[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FCMM1RWNGY3DB27RPQFF2":3,"skill-same:01M79FCMM1RWNGY3DB27RPQFF2":98},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M79FCMM1RWNGY3DB27RPQFF2","nemo-data-designer-plugin",null,"Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\n\nname: nemo-data-designer-plugin\ndescription: Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.\nargument-hint: [describe the dataset you want to generate]\nlicense: Apache-2.0\nmetadata:\n  owner: nemo-platform\n---\n\n# Before You Start\n\nDo not explore the workspace first. The workflow's Learn step gives you everything you need.\n\n# Goal\n\nBuild a synthetic dataset using the Data Designer library that matches this description:\n\n$ARGUMENTS\n\n# Workflow\n\nUse **Autopilot** mode if the user implies they don't want to answer questions — e.g., they say something like \"be opinionated\", \"you decide\", \"make reasonable assumptions\", \"just build it\", \"surprise me\", etc. Otherwise, use **Interactive** mode (default).\n\nRead **only** the workflow file that matches the selected mode, then follow it:\n\n- **Interactive** → read `workflows\u002Finteractive.md`\n- **Autopilot** → read `workflows\u002Fautopilot.md`\n\n# Rules\n\n- Keep all columns in the output by default. The only exceptions for dropping a column are: (1) the user explicitly asks, or (2) it is a helper column that exists solely to derive other columns (e.g., a sampled person object used to extract name, city, etc.). When in doubt, keep the column.\n- Do not suggest or ask about seed datasets. Only use one when the user explicitly provides seed data or asks to build from existing records. When using a seed, read `references\u002Fseed-datasets.md`.\n- When the dataset requires person data (names, demographics, addresses), read `references\u002Fperson-sampling.md`.\n- If a dataset script that matches the dataset description already exists, ask the user whether to edit it or create a new one.\n- For commands and context specific to this NeMo Platform plugin (e.g., sourcing model configs from IGW providers or in-script `ModelConfig`s, installing or publishing Nemotron Personas locales, platform-side resource pointers), read `references\u002Fnemo-platform-plugin-additions.md`.\n\n# Usage Tips and Common Pitfalls\n\n- **Sampler and validation columns need both a type and params.** E.g., `sampler_type=\"category\"` with `params=dd.CategorySamplerParams(...)`.\n- **Jinja2 templates** in `prompt`, `system_prompt`, and `expr` fields: reference columns with `{{ column_name }}`, nested fields with `{{ column_name.field }}`.\n- `**SamplerColumnConfig`:** Takes `params`, not `sampler_params`.\n- **LLM judge score access:** `LLMJudgeColumnConfig` produces a nested dict where each score name maps to `{reasoning: str, score: int}`. To get the numeric score, use the `.score` attribute. For example, for a judge column named `quality` with a score named `correctness`, use `{{ quality.correctness.score }}`. Using `{{ quality.correctness }}` returns the full dict, not the numeric score.\n\n# Troubleshooting\n\n- `**nemo data-designer` CLI not found:** Tell the user that `nemo data-designer` is not installed in this environment (requires Python >= 3.11). Ask if they would like you to create a virtual environment and install it, or if they prefer to do it themselves. Do not install anything without the user's permission.\n- **Network errors during preview:** A sandbox environment may be blocking outbound requests. Ask the user for permission to retry the command with the sandbox disabled. Only as a last resort, if retrying outside the sandbox also fails, tell the user to run the command themselves.\n\n# Output Template\n\nWrite a Python file to the current directory with a `load_config_builder()` function returning a `DataDesignerConfigBuilder`. Name the file descriptively (e.g., `customer_reviews.py`). Use PEP 723 inline metadata for dependencies.\n\n```python\n# \u002F\u002F\u002F script\n# dependencies = [\n#   \"data-designer\", # always required\n#   \"pydantic\", # only if this script imports from pydantic\n#   # add additional dependencies here\n# ]\n# \u002F\u002F\u002F\nimport data_designer.config as dd\nfrom pydantic import BaseModel, Field\n\n\n# Use Pydantic models when the output needs to conform to a specific schema\nclass MyStructuredOutput(BaseModel):\n    field_one: str = Field(description=\"...\")\n    field_two: int = Field(description=\"...\")\n\n\n# Use custom generators when built-in column types aren't enough\n@dd.custom_column_generator(\n    required_columns=[\"col_a\"],\n    side_effect_columns=[\"extra_col\"],\n)\ndef generator_function(row: dict) -> dict:\n    # add custom logic here that depends on \"col_a\" and update row in place\n    row[\"name_in_custom_column_config\"] = \"custom value\"\n    row[\"extra_col\"] = \"extra value\"\n    return row\n\n\ndef load_config_builder() -> dd.DataDesignerConfigBuilder:\n    config_builder = dd.DataDesignerConfigBuilder(\n        # Declaring model configs programmatically here is the portable path:\n        # it works for both local `run` and cluster `submit`, while the local\n        # YAML registry alternative only works for `run`. The provider below\n        # is a common default created during `nemo setup` — confirm it (or\n        # discover others) with `nemo inference providers list`. See\n        # references\u002Fnemo-platform-plugin-additions.md for the local-YAML alternative.