[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXYWC5GMTHFN8TCJJ5BS0Q":3,"skill-same:01M6BXYWC5GMTHFN8TCJJ5BS0Q":79},{"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":28,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":12,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6BXYWC5GMTHFN8TCJJ5BS0Q","api-workflows",null,"Call nodetool.workflows, nodetool.jobs or nodetool.nodes from a code action: list, validate, save, run, debug and version workflow graphs, wait on background jobs, and look up or probe node types. Load before the first call into these namespaces.","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\u002Fapi-workflows\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"workflows","api","api workflows","load","workflow","namespaces","action","types","wait","background jobs","call","up","version","list","node","nodetool","save","first","code","run","debug","validate","2026-11-10 10:12:30",false,"---\nname: api-workflows\ndescription: \"Call nodetool.workflows, nodetool.jobs or nodetool.nodes from a code action: list, validate, save, run, debug and version workflow graphs, wait on background jobs, and look up or probe node types. Load before the first call into these namespaces.\"\n---\n\n# nodetool.workflows, nodetool.jobs, nodetool.nodes\n\nThese three namespaces cover saved graphs, the runs they start, and the node\ncatalog a graph is built from. How to design a graph is\n`nodetool-workflow-builder`. This skill is the call reference.\n\nEvery method takes an id as the full id or its 12-character prefix, and every\nmethod throws when its backing tool is not on this belt.\n\n## nodetool.workflows\n\n| Call | Does | Answers |\n| :--- | :--- | :--- |\n| `list({workflow_type, query, limit})` | Lists workflows. `workflow_type` is `\"user\"` (default), `\"example\"` or `\"all\"`. | `{workflows: [{id, name, description, tags}]}` — an envelope, not an array |\n| `get(id)` | Reads one workflow with its graph. | The workflow record |\n| `create(name, graph, {description, tags, access, project_id})` | Saves a new workflow. `graph` is a DSL result, `{nodes, edges}`, or a workflow record. `create({name, graph})` also works. | The saved workflow with its `id` |\n| `validate(idOrGraph)` | Checks a graph against the node registry without a run. | `{ok, issues}`. Throws when the graph has errors, so a broken graph cannot reach a paid run. |\n| `run(id, params, {interactive, node_ids, reuse_results})` | Runs and blocks until the run settles. | The run result. With `interactive: true`, a failed node returns `status: \"escalated\"`. |\n| `start(id, params, {node_ids, reuse_results})` | Starts a run and returns at once. | A receipt `{job_id, id, status: \"running\"}` |\n| `debug(id, params, {interactive, node_ids, reuse_results, include_graph, log_limit})` | Runs and reports. | `{workflow_id, run, job, workflow}`. An escalated debug answers `{workflow_id, run}` with the escalation under `run`. |\n| `resolve(sessionId, escalationId, action, {outputs, reason, apply_to})` | Answers an escalation. | The next escalation, or the final report |\n| `example(\"\u003Cpackage>\u002F\u003Cname>\")` | Loads a shipped example with its graph. A bare name reads from `nodetool-base`. | The example workflow |\n| `versions(id, {limit})`, `getVersion(id, n)` | Lists and reads snapshots. | Version rows, newest first |\n| `snapshot(id, {name, description})` | Saves the current graph as a manual version. | The new version number |\n| `restore(id, n)` | Rolls the graph back. The graph it replaces is snapshotted first, so a restore can be undone. | — |\n| `deleteVersion(id, n)` | Deletes one snapshot. This cannot be undone. | — |\n| `open(id?)` | Opens the editable object model of a graph that is open in the editor. Throws when no editor tools are on the belt. | A workflow object: `addNode`, `connect`, `commit()` |\n\n`node_ids` runs only those nodes and what they need upstream. Unrelated\nbranches and downstream nodes are not executed or billed. An upstream\ngenerator that already produced output in this workflow is fed that output\ninstead of running again, unless `reuse_results: false`. This is the cheapest\nway to re-run one repaired node.\n\n### The debug report\n\n`debug` answers `{workflow_id, run, job, workflow}`:\n\n- `run.status` is the verdict of the run, and `run.error` names the failure.\n- `run.outputs` is keyed by output name. Each name holds an **array** of the\n  values it emitted, so read `run.outputs.summary[0]`, not `run.outputs.summary`.