[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T2ACD52P9613XR0THFV8Z":3,"skill-same:01M78T2ACD52P9613XR0THFV8Z":83},{"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},"01M78T2ACD52P9613XR0THFV8Z","autoviz",null,"Routes AutoViz users to automated EDA, data-quality, and text\u002Fwordcloud 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\u002Fautoviz\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: autoviz\ndescription: \"Routes AutoViz users to automated EDA, data-quality, and\n  text\u002Fwordcloud workflows.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# AutoViz\n\nUse this skill when a user wants to explore a tabular dataset with AutoViz, fix data-quality problems with `FixDQ`, or generate wordclouds from string columns. Keep this skill router-like: send the user to the most specific sub-skill, then use the bundled references and scripts for details.\n\n## First decision\n\n- If the task is about loading a file or DataFrame and producing plots, use [`sub-skills\u002Feda-visualization\u002FSKILL.md`](sub-skills\u002Feda-visualization\u002FSKILL.md).\n- If the task is about data-quality reporting or `FixDQ`, use [`sub-skills\u002Fdata-quality-fixes\u002FSKILL.md`](sub-skills\u002Fdata-quality-fixes\u002FSKILL.md).\n- If the task is about text columns, NLP cleanup, or wordclouds, use [`sub-skills\u002Ftext-wordclouds\u002FSKILL.md`](sub-skills\u002Ftext-wordclouds\u002FSKILL.md).\n\n## Minimal usage shape\n\n```python\nfrom autoviz import AutoViz_Class\n\nAV = AutoViz_Class()\ndft = AV.AutoViz(\n    filename,\n    sep=\",\",\n    depVar=\"\",\n    dfte=df,\n    header=0,\n    verbose=1,\n    lowess=False,\n    chart_format=\"svg\",\n    max_rows_analyzed=150000,\n    max_cols_analyzed=30,\n    save_plot_dir=None,\n)\n```\n\n## What to read next\n\n- Read [`references\u002Foverview.md`](references\u002Foverview.md) for the package surface and the quickest route to the right sub-skill.\n- Read [`references\u002Finstall-and-compatibility.md`](references\u002Finstall-and-compatibility.md) if imports, `pip check`, `xgboost`, pandas, or interactive-backend dependencies fail.\n- Read [`references\u002Fchart-formats.md`](references\u002Fchart-formats.md) when the user asks for `png`, `svg`, `jpg`, `bokeh`, `server`, or `html` output behavior.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for import, environment, plotting, and text-column failure modes.\n- Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) when you need exact signatures or helper names.\n- Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) when you need to check source freshness or decide whether the skill should be refreshed.\n- Read [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json) when you need the managed router placement metadata used during import.\n- Read [`scripts\u002Finspect_install.py`](scripts\u002Finspect_install.py) when you need a quick runtime snapshot from a prepared environment.\n\n## Common routing cues\n\n- `AutoViz_Class`, `AutoViz_Main`, `filename`, `dfte`, `chart_format`, `save_plot_dir`, `max_rows_analyzed`, or `max_cols_analyzed` usually mean the EDA sub-skill.\n- `FixDQ`, `data_cleaning_suggestions`, duplicate rows, infinity, rare categories, mixed types, or leakage usually mean the data-quality sub-skill.\n- `wordcloud`, `nltk`, `textblob`, `emoji`, `stopwords`, `discrete string`, or NLP columns usually mean the text sub-skill.\n- If the user asks about installation, package versions, or why `import autoviz` fails, route to the relevant references first and then return to the right sub-skill.\n\n## Import note\n\n`import autoviz` prints a banner in this repository version. That is expected and not a failure.\n\n## Quick expectations\n\n- The package is CPU-oriented.\n- Interactive chart formats depend on `hvplot`, `holoviews`, `panel`, `bokeh`, and `IPython`.\n- `data_cleaning_suggestions` uses `pandas_dq`.\n- `FixDQ` is the transformer-style path for reusable data-quality cleanup.\n- Wordcloud generation may trigger an NLTK download if string columns are present.\n- A tiny toy DataFrame can be classified in surprising ways, so use the bundled smoke scripts when debugging.\n\n## What not to do\n\n- Do not point users at the original source checkout as a required runtime dependency.\n- Do not suggest source notebooks or repo tests as the primary user workflow when a bundled script exists.\n- Do not claim accelerator requirements; this skill's covered workflows are CPU-based.\n- Do not hide compatibility warnings in prose when `pip check` or import output shows a concrete failure.\n\n## Handoff shape\n\nWhen the user is still deciding, keep the response short and route them to the right sub-skill plus the correct reference.\nWhen the user wants action, use the bundled script for that sub-skill, verify the runtime, and then summarize the result in package terms rather than source-file terms.\n\n## Escalation\n\nIf the user wants a broader comparison with another package, first finish the AutoViz route and then explain the boundary clearly.\nIf the issue is really a repository install or compatibility failure, point them to the install-and-compatibility and troubleshooting references before changing the workflow.\n","# AutoViz\n\nUse this skill when a user wants to explore a tabular dataset with AutoViz, fix data-quality problems with `FixDQ`, or generate wordclouds from string columns. Keep this skill router-like: send the user to the most specific sub-skill, then use the bundled references and scripts for details.\n\n## First decision\n\n- If the task is about loading a file or DataFrame and producing plots, use [`sub-skills\u002Feda-visualization\u002FSKILL.md`](sub-skills\u002Feda-visualization\u002FSKILL.md).