[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795WS8S4B5K98RMHMA9YRBY":3,"skill-same:01M795WS8S4B5K98RMHMA9YRBY":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M795WS8S4B5K98RMHMA9YRBY","synthetic-data-generator",null,"Use SDGX\u002FSynthetic Data Generator for tabular synthetic data, metadata inspection, relationship metadata, CLI fit\u002Fsample, LLM synthesis, evaluation metrics, and plugin-oriented extension workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: synthetic-data-generator\ndescription: \"Use SDGX\u002FSynthetic Data Generator for tabular synthetic data,\n  metadata inspection, relationship metadata, CLI fit\u002Fsample, LLM synthesis,\n  evaluation metrics, and plugin-oriented extension workflows.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Synthetic Data Generator (SDGX) Repo Skill\n\nUse this skill when a task names `sdgx`, Synthetic Data Generator, or asks for structured\u002Ftabular synthetic data generation with SDGX APIs or the `sdgx` CLI. The package centers on `pandas` tables, metadata inspection, default data processors, CTGAN\u002FGaussianCopula synthesis, OpenAI-backed tabular generation, and tabular quality metrics.\n\nDo **not** use this skill for generic GAN theory, unrelated synthetic image\u002Ftext generation, or privacy-policy decisions that are not about operating SDGX APIs.\n\n## Fast orientation\n\n- Public package\u002Fdistribution: `sdgx`.\n- Main import check: `import sdgx; print(sdgx.__version__)`.\n- Main CLI: `sdgx` with `fit`, `sample`, and `list-*` subcommands.\n- Primary high-level API: `sdgx.synthesizer.Synthesizer`.\n- Canonical single-table ML model: `sdgx.models.ml.single_table.ctgan.CTGANSynthesizerModel`.\n- Statistic model available by direct import: `sdgx.models.statistics.single_table.copula.GaussianCopulaSynthesizerModel`.\n- LLM model: `sdgx.models.LLM.single_table.gpt.SingleTableGPTModel`.\n\nRead [references\u002Finstall-and-import.md](references\u002Finstall-and-import.md) before installing, verifying imports, or choosing CPU\u002FCUDA\u002FOpenAI settings. Run [scripts\u002Fcheck_sdgx_environment.py](scripts\u002Fcheck_sdgx_environment.py) when you need a quick registry\u002Fimport\u002Fbackend check in the active environment.\n\n## Quick install\n\n```bash\npip install sdgx\npython - \u003C\u003C'PY'\nimport sdgx\nprint(sdgx.__version__)\nPY\nsdgx --help\n```\n\nFor local checkout work, `pip install .` or `pip install '.[test]'` from the repository root are the documented alternatives.\n\n## Route by task\n\n- **Data connectors, loaders, metadata, processors, cachers, inspectors, relationships, and plugins:** read [sub-skills\u002Fdata-preparation\u002FSKILL.md](sub-skills\u002Fdata-preparation\u002FSKILL.md). Start here when the task is about CSV\u002FDataFrame\u002Fgenerator inputs, metadata JSON, datetimes, fixed\u002Fspecific column combinations, PII columns, caching, or custom extension registration.\n- **Fit\u002Fsample tabular synthesizers or use the `sdgx` CLI:** read [sub-skills\u002Fsingle-table-synthesis\u002FSKILL.md](sub-skills\u002Fsingle-table-synthesis\u002FSKILL.md). Start here for `Synthesizer`, CTGAN, GaussianCopula, model save\u002Fload, `sdgx fit`, `sdgx sample`, `--json_output`, and `--torchrun`.\n- **Generate tabular data with OpenAI-compatible LLMs or infer off-table features:** read [sub-skills\u002Fllm-synthesis\u002FSKILL.md](sub-skills\u002Fllm-synthesis\u002FSKILL.md). Start here for `SingleTableGPTModel`, `OPENAI_KEY`, `OPENAI_URL`, metadata-only generation, raw-data prompting, and response parsing.\n- **Evaluate real vs synthetic data or adapt benchmark-style checks:** read [sub-skills\u002Fevaluation\u002FSKILL.md](sub-skills\u002Fevaluation\u002FSKILL.md). Start here for Jensen-Shannon divergence (`JSD`), mutual-information similarity (`MISim`), and safe metric scripts.\n\n## Common operating pattern\n\n1. Choose a data connector or create a `pandas.DataFrame`.\n2. Build or inspect `Metadata` and optionally customize column types, primary keys, specific combinations, categorical encoders, and datetime formats.