\n- `run.verdict.issues` lists what went wrong, node by node.\n- `job` carries the status, the cost and the logs.\n\n### Escalations\n\nAn interactive run parks on a failed node and answers `status: \"escalated\"`\nwith a `session_id`, an `escalation_id` and `escalation.allowedActions`. The actions\nare `retry`, `substitute` (with `{outputs}`, only when the escalation has a\n`candidateOutput`), `skip`, `end_stream` and `fail` (with `{reason}`).\n`apply_to: \"signature\"` also answers later failures with the same signature.\n`run` answers the escalation at the top level. `debug` nests it under `run`,\nso drive the loop with `run`. `resolve` answers the next escalation or the\nfinal report, both at the top level. Write the whole loop in one action:\n\n```js\nlet report = await nodetool.workflows.run(id, params, { interactive: true });\nwhile (report.status === \"escalated\") {\n  report = await nodetool.workflows.resolve(report.session_id, report.escalation_id, \"skip\");\n}\nreturn { status: report.status, error: report.error, issues: report.verdict?.issues };\n```\n\nAn unanswered escalation fails the run when its decision timeout expires.\n\n### Rules\n\n- A saved graph is not a run. When the user asked for results, call `run`.\n- Validate before `create` and before a paid run. `validate` throws on errors,\n  and its message lists the errors only.\n- A `*_model` property left unset fails validation. Assign\n  `(await nodetool.models.pick(capability)).ref`.\n- `create` checks model properties. An unknown provider or model id is refused\n  and not saved.\n\n## nodetool.jobs\n\nA job is one execution of a workflow, and a render of a timeline is a job too.\n\n| Call | Answers |\n| :--- | :--- |\n| `list({workflow_id, limit})` | Job rows with status, timing, error and the names of the outputs. The values are not in the list. |\n| `get(idOrReceipt)` | One job, with the outputs once it has settled |\n| `logs(idOrReceipt, {limit})` | The log tail. It answers for a failed job too, with the failure under `job_error`. |\n| `wait(idOrReceipt, {timeoutMs, pollMs})` | Polls until the status is `completed`, `failed`, `cancelled` or `error`, then answers the job. On a timeout it throws with the last status. |\n\nEvery call takes the id string or the receipt that `start()` answered.\nStart, do other work, then wait, all in one action:\n\n```js\nconst receipt = await nodetool.workflows.start(id, { prompt: \"a fox\" });\n\u002F\u002F … other work in the same action …\nconst settled = await nodetool.jobs.wait(receipt, { timeoutMs: 300000 });\nreturn { status: settled.status, outputs: settled.outputs };\n```\n\nDo not write one `get()` per action. `wait` is the polling loop. A code\naction stops after 600 s, so keep `timeoutMs` well under 600000 and call\n`wait` again in the next action when the job is still running.\n\n## nodetool.nodes\n\n| Call | Does | Answers |\n| :--- | :--- | :--- |\n| `search(query, {n_results, namespace, input_type, output_type, include_provider_nodes})` | Searches the catalog. `query` is a string or an array of terms. | `{total, results}`. The node type of a result is on `type`, not `node_type`. |\n| `info(type)` | Reads one node type: properties, inputs, outputs, defaults. | The node metadata |\n| `list({namespace, limit})` | Browses a namespace. An unknown namespace answers with the namespaces that exist. | Node rows |\n| `run(type, inputs)` | Runs ONE node with a property bag, with no workflow. | The outputs, keyed by slot |\n\n- Never guess a node type. Search, then read `info` for the exact property\n  names before you wire the node.\n- Provider nodes (`openai.*`, `fal.*` and others) are hidden unless you pass\n  `include_provider_nodes: true`. Pass it only when the user named a provider.\n- `run` is the cheapest probe of what a node does. Try one node before you\n  put it in a graph.\n- To call nodes as functions inside an action, import them from\n  `@nodetool-ai\u002Fsandbox-flow`. To author a graph, import them from\n  `@nodetool-ai\u002Fsandbox-dsl`. `nodetool-js-scripting` covers both packs.\n","# nodetool.workflows, nodetool.jobs, nodetool.nodes\n\nThese three namespaces cover saved graphs, the runs they start, and the node\ncatalog a graph is built from. How to design a graph is\n`nodetool-workflow-builder`. This skill is the call reference.\n\nEvery method takes an id as the full id or its 12-character prefix, and every\nmethod throws when its backing tool is not on this belt.