[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY0EDZNPZKPRKDNEF6VQT0":3,"skill-same:01M6BY0EDZNPZKPRKDNEF6VQT0":66},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":12,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6BY0EDZNPZKPRKDNEF6VQT0","manimgx",null,"Write, inspect and render ManimGX scenes: math and 3D animations in Manim Community Edition's Python API, run by the nodetool.manimgx nodes. Use for equations, proofs, plots, geometry, 3D surfaces and explainer animations.","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\u002Fmanimgx\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"use","animations","for","inspect","render","geometry","scenes","community","surfaces","Nodes","python","write","math","nodetool","explainer","3D","manim","api","run","2026-11-10 10:12:30",false,"---\nname: manimgx\ndescription: \"Write, inspect and render ManimGX scenes: math and 3D animations in Manim Community Edition's Python API, run by the nodetool.manimgx nodes. Use for equations, proofs, plots, geometry, 3D surfaces and explainer animations.\"\n---\n\n# Animate with ManimGX\n\nManimGX renders animations written in Manim Community Edition's Python API on a\nRust GPU engine. A scene is a Python module; the `nodetool.manimgx` nodes run\nit on the machine NodeTool runs on. They need `manimgx` installed there\n(ManimGX in the desktop Package Manager, or `uv tool install manimgx` with\nPython 3.13 or newer) and are absent from the hosted cloud, because a scene is\na program.\n\n| Node | Takes | Gives |\n| :--- | :--- | :--- |\n| `nodetool.manimgx.InspectScene` | `code`, `scene_name`, `times`, `timeout` | `ok`, `problems`, `report`, `storyboard`, `duration` |\n| `nodetool.manimgx.RenderScene` | `code`, `scene_name`, `width`, `height`, `fps`, `preset`, `crf`, `timeout` | `video`, `storyboard`, `report`, `subtitles`, `duration` |\n| `nodetool.manimgx.GenerateScene` | `prompt`, `model`, `max_attempts`, `send_storyboard`, `width`, `height`, `fps`, `timeout` | `video`, `code`, `storyboard`, `report`, `attempts` |\n\n`timeout` is the limit in seconds for each ManimGX run (default 300).\n\n`GenerateScene` runs the whole loop below inside one node with a language\nmodel, for up to `max_attempts` rounds (default 3, at most 8). Each round is a\npaid model call, and `send_storyboard` (on by default) sends the storyboard\npictures to it, which needs a vision model. Confirm the model with the user\nbefore running it. Write the scene yourself when you can see the storyboard and\nfix it.\n\n## The loop\n\n1. **Write** the module. Start from the template under\n   [Authoring](#authoring).\n2. **Inspect** it with `InspectScene`. `ok: false` means the scene failed:\n   `report` holds the traceback trimmed to the scene's lines and a \"did you\n   mean\" hint. `problems: true` means it ran but the 2D layout checks found\n   clipped content, overlapping text or labels too small to read. Each problem\n   is numbered in `report` and outlined on the storyboard. Look at the\n   storyboard pictures, not only the report. 3D scenes get pictures and a\n   timeline without layout checks.\n3. **Fix and inspect again** until `ok` is true and `problems` is false. To\n   check particular moments, pass `times: \"1.5,end\"`.\n4. **Render** with `RenderScene` at the size and frame rate asked for. Drafts\n   at 1280x720 and 30 fps render in seconds. The default is 1920x1080 at 30 fps.\n5. **Deliver** the video and the scene's code. Save the code where the person\n   can edit it, such as the `code` of a `RenderScene` node in their workflow.\n\nFrom a code action or a Code node, call the nodes as functions:\n\n```js\nimport \"@nodetool-ai\u002Fsandbox-nodetool\u002Fflow\";\nimport { inspectScene, renderScene } from \"@nodetool-ai\u002Fsandbox-flow\u002Fnodetool.manimgx\";\n\nconst check = await inspectScene({ code, title: \"Circle area\" });\nif (check.ok && !check.problems) {\n  const film = await renderScene({ code, width: 1280, height: 720, fps: 30, title: \"Circle area\" });\n}\n```\n\nExtra keys such as `title` above are the node's dynamic inputs.\n\n## Inputs from the workflow\n\nEvery node takes dynamic inputs. Their values reach the scene as a dict:\n\n```python\nfrom nodetool_inputs import inputs\n```\n\nNumbers, strings, lists and dicts arrive as JSON. Image, audio and video\ninputs arrive as file paths: `m.ImageMobject(inputs[\"logo\"])` for an image,\n`self.add_sound(inputs[\"voice\"])` for audio.\n\nA scene is Python that runs as the server user, with that user's file and\nnetwork access. Only its environment is restricted, so it never sees the\nserver's secrets. Treat scene code as trusted code: do not run a scene from a\nsource the user has not vouched for.\n\n## Authoring\n\n```python\nimport manimgx as m\nfrom nodetool_inputs import inputs\n\n\nclass CircleArea(m.Scene):\n    def construct(self) -> None:\n        circle = m.Circle(radius=1, color=m.BLUE, fill_opacity=0.3)\n        formula = m.MathTex(r\"A = \\pi r^2\").next_to(circle, m.RIGHT, buff=0.6)\n        m.VGroup(circle, formula).center()\n        self.play(m.Create(circle), m.Write(formula))\n        self.wait(1)\n```\n\n- Import `manimgx as m`. Put the animation in a `Scene` subclass's\n  `construct`. With more than one scene in the module, set `scene_name`.