\n        model_configs=[\n            dd.ModelConfig(\n                alias=\"text\",\n                model=\"...\",\n                provider=\"default\u002Fnvidia-build\",\n                inference_parameters=dd.ChatCompletionInferenceParams(),\n            ),\n        ],\n    )\n\n    # Seed dataset (only if the user explicitly mentions a seed dataset path)\n    # config_builder.with_seed_dataset(dd.LocalFileSeedSource(path=\"path\u002Fto\u002Fseed.parquet\"))\n\n    # config_builder.add_column(...)\n    # config_builder.add_processor(...)\n\n    return config_builder\n```\n\nOnly include Pydantic models, custom generators, seed datasets, and extra dependencies when the task requires them. Prefer including `model_configs` when the dataset uses LLM columns — declaring it in the script keeps the config portable between local `run` and cluster `submit`, while the local YAML registry alternative only works for `run`.\n","# Before You Start\n\nDo not explore the workspace first. The workflow's Learn step gives you everything you need.\n\n# Goal\n\nBuild a synthetic dataset using the Data Designer library that matches this description:\n\n$ARGUMENTS\n\n# Workflow\n\nUse **Autopilot** mode if the user implies they don't want to answer questions — e.g., they say something like \"be opinionated\", \"you decide\", \"make reasonable assumptions\", \"just build it\", \"surprise me\", etc. Otherwise, use **Interactive** mode (default).\n\nRead **only** the workflow file that matches the selected mode, then follow it:\n\n- **Interactive** → read `workflows\u002Finteractive.md`\n- **Autopilot** → read `workflows\u002Fautopilot.md`\n\n# Rules\n\n- Keep all columns in the output by default. The only exceptions for dropping a column are: (1) the user explicitly asks, or (2) it is a helper column that exists solely to derive other columns (e.g., a sampled person object used to extract name, city, etc.). When in doubt, keep the column.\n- Do not suggest or ask about seed datasets. Only use one when the user explicitly provides seed data or asks to build from existing records. When using a seed, read `references\u002Fseed-datasets.md`.\n- When the dataset requires person data (names, demographics, addresses), read `references\u002Fperson-sampling.md`.\n- If a dataset script that matches the dataset description already exists, ask the user whether to edit it or create a new one.\n- For commands and context specific to this NeMo Platform plugin (e.g., sourcing model configs from IGW providers or in-script `ModelConfig`s, installing or publishing Nemotron Personas locales, platform-side resource pointers), read `references\u002Fnemo-platform-plugin-additions.md`.\n\n# Usage Tips and Common Pitfalls\n\n- **Sampler and validation columns need both a type and params.** E.g., `sampler_type=\"category\"` with `params=dd.CategorySamplerParams(...)`.\n- **Jinja2 templates** in `prompt`, `system_prompt`, and `expr` fields: reference columns with `{{ column_name }}`, nested fields with `{{ column_name.field }}`.\n- `**SamplerColumnConfig`:** Takes `params`, not `sampler_params`.\n- **LLM judge score access:** `LLMJudgeColumnConfig` produces a nested dict where each score name maps to `{reasoning: str, score: int}`. To get the numeric score, use the `.score` attribute. For example, for a judge column named `quality` with a score named `correctness`, use `{{ quality.correctness.score }}`. Using `{{ quality.correctness }}` returns the full dict, not the numeric score.\n\n# Troubleshooting\n\n- `**nemo data-designer` CLI not found:** Tell the user that `nemo data-designer` is not installed in this environment (requires Python >= 3.11). Ask if they would like you to create a virtual environment and install it, or if they prefer to do it themselves. Do not install anything without the user's permission.\n- **Network errors during preview:** A sandbox environment may be blocking outbound requests. Ask the user for permission to retry the command with the sandbox disabled. Only as a last resort, if retrying outside the sandbox also fails, tell the user to run the command themselves.\n\n# Output Template\n\nWrite a Python file to the current directory with a `load_config_builder()` function returning a `DataDesignerConfigBuilder`. Name the file descriptively (e.g., `customer_reviews.py`). Use PEP 723 inline metadata for dependencies.