\n\n## nodetool.workflows\n\n| Call | Does | Answers |\n| :--- | :--- | :--- |\n| `list({workflow_type, query, limit})` | Lists workflows. `workflow_type` is `\"user\"` (default), `\"example\"` or `\"all\"`. | `{workflows: [{id, name, description, tags}]}` — an envelope, not an array |\n| `get(id)` | Reads one workflow with its graph. | The workflow record |\n| `create(name, graph, {description, tags, access, project_id})` | Saves a new workflow. `graph` is a DSL result, `{nodes, edges}`, or a workflow record. `create({name, graph})` also works. | The saved workflow with its `id` |\n| `validate(idOrGraph)` | Checks a graph against the node registry without a run. | `{ok, issues}`. Throws when the graph has errors, so a broken graph cannot reach a paid run. |\n| `run(id, params, {interactive, node_ids, reuse_results})` | Runs and blocks until the run settles. | The run result. With `interactive: true`, a failed node returns `status: \"escalated\"`. |\n| `start(id, params, {node_ids, reuse_results})` | Starts a run and returns at once. | A receipt `{job_id, id, status: \"running\"}` |\n| `debug(id, params, {interactive, node_ids, reuse_results, include_graph, log_limit})` | Runs and reports. | `{workflow_id, run, job, workflow}`. An escalated debug answers `{workflow_id, run}` with the escalation under `run`. |\n| `resolve(sessionId, escalationId, action, {outputs, reason, apply_to})` | Answers an escalation. | The next escalation, or the final report |\n| `example(\"\u003Cpackage>\u002F\u003Cname>\")` | Loads a shipped example with its graph. A bare name reads from `nodetool-base`. | The example workflow |\n| `versions(id, {limit})`, `getVersion(id, n)` | Lists and reads snapshots. | Version rows, newest first |\n| `snapshot(id, {name, description})` | Saves the current graph as a manual version. | The new version number |\n| `restore(id, n)` | Rolls the graph back. The graph it replaces is snapshotted first, so a restore can be undone. | — |\n| `deleteVersion(id, n)` | Deletes one snapshot. This cannot be undone. | — |\n| `open(id?)` | Opens the editable object model of a graph that is open in the editor. Throws when no editor tools are on the belt. | A workflow object: `addNode`, `connect`, `commit()` |\n\n`node_ids` runs only those nodes and what they need upstream. Unrelated\nbranches and downstream nodes are not executed or billed. An upstream\ngenerator that already produced output in this workflow is fed that output\ninstead of running again, unless `reuse_results: false`. This is the cheapest\nway to re-run one repaired node.\n\n### The debug report\n\n`debug` answers `{workflow_id, run, job, workflow}`:\n\n- `run.status` is the verdict of the run, and `run.error` names the failure.\n- `run.outputs` is keyed by output name. Each name holds an **array** of the\n  values it emitted, so read `run.outputs.summary[0]`, not `run.outputs.summary`.\n- `run.verdict.issues` lists what went wrong, node by node.\n- `job` carries the status, the cost and the logs.\n\n### Escalations\n\nAn interactive run parks on a failed node and answers `status: \"escalated\"`\nwith a `session_id`, an `escalation_id` and `escalation.allowedActions`. The actions\nare `retry`, `substitute` (with `{outputs}`, only when the escalation has a\n`candidateOutput`), `skip`, `end_stream` and `fail` (with `{reason}`).\n`apply_to: \"signature\"` also answers later failures with the same signature.\n`run` answers the escalation at the top level. `debug` nests it under `run`,\nso drive the loop with `run`. `resolve` answers the next escalation or the\nfinal report, both at the top level. Write the whole loop in one action:\n\n```js\nlet report = await nodetool.workflows.run(id, params, { interactive: true });\nwhile (report.status === \"escalated\") {\n  report = await nodetool.workflows.resolve(report.session_id, report.escalation_id, \"skip\");\n}\nreturn { status: report.status, error: report.error, issues: report.verdict?.issues };\n```\n\nAn unanswered escalation fails the run when its decision timeout expires.\n\n### Rules\n\n- A saved graph is not a run. When the user asked for results, call `run`.\n- Validate before `create` and before a paid run. `validate` throws on errors,\n  and its message lists the errors only.\n- A `*_model` property left unset fails validation. Assign\n  `(await nodetool.models.pick(capability)).ref`.\n- `create` checks model properties. An unknown provider or model id is refused\n  and not saved.\n\n## nodetool.jobs\n\nA job is one execution of a workflow, and a render of a timeline is a job too.