\n- Time advances only through `self.play(...)` and `self.wait(...)`.\n  `self.add(...)` adds without animating.\n- Compose placement with `VGroup`, `arrange`, `next_to`, `to_edge` and\n  `center`, so labels follow their subjects. The frame is about 14.2 units wide\n  and 8 tall, centred on the origin.\n- `Text` for prose. `MathTex` with raw strings for LaTeX mathematics, or Typst.\n  No LaTeX installation is needed.\n- For changing values, animate a `ValueTracker` and derive geometry from it.\n  An updater uses elapsed time or current state, never a frame count, so the\n  motion keeps its timing at any `fps`.\n- For 3D, derive from `m.ThreeDScene`: `self.set_camera_orientation(phi=65 *\n  m.DEGREES, theta=-45 * m.DEGREES)`, `Surface`, `Sphere`, `Cube`,\n  `ThreeDAxes`, `self.begin_ambient_camera_rotation(rate=0.5)`.\n- `self.next_section(\"name\")` splits a film into sections. Subcaptions and\n  `self.say(...)` produce subtitles, which `RenderScene` returns as SubRip text.\n\nManimGX's own reference lists every class and keyword:\n[manimgx.academa.ai\u002Freference](https:\u002F\u002Fmanimgx.academa.ai\u002Freference\u002F), and\n[llms.txt](https:\u002F\u002Fmanimgx.academa.ai\u002Fllms.txt) links the guides as Markdown.\nWhere ManimGX and Manim CE differ, ManimGX's page is right.\n\n## Where the result goes next\n\n`video` is an inline video ref. Save it as an asset, or place it on a timeline\nlike any generated clip. A narrated explainer keeps its timing from the voice:\nwrite the script first (`script-video`), then size each scene's waits to its\nline.\n","# Animate with ManimGX\n\nManimGX renders animations written in Manim Community Edition's Python API on a\nRust GPU engine. A scene is a Python module; the `nodetool.manimgx` nodes run\nit on the machine NodeTool runs on. They need `manimgx` installed there\n(ManimGX in the desktop Package Manager, or `uv tool install manimgx` with\nPython 3.13 or newer) and are absent from the hosted cloud, because a scene is\na program.\n\n| Node | Takes | Gives |\n| :--- | :--- | :--- |\n| `nodetool.manimgx.InspectScene` | `code`, `scene_name`, `times`, `timeout` | `ok`, `problems`, `report`, `storyboard`, `duration` |\n| `nodetool.manimgx.RenderScene` | `code`, `scene_name`, `width`, `height`, `fps`, `preset`, `crf`, `timeout` | `video`, `storyboard`, `report`, `subtitles`, `duration` |\n| `nodetool.manimgx.GenerateScene` | `prompt`, `model`, `max_attempts`, `send_storyboard`, `width`, `height`, `fps`, `timeout` | `video`, `code`, `storyboard`, `report`, `attempts` |\n\n`timeout` is the limit in seconds for each ManimGX run (default 300).\n\n`GenerateScene` runs the whole loop below inside one node with a language\nmodel, for up to `max_attempts` rounds (default 3, at most 8). Each round is a\npaid model call, and `send_storyboard` (on by default) sends the storyboard\npictures to it, which needs a vision model. Confirm the model with the user\nbefore running it. Write the scene yourself when you can see the storyboard and\nfix it.\n\n## The loop\n\n1. **Write** the module. Start from the template under\n   [Authoring](#authoring).\n2. **Inspect** it with `InspectScene`. `ok: false` means the scene failed:\n   `report` holds the traceback trimmed to the scene's lines and a \"did you\n   mean\" hint. `problems: true` means it ran but the 2D layout checks found\n   clipped content, overlapping text or labels too small to read. Each problem\n   is numbered in `report` and outlined on the storyboard. Look at the\n   storyboard pictures, not only the report. 3D scenes get pictures and a\n   timeline without layout checks.\n3. **Fix and inspect again** until `ok` is true and `problems` is false. To\n   check particular moments, pass `times: \"1.5,end\"`.\n4. **Render** with `RenderScene` at the size and frame rate asked for. Drafts\n   at 1280x720 and 30 fps render in seconds. The default is 1920x1080 at 30 fps.\n5. **Deliver** the video and the scene's code. Save the code where the person\n   can edit it, such as the `code` of a `RenderScene` node in their workflow.\n\nFrom a code action or a Code node, call the nodes as functions:\n\n```js\nimport \"@nodetool-ai\u002Fsandbox-nodetool\u002Fflow\";\nimport { inspectScene, renderScene } from \"@nodetool-ai\u002Fsandbox-flow\u002Fnodetool.manimgx\";\n\nconst check = await inspectScene({ code, title: \"Circle area\" });\nif (check.ok && !check.problems) {\n  const film = await renderScene({ code, width: 1280, height: 720, fps: 30, title: \"Circle area\" });\n}\n```\n\nExtra keys such as `title` above are the node's dynamic inputs.