[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY2KQ6R4C7QVM88EF1X7VP":3,"skill-same:01M6BY2KQ6R4C7QVM88EF1X7VP":69},{"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":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":12,"ownerDescription":54,"updatedAt":55,"install":56,"resources":68},"01M6BY2KQ6R4C7QVM88EF1X7VP","nodetool-skill-author",null,"Write or revise a NodeTool skill: a user skill row through create_skill, or a shipped system skill under packages\u002Fsystem-skills. Use when instructions should persist across sessions.","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\u002Fnodetool-skill-author\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"author","nodetool skill author","nodetool","user","when","persist","true","revise","across","user skill","use","sessions","instructions","write","system","create","packages","2026-11-10 10:12:30",false,"---\nname: nodetool-skill-author\ndescription: \"Write or revise a NodeTool skill: a user skill row through create_skill, or a shipped system skill under packages\u002Fsystem-skills. Use when instructions should persist across sessions.\"\nfeatured: true\n---\n\n# Author a NodeTool skill\n\nA skill is a named set of instructions an agent loads when its description\nmatches the task. Write one when the same direction would otherwise be repeated\nevery session. Do not write one for a single job: do the job.\n\n## Which kind\n\n| | User skill | System skill |\n|---|---|---|\n| Lives in | A row in the user's account | `packages\u002Fsystem-skills\u002F\u003Cname>\u002FSKILL.md` in the build |\n| Written by | `create_skill`, `update_skill`, `delete_skill` | A file in a pull request |\n| Scope | That user | Every install, on day one, with no seeding migration |\n| Editable at runtime | Yes | No. Immutable, and `create_skill`, `update_skill` and renames refuse a shipped name. A user row that already held the name before the skill shipped still shadows it |\n\nA repository skill under `.claude\u002Fskills\u002F` is a third thing: it directs the\ncoding agent working on the NodeTool repository, not the agent inside the\nproduct — the engineering loop, not a product surface. Its maintenance rules\nare in a checkout's `.claude\u002FREADME.md`, § Maintaining skills.\n\nA skill that teaches a product surface is a system skill even when the coding\nagent also wants it. `packages\u002Fsystem-skills\u002F\u003Cname>` holds the one copy and\n`.claude\u002Fskills\u002F\u003Cname>` is a symlink to it, so the product and the repository\nread the same document. Write a second copy under `.claude\u002Fskills\u002F` and the\ntwo drift; `npm run check:agents-docs` fails on one.\n\n## The contract\n\nA system skill is one Markdown document with frontmatter:\n\n```markdown\n---\nname: my-skill\ndescription: When to use this\n---\n\nThe instructions.\n```\n\nA user skill has the same three parts as separate `create_skill` fields:\n`{name, description, content}`. `content` is the body only. Do not put\nfrontmatter in it.\n\n- `name` is a lowercase slug, `a-z0-9-` only, at most 64 characters. It cannot\n  contain `anthropic` or `claude`. A user's names must be unique per user.\n- `description` is one bounded line, at most 1024 characters, with no markup.\n  **It is the only part always in context**, so write it as *when to use this*,\n  not as what the skill contains. A description that does not name the trigger\n  means the skill never loads.\n- `featured: true` is for a shipped skill only. It puts the skill in the\n  catalog that every turn carries. Every other shipped skill is found with\n  `list_skills({query})`, so feature a skill only when a turn needs it before\n  its first call: the entry point of a product surface, or a craft skill that\n  work on that surface always reads.\n- The body must be non-empty. Frontmatter is parsed as scalar `key: value`\n  pairs, not full YAML, and the fence is the first `---` line after the opening\n  one, so a `---` rule inside the body survives.\n- `##` headings organize the body for the reader. `load_skill` returns the\n  whole document in one piece, so a section does not save context.\n\nConfirm the parse by listing it back: `list_skills` shows name and description,\n`load_skill {name}` returns the full instructions.\n\n## Write it so it fires and so it holds\n\n- **Lead with the result, then the loop.** The reader is mid-task and will act\n  on the first thing that looks like an instruction.\n- **Name tools exactly.** A renamed tool in a skill is a failure a model cannot\n  recover from. Check each call against the live schema or the capability\n  registry before writing it.\n- **State what a tool refuses**, not only what it accepts. Most skill failures\n  are a call made with a field the tool drops.\n- **Point at the neighbour** rather than restating it. A craft skill quotes a\n  call, the contract skill owns it.\n- **Do not add checkpoints or deliverables** the user did not ask for. An\n  example in a skill is an illustration, not a requirement on the next request.