\n\n```python\n# \u002F\u002F\u002F script\n# dependencies = [\n#   \"data-designer\", # always required\n#   \"pydantic\", # only if this script imports from pydantic\n#   # add additional dependencies here\n# ]\n# \u002F\u002F\u002F\nimport data_designer.config as dd\nfrom pydantic import BaseModel, Field\n\n\n# Use Pydantic models when the output needs to conform to a specific schema\nclass MyStructuredOutput(BaseModel):\n    field_one: str = Field(description=\"...\")\n    field_two: int = Field(description=\"...\")\n\n\n# Use custom generators when built-in column types aren't enough\n@dd.custom_column_generator(\n    required_columns=[\"col_a\"],\n    side_effect_columns=[\"extra_col\"],\n)\ndef generator_function(row: dict) -> dict:\n    # add custom logic here that depends on \"col_a\" and update row in place\n    row[\"name_in_custom_column_config\"] = \"custom value\"\n    row[\"extra_col\"] = \"extra value\"\n    return row\n\n\ndef load_config_builder() -> dd.DataDesignerConfigBuilder:\n    config_builder = dd.DataDesignerConfigBuilder(\n        # Declaring model configs programmatically here is the portable path:\n        # it works for both local `run` and cluster `submit`, while the local\n        # YAML registry alternative only works for `run`. The provider below\n        # is a common default created during `nemo setup` — confirm it (or\n        # discover others) with `nemo inference providers list`. See\n        # references\u002Fnemo-platform-plugin-additions.md for the local-YAML alternative.\n        model_configs=[\n            dd.ModelConfig(\n                alias=\"text\",\n                model=\"...\",\n                provider=\"default\u002Fnvidia-build\",\n                inference_parameters=dd.ChatCompletionInferenceParams(),\n            ),\n        ],\n    )\n\n    # Seed dataset (only if the user explicitly mentions a seed dataset path)\n    # config_builder.with_seed_dataset(dd.LocalFileSeedSource(path=\"path\u002Fto\u002Fseed.parquet\"))\n\n    # config_builder.add_column(...)\n    # config_builder.add_processor(...)\n\n    return config_builder\n```\n\nOnly include Pydantic models, custom generators, seed datasets, and extra dependencies when the task requires them. Prefer including `model_configs` when the dataset uses LLM columns — declaring it in the script keeps the config portable between local `run` and cluster `submit`, while the local YAML registry alternative only works for `run`.\n",{"name":5,"license":15,"metadata":24,"description":7,"argument-hint":26},{"owner":25},"nemo-platform",[27],"describe the dataset you want to generate","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","skills\u002Fnvidia\u002Fnemo-data-designer-plugin","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill nemo-data-designer-plugin",{"tool":40,"command":41},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill nemo-data-designer-plugin",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill nemo-data-designer-plugin","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002FSKILL.md",true,[48,54,58,62,66,70,74,80,84,90,94],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"BENCHMARK.md","REFERENCE","参考文档",3916,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002FBENCHMARK.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"evals\u002Fevals.json",1503,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Fevals\u002Fevals.json",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fnemo-platform-plugin-additions.md",7814,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Freferences\u002Fnemo-platform-plugin-additions.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fperson-sampling.md",2356,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Freferences\u002Fperson-sampling.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fpreview-review.md",1875,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Freferences\u002Fpreview-review.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fseed-datasets.md",1175,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Freferences\u002Fseed-datasets.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fget_person_object_schema.py","SCRIPT","脚本",1764,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Fscripts\u002Fget_person_object_schema.py",{"path":81,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":82,"sourceHtmlUrl":83},"skill-card.md",3858,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Fskill-card.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"skill.oms.sig","OTHER","其他",6309,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Fskill.oms.sig",{"path":91,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":92,"sourceHtmlUrl":93},"workflows\u002Fautopilot.md",3056,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Fworkflows\u002Fautopilot.md",{"path":95,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":96,"sourceHtmlUrl":97},"workflows\u002Finteractive.md",3733,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-data-designer-plugin\u002Fworkflows\u002Finteractive.md",[99,106,113,120,127,134],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]