\n\n## Inputs from the workflow\n\nEvery node takes dynamic inputs. Their values reach the scene as a dict:\n\n```python\nfrom nodetool_inputs import inputs\n```\n\nNumbers, strings, lists and dicts arrive as JSON. Image, audio and video\ninputs arrive as file paths: `m.ImageMobject(inputs[\"logo\"])` for an image,\n`self.add_sound(inputs[\"voice\"])` for audio.\n\nA scene is Python that runs as the server user, with that user's file and\nnetwork access. Only its environment is restricted, so it never sees the\nserver's secrets. Treat scene code as trusted code: do not run a scene from a\nsource the user has not vouched for.\n\n## Authoring\n\n```python\nimport manimgx as m\nfrom nodetool_inputs import inputs\n\n\nclass CircleArea(m.Scene):\n    def construct(self) -> None:\n        circle = m.Circle(radius=1, color=m.BLUE, fill_opacity=0.3)\n        formula = m.MathTex(r\"A = \\pi r^2\").next_to(circle, m.RIGHT, buff=0.6)\n        m.VGroup(circle, formula).center()\n        self.play(m.Create(circle), m.Write(formula))\n        self.wait(1)\n```\n\n- Import `manimgx as m`. Put the animation in a `Scene` subclass's\n  `construct`. With more than one scene in the module, set `scene_name`.\n- Time advances only through `self.play(...)` and `self.wait(...)`.\n  `self.add(...)` adds without animating.\n- Compose placement with `VGroup`, `arrange`, `next_to`, `to_edge` and\n  `center`, so labels follow their subjects. The frame is about 14.2 units wide\n  and 8 tall, centred on the origin.\n- `Text` for prose. `MathTex` with raw strings for LaTeX mathematics, or Typst.\n  No LaTeX installation is needed.\n- For changing values, animate a `ValueTracker` and derive geometry from it.\n  An updater uses elapsed time or current state, never a frame count, so the\n  motion keeps its timing at any `fps`.\n- For 3D, derive from `m.ThreeDScene`: `self.set_camera_orientation(phi=65 *\n  m.DEGREES, theta=-45 * m.DEGREES)`, `Surface`, `Sphere`, `Cube`,\n  `ThreeDAxes`, `self.begin_ambient_camera_rotation(rate=0.5)`.\n- `self.next_section(\"name\")` splits a film into sections. Subcaptions and\n  `self.say(...)` produce subtitles, which `RenderScene` returns as SubRip text.\n\nManimGX's own reference lists every class and keyword:\n[manimgx.academa.ai\u002Freference](https:\u002F\u002Fmanimgx.academa.ai\u002Freference\u002F), and\n[llms.txt](https:\u002F\u002Fmanimgx.academa.ai\u002Fllms.txt) links the guides as Markdown.\nWhere ManimGX and Manim CE differ, ManimGX's page is right.\n\n## Where the result goes next\n\n`video` is an inline video ref. Save it as an asset, or place it on a timeline\nlike any generated clip. A narrated explainer keeps its timing from the voice:\nwrite the script first (`script-video`), then size each scene's waits to its\nline.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fmanimgx",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":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add nodetool-ai\u002Fnodetool --skill manimgx",{"tool":58,"command":59},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill manimgx",{"tool":61,"command":62},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill manimgx","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fmanimgx\u002FSKILL.md",true,[],[67,76,110,140,155,171],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":75},"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":77,"name":32,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":91,"publishedAt":38},"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",[81,86],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,92,93,94,95,96,97,98,99,19,100,21,101,102,103,104,105,106,37,107,108,109],"MCP","Media","workflows","when","generation","media generation","with","visual","collections","node","work","debug","graph","validate","assets","server","mcp server","workflow",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":119,"publishedAt":38},"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",[116],{"categoryNo":117,"categoryName":118,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000016","图像与多媒体",[120,121,122,123,124,125,126,101,127,128,129,130,131,132,133,134,135,136,137,138,139],"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","Video",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":148,"publishedAt":38},"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",[146,147],{"categoryNo":117,"categoryName":118,"taxonomyType":84,"taxonomyTypeDesc":85},{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[109,149,139,150,151,152,153,19,154,32,21],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":38},"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",[161],{"categoryNo":117,"categoryName":118,"taxonomyType":84,"taxonomyTypeDesc":85},[163,164,139,98,165,166,32,167,168,169,170],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":178,"publishedAt":38},"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",[177],{"categoryNo":117,"categoryName":118,"taxonomyType":84,"taxonomyTypeDesc":85},[179,139,138,180,30,181,182,183,184,185,186,187,188,95,189,190,137,191,192,193,194],"video audio continuity","continuity","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]