\n3. Choose a model and entrypoint:\n   - Library: `Synthesizer(model=..., data_connector=..., metadata=...)` then `fit()` and `sample(n)`.\n   - CLI: `sdgx fit ...` then `sdgx sample ...`.\n   - LLM: `SingleTableGPTModel` with raw data or metadata, after confirming key\u002Fbase URL policy.\n4. Validate outputs: expected columns, row count, null\u002Fdatetime\u002FPII behavior, and metric ranges.\n5. Use troubleshooting references when imports, metadata checks, cache writes, optional dependencies, CUDA, or API credentials fail.\n\n## Repo-level references\n\n- [references\u002Fcomponent-map.md](references\u002Fcomponent-map.md) maps the SDGX architecture, managers, default processors, and public package surfaces.\n- [references\u002Finstall-and-import.md](references\u002Finstall-and-import.md) records installation, import, environment variable, and backend guidance.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers cross-cutting failures shared by multiple workflows.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) records the source version and evidence paths used to create this skill.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured metadata for `repo-skills-router` import.\n\n## Guardrails\n\n- Never assume the package has an installed inspection environment just because the checkout imports from the current directory; verify with the target Python.\n- Do not run notebook or benchmark-scale workflows as quick checks. Use tiny fixtures and short smoke scripts unless the user explicitly requests benchmark execution.\n- Treat LLM generation as a network\u002Fcredential workflow. Do not send sensitive raw rows to an external API unless the user explicitly authorizes that data flow.\n- When debugging an SDGX error, preserve the exact exception class from `sdgx.exceptions`; CLI `--json_output true` can surface structured exit messages.\n","# Synthetic Data Generator (SDGX) Repo Skill\n\nUse this skill when a task names `sdgx`, Synthetic Data Generator, or asks for structured\u002Ftabular synthetic data generation with SDGX APIs or the `sdgx` CLI. The package centers on `pandas` tables, metadata inspection, default data processors, CTGAN\u002FGaussianCopula synthesis, OpenAI-backed tabular generation, and tabular quality metrics.\n\nDo **not** use this skill for generic GAN theory, unrelated synthetic image\u002Ftext generation, or privacy-policy decisions that are not about operating SDGX APIs.\n\n## Fast orientation\n\n- Public package\u002Fdistribution: `sdgx`.\n- Main import check: `import sdgx; print(sdgx.__version__)`.\n- Main CLI: `sdgx` with `fit`, `sample`, and `list-*` subcommands.\n- Primary high-level API: `sdgx.synthesizer.Synthesizer`.\n- Canonical single-table ML model: `sdgx.models.ml.single_table.ctgan.CTGANSynthesizerModel`.\n- Statistic model available by direct import: `sdgx.models.statistics.single_table.copula.GaussianCopulaSynthesizerModel`.\n- LLM model: `sdgx.models.LLM.single_table.gpt.SingleTableGPTModel`.\n\nRead [references\u002Finstall-and-import.md](references\u002Finstall-and-import.md) before installing, verifying imports, or choosing CPU\u002FCUDA\u002FOpenAI settings. Run [scripts\u002Fcheck_sdgx_environment.py](scripts\u002Fcheck_sdgx_environment.py) when you need a quick registry\u002Fimport\u002Fbackend check in the active environment.\n\n## Quick install\n\n```bash\npip install sdgx\npython - \u003C\u003C'PY'\nimport sdgx\nprint(sdgx.__version__)\nPY\nsdgx --help\n```\n\nFor local checkout work, `pip install .` or `pip install '.[test]'` from the repository root are the documented alternatives.\n\n## Route by task\n\n- **Data connectors, loaders, metadata, processors, cachers, inspectors, relationships, and plugins:** read [sub-skills\u002Fdata-preparation\u002FSKILL.md](sub-skills\u002Fdata-preparation\u002FSKILL.md). Start here when the task is about CSV\u002FDataFrame\u002Fgenerator inputs, metadata JSON, datetimes, fixed\u002Fspecific column combinations, PII columns, caching, or custom extension registration.