\n- If the task is about data-quality reporting or `FixDQ`, use [`sub-skills\u002Fdata-quality-fixes\u002FSKILL.md`](sub-skills\u002Fdata-quality-fixes\u002FSKILL.md).\n- If the task is about text columns, NLP cleanup, or wordclouds, use [`sub-skills\u002Ftext-wordclouds\u002FSKILL.md`](sub-skills\u002Ftext-wordclouds\u002FSKILL.md).\n\n## Minimal usage shape\n\n```python\nfrom autoviz import AutoViz_Class\n\nAV = AutoViz_Class()\ndft = AV.AutoViz(\n    filename,\n    sep=\",\",\n    depVar=\"\",\n    dfte=df,\n    header=0,\n    verbose=1,\n    lowess=False,\n    chart_format=\"svg\",\n    max_rows_analyzed=150000,\n    max_cols_analyzed=30,\n    save_plot_dir=None,\n)\n```\n\n## What to read next\n\n- Read [`references\u002Foverview.md`](references\u002Foverview.md) for the package surface and the quickest route to the right sub-skill.\n- Read [`references\u002Finstall-and-compatibility.md`](references\u002Finstall-and-compatibility.md) if imports, `pip check`, `xgboost`, pandas, or interactive-backend dependencies fail.\n- Read [`references\u002Fchart-formats.md`](references\u002Fchart-formats.md) when the user asks for `png`, `svg`, `jpg`, `bokeh`, `server`, or `html` output behavior.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for import, environment, plotting, and text-column failure modes.\n- Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) when you need exact signatures or helper names.\n- Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) when you need to check source freshness or decide whether the skill should be refreshed.\n- Read [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json) when you need the managed router placement metadata used during import.\n- Read [`scripts\u002Finspect_install.py`](scripts\u002Finspect_install.py) when you need a quick runtime snapshot from a prepared environment.\n\n## Common routing cues\n\n- `AutoViz_Class`, `AutoViz_Main`, `filename`, `dfte`, `chart_format`, `save_plot_dir`, `max_rows_analyzed`, or `max_cols_analyzed` usually mean the EDA sub-skill.\n- `FixDQ`, `data_cleaning_suggestions`, duplicate rows, infinity, rare categories, mixed types, or leakage usually mean the data-quality sub-skill.\n- `wordcloud`, `nltk`, `textblob`, `emoji`, `stopwords`, `discrete string`, or NLP columns usually mean the text sub-skill.\n- If the user asks about installation, package versions, or why `import autoviz` fails, route to the relevant references first and then return to the right sub-skill.\n\n## Import note\n\n`import autoviz` prints a banner in this repository version. That is expected and not a failure.\n\n## Quick expectations\n\n- The package is CPU-oriented.\n- Interactive chart formats depend on `hvplot`, `holoviews`, `panel`, `bokeh`, and `IPython`.\n- `data_cleaning_suggestions` uses `pandas_dq`.\n- `FixDQ` is the transformer-style path for reusable data-quality cleanup.\n- Wordcloud generation may trigger an NLTK download if string columns are present.\n- A tiny toy DataFrame can be classified in surprising ways, so use the bundled smoke scripts when debugging.\n\n## What not to do\n\n- Do not point users at the original source checkout as a required runtime dependency.\n- Do not suggest source notebooks or repo tests as the primary user workflow when a bundled script exists.\n- Do not claim accelerator requirements; this skill's covered workflows are CPU-based.\n- Do not hide compatibility warnings in prose when `pip check` or import output shows a concrete failure.\n\n## Handoff shape\n\nWhen the user is still deciding, keep the response short and route them to the right sub-skill plus the correct reference.\nWhen the user wants action, use the bundled script for that sub-skill, verify the runtime, and then summarize the result in package terms rather than source-file terms.\n\n## Escalation\n\nIf the user wants a broader comparison with another package, first finish the AutoViz route and then explain the boundary clearly.\nIf the issue is really a repository install or compatibility failure, point them to the install-and-compatibility and troubleshooting references before changing the workflow.\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\u002Fautoviz",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 autoviz",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill autoviz",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill autoviz","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002FSKILL.md",[47,53,57,61,65,69,73,77],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",3508,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fchart-formats.md",1813,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Fchart-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Finstall-and-compatibility.md",2441,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Finstall-and-compatibility.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Foverview.md",2001,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Foverview.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frepo-provenance.md",1242,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Frepo-provenance.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Frepo-routing-metadata.json",460,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Frepo-routing-metadata.json",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Ftroubleshooting.md",2774,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Freferences\u002Ftroubleshooting.md",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Finspect_install.py","SCRIPT","脚本",1313,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautoviz\u002Fscripts\u002Finspect_install.py",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]