display: \"flex\",\nflexDirection: \"row\", gap, alignItems: \"center\"}` on a group clip, both as\nits real children via `parentId`) so the wordmark's position follows the\nmark's changing box; a backing plate is a third child with `flexItem:\n{position: \"absolute\", inset: 0}` behind the wordmark. These are document\nfields, so read and write the full document with `get_timeline` and\n`set_timeline_document`.\n`set_clip_params` refuses `repeater`, `animationLinks`, and `layout`.\n\n## Wordmark\n\nA text clip with a stagger. Per character for a short mark, per word for a\nlockup with a tagline:\n\n```json\n{\"role\": \"in\", \"preset\": \"pop\", \"durationMs\": 380,\n \"stagger\": {\"unit\": \"character\", \"offsetMs\": 45, \"from\": \"start\"}}\n```\n\nWork the span out — `durationMs + offsetMs × (units − 1)` — and compare it\nagainst the clip. A span that does not fit is compressed silently, and a\ncompressed wordmark is the reason a reveal \"does not look staggered\".\n`stagger_compressed` is the warning.\n\nSet the family to a bundled one — `Inter`, `Space Grotesk`, `Bebas Neue`,\n`Playfair Display`, `Lora`, `JetBrains Mono` — or the render and the editor\nresolve it differently and the lockup's width changes under you.\n\n## What not to do to a mark\n\nScale, opacity, rotation about the mark's own anchor, and position are safe.\n`scaleX` and `scaleY` on their own are not: `squash` distorts the geometry, and a\ndistorted logo is a brand problem rather than a taste one. Keep motion out of the\nclearspace — a support element sliding through the mark's margin cheapens it.\n\n## Landing on a sound logo\n\nDecide the audio first. A sound logo that does not exist yet is a 1–3 s\neffects brief — source, action, space — on ElevenLabs sound effects\n(`elevenlabs-audio-prompting`) or a `TrackType: SFX` prompt on Stable Audio\n(`stable-audio-prompting`); a 30-second request for a hit is a hit followed by\nroom tone. Then `detect_audio_events` on the sting reports `onsets.times` in\n**seconds**; multiply by 1000. Time the reveal so the mark reaches full opacity\nand scale on that millisecond:\n\n`delayMs` on the `in` animation = onset ms − the clip's `startMs` −\n`durationMs`. Then add the accent on the hit itself, as a separate emphasis:\n`{\"role\": \"emphasis\", \"preset\": \"pulse\", \"durationMs\": 220, \"delayMs\": \u003Conset −\nstartMs>, \"params\": {\"intensity\": 0.04}}`.\n\nA settle that floats free of the sound reads as cheap even when both are good.\n`snap_to_beats` is the blunt version when the whole end card has to sit on the\ngrid.\n\nFor a mark that should stay on beat if the sequence tempo changes, put a\n`beat: {index, scope: \"sequence\", offsetMs?}` anchor on its animation in the\nfull document. The index is one-based and `delayMs` adds to it. The\n`animate_clip` tool input does not accept `beat`. Keep the stored animation's\n`id`, `role`, `preset`, and `durationMs` when adding it. If the sound logo's measured\nonset is the source of truth, keep the absolute delay or use\n`bake_audio_animation` for audio-driven motion instead.\n\n## Idle loop\n\nFor a loader or a splash that waits, a `loop` at low amplitude: `breathe` with\n`intensity` 0.02–0.04, or `rotate` on a mark that is radially symmetric. Set\n`durationMs` to the cycle, 2000–4000ms, and remember a cycle longer than the clip\nshows a fragment of the motion.\n\nNever loop a wordmark somebody is reading.\n\n## Hold the end frame\n\nThe last thing on screen is the static mark. Leave the end hold\n`motion-principles` sets (at least 1000ms) after the reveal completes with\nnothing animating — an end card that cuts the instant it\nsettles reads as a mistake. On a 2500ms clip with a 1100ms draw and a 220ms\naccent, that is satisfied; check it rather than assuming.\n\n## Start from a rig when it fits\n\n`list_compositions` and `get_composition` show the shipped `logo-sting` rig and\nits parameters. `insert_composition` places it as a group with fresh clip IDs.\nInspect those IDs before changing its timing or staggering its parts. Use the\n`title-slam` or `word-cards` examples for a typographic reveal; they are\nstarting documents rather than tool presets.\n\n## Check it\n\n- `validate_timeline`: `replace_curves_overlap` on the trims, `stagger_compressed`\n  on the wordmark, `animation_exceeds_clip` on a reveal longer than its clip,\n  `shape_path_invalid` or `unknown_shape_kind` on a mark that draws nothing.\n- `preview_timeline_frame` at the midpoint of the draw, a held moment, and the\n  last frame. The midpoint is where a half-drawn path or a stroke that never\n  closes shows up; the last frame is where you confirm the mark is clean and\n  complete.\n- Then `render_timeline`, because a sting is judged at speed.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Flogo-reveal",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":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add nodetool-ai\u002Fnodetool --skill logo-reveal",{"tool":60,"command":61},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill logo-reveal",{"tool":63,"command":64},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill logo-reveal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Flogo-reveal\u002FSKILL.md",true,[68,74],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Faiwg_mutation_native_probe.py","SCRIPT","脚本",1927,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Ftesting-quality\u002Fskills\u002Fmutation-test\u002Fscripts\u002Faiwg_mutation_native_probe.py",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fnative_extension_preflight.py",14644,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Ftesting-quality\u002Fskills\u002Fmutation-test\u002Fscripts\u002Fnative_extension_preflight.py",[79,88,123,152,166,182],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"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":89,"name":37,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":103,"publishedAt":40},"01M6BY4D93R0Q9400ZHJ04DXP1","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",[93,98],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[37,104,105,106,107,108,109,110,111,33,112,25,113,114,115,116,117,118,119,120,121,122],"MCP","Media","workflows","when","generation","media generation","with","visual","collections","node","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":132,"publishedAt":40},"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",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000016","图像与多媒体",[133,134,135,136,137,138,139,113,140,141,142,143,144,145,146,147,148,38,149,150,151],"prompting","wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget","generate","text","image","model","Audio","Video",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":160,"publishedAt":40},"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",[158,159],{"categoryNo":130,"categoryName":131,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[122,161,151,162,163,32,164,33,165,37,25],"video workflow","reusable","storyboard","batches","single",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":173,"publishedAt":40},"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",[172],{"categoryNo":130,"categoryName":131,"taxonomyType":96,"taxonomyTypeDesc":97},[174,175,151,110,176,177,37,178,179,180,181],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"publishedAt":40},"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",[188],{"categoryNo":130,"categoryName":131,"taxonomyType":96,"taxonomyTypeDesc":97},[190,151,150,191,192,193,194,195,196,197,198,199,200,107,201,202,149,203,204,205,206],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]