\n- **Fit\u002Fsample tabular synthesizers or use the `sdgx` CLI:** read [sub-skills\u002Fsingle-table-synthesis\u002FSKILL.md](sub-skills\u002Fsingle-table-synthesis\u002FSKILL.md). Start here for `Synthesizer`, CTGAN, GaussianCopula, model save\u002Fload, `sdgx fit`, `sdgx sample`, `--json_output`, and `--torchrun`.\n- **Generate tabular data with OpenAI-compatible LLMs or infer off-table features:** read [sub-skills\u002Fllm-synthesis\u002FSKILL.md](sub-skills\u002Fllm-synthesis\u002FSKILL.md). Start here for `SingleTableGPTModel`, `OPENAI_KEY`, `OPENAI_URL`, metadata-only generation, raw-data prompting, and response parsing.\n- **Evaluate real vs synthetic data or adapt benchmark-style checks:** read [sub-skills\u002Fevaluation\u002FSKILL.md](sub-skills\u002Fevaluation\u002FSKILL.md). Start here for Jensen-Shannon divergence (`JSD`), mutual-information similarity (`MISim`), and safe metric scripts.\n\n## Common operating pattern\n\n1. Choose a data connector or create a `pandas.DataFrame`.\n2. Build or inspect `Metadata` and optionally customize column types, primary keys, specific combinations, categorical encoders, and datetime formats.\n3. Choose a model and entrypoint:\n   - Library: `Synthesizer(model=..., data_connector=..., metadata=...)` then `fit()` and `sample(n)`.\n   - CLI: `sdgx fit ...` then `sdgx sample ...`.\n   - LLM: `SingleTableGPTModel` with raw data or metadata, after confirming key\u002Fbase URL policy.\n4. Validate outputs: expected columns, row count, null\u002Fdatetime\u002FPII behavior, and metric ranges.\n5. Use troubleshooting references when imports, metadata checks, cache writes, optional dependencies, CUDA, or API credentials fail.\n\n## Repo-level references\n\n- [references\u002Fcomponent-map.md](references\u002Fcomponent-map.md) maps the SDGX architecture, managers, default processors, and public package surfaces.\n- [references\u002Finstall-and-import.md](references\u002Finstall-and-import.md) records installation, import, environment variable, and backend guidance.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers cross-cutting failures shared by multiple workflows.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) records the source version and evidence paths used to create this skill.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured metadata for `repo-skills-router` import.\n\n## Guardrails\n\n- Never assume the package has an installed inspection environment just because the checkout imports from the current directory; verify with the target Python.\n- Do not run notebook or benchmark-scale workflows as quick checks. Use tiny fixtures and short smoke scripts unless the user explicitly requests benchmark execution.\n- Treat LLM generation as a network\u002Fcredential workflow. Do not send sensitive raw rows to an external API unless the user explicitly authorizes that data flow.\n- When debugging an SDGX error, preserve the exact exception class from `sdgx.exceptions`; CLI `--json_output true` can surface structured exit messages.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill synthetic-data-generator",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill synthetic-data-generator",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill synthetic-data-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcomponent-map.md","REFERENCE","参考文档",3117,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002Freferences\u002Fcomponent-map.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Finstall-and-import.md",3058,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002Freferences\u002Finstall-and-import.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",2119,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",349,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",3912,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_sdgx_environment.py","SCRIPT","脚本",4054,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsynthetic-data-generator\u002Fscripts\u002Fcheck_sdgx_environment.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]