\n\n## Shipping a system skill\n\nOne directory holding a `SKILL.md` whose frontmatter `name` matches the\ndirectory. Nothing imports these files, so `packages\u002Fsystem-skills` is not a\nworkspace: `stageSystemSkills` in `scripts\u002Fbundle-backend.mjs` copies every\ndirectory into `_skills\u002F` beside the bundled `server.mjs`, and\n`scripts\u002Fverify-backend-bundle.mjs` fails a build that misses one. A new\ndirectory ships with no other change.\n\nDiscovery checks `NODETOOL_SYSTEM_SKILLS_DIR` first, and when it is set nothing\nelse is searched. Otherwise it uses `_skills\u002F` beside the bundle, else\n`packages\u002Fsystem-skills` on the way up. Only `SKILL.md` is read: a\nskill ships as one document, so material that would have been a `references\u002F`\nfile belongs in a `##` section of the body.\n\nSymlink the new directory into `.claude\u002Fskills\u002F\u003Cname>` when the repository's\ncoding agent should reach it too.\n\nTwo follow-ups a new system skill usually needs:\n\n- Check the tool names yourself. `packages\u002Fagents\u002Ftests\u002Fshipped-skill-names.test.ts`\n  reads snake_case calls out of every shipped skill and checks them against the\n  registry, but only names with a known verb prefix (`add_`, `create_`, `get_`,\n  `list_` and so on). Names such as `web_search`, `request_secret` or\n  `find_model` pass unchecked, and so do node types. A skill\n  whose body names timeline calls can also go in that test's `SKILL_NAMES`,\n  which matches them exactly against the capability specs and `edit_timeline`'s\n  op list.\n- A skill that guides one model line goes in `MODEL_PROMPTING_SKILLS`\n  (`packages\u002Fagents\u002Fsrc\u002Fmodel-prompting-skills.ts`) so `find_model` attaches it\n  to a matching route. `packages\u002Fagents\u002Ftests\u002Fmodel-prompting-skills.test.ts`\n  checks that table against the skills on disk, the model ids the shipped\n  provider manifests name, and the capability registry.\n\n## Reference\n\nIn a NodeTool checkout, these repository sources go further:\n\n- `packages\u002Fsystem-skills\u002FREADME.md` — the shipped set, and how one job\n  routes across it.\n- `packages\u002Fagents\u002Fsrc\u002Fsystem-skills.ts` — loader and discovery rules.\n- `packages\u002Fprotocol\u002Fsrc\u002Fskill-document.ts` — the parser and the validators.\n","# Author a NodeTool skill\n\nA skill is a named set of instructions an agent loads when its description\nmatches the task. Write one when the same direction would otherwise be repeated\nevery session. Do not write one for a single job: do the job.\n\n## Which kind\n\n| | User skill | System skill |\n|---|---|---|\n| Lives in | A row in the user's account | `packages\u002Fsystem-skills\u002F\u003Cname>\u002FSKILL.md` in the build |\n| Written by | `create_skill`, `update_skill`, `delete_skill` | A file in a pull request |\n| Scope | That user | Every install, on day one, with no seeding migration |\n| Editable at runtime | Yes | No. Immutable, and `create_skill`, `update_skill` and renames refuse a shipped name. A user row that already held the name before the skill shipped still shadows it |\n\nA repository skill under `.claude\u002Fskills\u002F` is a third thing: it directs the\ncoding agent working on the NodeTool repository, not the agent inside the\nproduct — the engineering loop, not a product surface. Its maintenance rules\nare in a checkout's `.claude\u002FREADME.md`, § Maintaining skills.\n\nA skill that teaches a product surface is a system skill even when the coding\nagent also wants it. `packages\u002Fsystem-skills\u002F\u003Cname>` holds the one copy and\n`.claude\u002Fskills\u002F\u003Cname>` is a symlink to it, so the product and the repository\nread the same document. Write a second copy under `.claude\u002Fskills\u002F` and the\ntwo drift; `npm run check:agents-docs` fails on one.\n\n## The contract\n\nA system skill is one Markdown document with frontmatter:\n\n```markdown\n---\nname: my-skill\ndescription: When to use this\n---\n\nThe instructions.\n```\n\nA user skill has the same three parts as separate `create_skill` fields:\n`{name, description, content}`. `content` is the body only. Do not put\nfrontmatter in it.\n\n- `name` is a lowercase slug, `a-z0-9-` only, at most 64 characters. It cannot\n  contain `anthropic` or `claude`. A user's names must be unique per user.\n- `description` is one bounded line, at most 1024 characters, with no markup.\n  **It is the only part always in context**, so write it as *when to use this*,\n  not as what the skill contains. A description that does not name the trigger\n  means the skill never loads.\n- `featured: true` is for a shipped skill only. It puts the skill in the\n  catalog that every turn carries. Every other shipped skill is found with\n  `list_skills({query})`, so feature a skill only when a turn needs it before\n  its first call: the entry point of a product surface, or a craft skill that\n  work on that surface always reads.\n- The body must be non-empty. Frontmatter is parsed as scalar `key: value`\n  pairs, not full YAML, and the fence is the first `---` line after the opening\n  one, so a `---` rule inside the body survives.\n- `##` headings organize the body for the reader. `load_skill` returns the\n  whole document in one piece, so a section does not save context.\n\nConfirm the parse by listing it back: `list_skills` shows name and description,\n`load_skill {name}` returns the full instructions.