\n\n| Call | Answers |\n| :--- | :--- |\n| `list({workflow_id, limit})` | Job rows with status, timing, error and the names of the outputs. The values are not in the list. |\n| `get(idOrReceipt)` | One job, with the outputs once it has settled |\n| `logs(idOrReceipt, {limit})` | The log tail. It answers for a failed job too, with the failure under `job_error`. |\n| `wait(idOrReceipt, {timeoutMs, pollMs})` | Polls until the status is `completed`, `failed`, `cancelled` or `error`, then answers the job. On a timeout it throws with the last status. |\n\nEvery call takes the id string or the receipt that `start()` answered.\nStart, do other work, then wait, all in one action:\n\n```js\nconst receipt = await nodetool.workflows.start(id, { prompt: \"a fox\" });\n\u002F\u002F … other work in the same action …\nconst settled = await nodetool.jobs.wait(receipt, { timeoutMs: 300000 });\nreturn { status: settled.status, outputs: settled.outputs };\n```\n\nDo not write one `get()` per action. `wait` is the polling loop. A code\naction stops after 600 s, so keep `timeoutMs` well under 600000 and call\n`wait` again in the next action when the job is still running.\n\n## nodetool.nodes\n\n| Call | Does | Answers |\n| :--- | :--- | :--- |\n| `search(query, {n_results, namespace, input_type, output_type, include_provider_nodes})` | Searches the catalog. `query` is a string or an array of terms. | `{total, results}`. The node type of a result is on `type`, not `node_type`. |\n| `info(type)` | Reads one node type: properties, inputs, outputs, defaults. | The node metadata |\n| `list({namespace, limit})` | Browses a namespace. An unknown namespace answers with the namespaces that exist. | Node rows |\n| `run(type, inputs)` | Runs ONE node with a property bag, with no workflow. | The outputs, keyed by slot |\n\n- Never guess a node type. Search, then read `info` for the exact property\n  names before you wire the node.\n- Provider nodes (`openai.*`, `fal.*` and others) are hidden unless you pass\n  `include_provider_nodes: true`. Pass it only when the user named a provider.\n- `run` is the cheapest probe of what a node does. Try one node before you\n  put it in a graph.\n- To call nodes as functions inside an action, import them from\n  `@nodetool-ai\u002Fsandbox-flow`. To author a graph, import them from\n  `@nodetool-ai\u002Fsandbox-dsl`. `nodetool-js-scripting` covers both packs.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fapi-workflows",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":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add nodetool-ai\u002Fnodetool --skill api-workflows",{"tool":71,"command":72},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill api-workflows",{"tool":74,"command":75},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill api-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fapi-workflows\u002FSKILL.md",true,[],[80,89,114,144,159,175],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":88},"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":90,"name":44,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":98,"publishedAt":51},"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",[94,97],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[44,99,100,29,101,102,103,104,105,106,107,108,43,109,49,110,50,111,48,112,113,33],"MCP","Media","when","generation","media generation","with","visual","use","collections","for","work","graph","assets","server","mcp server",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":123,"publishedAt":51},"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",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[124,125,126,127,128,129,130,43,131,132,133,134,135,136,137,138,139,140,141,142,143],"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":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":152,"publishedAt":51},"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",[150,151],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[33,153,143,154,155,156,157,106,158,44,108],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":51},"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",[165],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[167,168,143,104,169,170,44,171,172,173,174],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":51},"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",[181],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[183,143,142,184,185,186,187,188,189,190,191,192,193,101,194,195,141,196,197,198,199],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]