\n\n## Write it so it fires and so it holds\n\n- **Lead with the result, then the loop.** The reader is mid-task and will act\n  on the first thing that looks like an instruction.\n- **Name tools exactly.** A renamed tool in a skill is a failure a model cannot\n  recover from. Check each call against the live schema or the capability\n  registry before writing it.\n- **State what a tool refuses**, not only what it accepts. Most skill failures\n  are a call made with a field the tool drops.\n- **Point at the neighbour** rather than restating it. A craft skill quotes a\n  call, the contract skill owns it.\n- **Do not add checkpoints or deliverables** the user did not ask for. An\n  example in a skill is an illustration, not a requirement on the next request.\n\n## Shipping a system skill\n\nOne directory holding a `SKILL.md` whose frontmatter `name` matches the\ndirectory. Nothing imports these files, so `packages\u002Fsystem-skills` is not a\nworkspace: `stageSystemSkills` in `scripts\u002Fbundle-backend.mjs` copies every\ndirectory into `_skills\u002F` beside the bundled `server.mjs`, and\n`scripts\u002Fverify-backend-bundle.mjs` fails a build that misses one. A new\ndirectory ships with no other change.\n\nDiscovery checks `NODETOOL_SYSTEM_SKILLS_DIR` first, and when it is set nothing\nelse is searched. Otherwise it uses `_skills\u002F` beside the bundle, else\n`packages\u002Fsystem-skills` on the way up. Only `SKILL.md` is read: a\nskill ships as one document, so material that would have been a `references\u002F`\nfile belongs in a `##` section of the body.\n\nSymlink the new directory into `.claude\u002Fskills\u002F\u003Cname>` when the repository's\ncoding agent should reach it too.\n\nTwo follow-ups a new system skill usually needs:\n\n- Check the tool names yourself. `packages\u002Fagents\u002Ftests\u002Fshipped-skill-names.test.ts`\n  reads snake_case calls out of every shipped skill and checks them against the\n  registry, but only names with a known verb prefix (`add_`, `create_`, `get_`,\n  `list_` and so on). Names such as `web_search`, `request_secret` or\n  `find_model` pass unchecked, and so do node types. A skill\n  whose body names timeline calls can also go in that test's `SKILL_NAMES`,\n  which matches them exactly against the capability specs and `edit_timeline`'s\n  op list.\n- A skill that guides one model line goes in `MODEL_PROMPTING_SKILLS`\n  (`packages\u002Fagents\u002Fsrc\u002Fmodel-prompting-skills.ts`) so `find_model` attaches it\n  to a matching route. `packages\u002Fagents\u002Ftests\u002Fmodel-prompting-skills.test.ts`\n  checks that table against the skills on disk, the model ids the shipped\n  provider manifests name, and the capability registry.\n\n## Reference\n\nIn a NodeTool checkout, these repository sources go further:\n\n- `packages\u002Fsystem-skills\u002FREADME.md` — the shipped set, and how one job\n  routes across it.\n- `packages\u002Fagents\u002Fsrc\u002Fsystem-skills.ts` — loader and discovery rules.\n- `packages\u002Fprotocol\u002Fsrc\u002Fskill-document.ts` — the parser and the validators.\n",{"name":5,"featured":46,"description":7},true,"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fnodetool-skill-author",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":57,"prompt":67,"zipAvailable":46},[58,61,64],{"tool":59,"command":60},"npx","npx skills add nodetool-ai\u002Fnodetool --skill nodetool-skill-author",{"tool":62,"command":63},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill nodetool-skill-author",{"tool":65,"command":66},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill nodetool-skill-author","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fnodetool-skill-author\u002FSKILL.md",[],[70,79,110,140,155,171],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"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":80,"name":26,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":90,"publishedAt":41},"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",[84,85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[26,91,92,93,28,94,95,96,97,34,98,99,100,101,102,103,104,105,106,107,108,109],"MCP","Media","workflows","generation","media generation","with","visual","collections","for","node","work","debug","graph","validate","assets","run","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":41},"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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[120,121,122,123,124,125,126,100,127,128,129,130,131,132,133,134,135,136,137,138,139],"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":41},"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":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,149,139,150,151,152,153,34,154,26,99],"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":41},"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":21,"taxonomyTypeDesc":22},[163,164,139,96,165,166,26,167,168,169,170],"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":41},"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":21,"taxonomyTypeDesc":22},[179,139,138,180,37,181,182,183,184,185,186,32,187,28,188,189,137,190,191,192,193],"video audio continuity","continuity","why","back","veo 3","at","cut","later","filter","generated","how to","mix","design","boundary","how"]