[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795VZ9CXM0HR19QMPPA88CS":3,"skill-same:01M795VZ9CXM0HR19QMPPA88CS":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M795VZ9CXM0HR19QMPPA88CS","dataset-comparison",null,"Compare two pandas DataFrames or two subsets of one DataFrame with Sweetviz, including target-aware validation and deterministic HTML output checks.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dataset-comparison\ndescription: \"Compare two pandas DataFrames or two subsets of one DataFrame with\n  Sweetviz, including target-aware validation and deterministic HTML output\n  checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Dataset Comparison\n\nUse this sub-skill when the task asks for Sweetviz comparison, train\u002Ftest profiling, dataset drift\u002Fprofile comparison, or subgroup comparison such as \"male vs female\". It owns `sweetviz.compare()` and `sweetviz.compare_intra()` guidance only.\n\n## Route here when\n\n- Comparing two existing pandas DataFrames, usually train\u002Ftest, baseline\u002Fcurrent, or reference\u002Fcandidate.\n- Splitting one DataFrame into two named groups with a boolean condition and comparing the groups.\n- The comparison includes a target feature and needs validation before rendering.\n- The user mentions `compare`, `compare_intra`, subgroup split, non-boolean condition, empty split, or compare-only columns.\n\n## Route elsewhere\n\n- Single-DataFrame `sweetviz.analyze()` or render-only\u002Fbrowser\u002Fnotebook details: use the `report-generation` sub-skill.\n- Detailed `FeatureConfig`, type forcing, config override files, duplicate-column cleanup, or input preflight beyond comparison-specific checks: use the `configuration-and-data-handling` sub-skill.\n- Install\u002Fimport\u002Fpackage-data\u002Ffont issues: use the Sweetviz root troubleshooting reference.\n\n## Operating flow\n\n1. Choose the constructor:\n   - `sweetviz.compare([source_df, \"Source name\"], [compare_df, \"Compare name\"], target_feat=..., feat_cfg=..., pairwise_analysis=...)` for two DataFrames.\n   - `sweetviz.compare_intra(source_df, condition_series, [\"True group\", \"False group\"], target_feat=..., feat_cfg=..., pairwise_analysis=...)` for a split of one DataFrame.\n2. Validate comparison inputs before constructing the report:\n   - No duplicate columns in either DataFrame.\n   - `compare_intra` condition has the same length as `source_df`, has plain boolean dtype, and creates non-empty true and false groups.\n   - Target feature exists in the source, is not skipped, is numeric or boolean, and has no missing values. If the compare DataFrame also contains the target, it must also have no missing values.\n   - Any names used in `FeatureConfig` are case-sensitive and must be present in the source DataFrame.\n3. Prefer explicit dataset names (`[df, \"Training Data\"]` or `(df, \"Training Data\")`) so report sections are interpretable.\n4. Pick `pairwise_analysis`: use `\"off\"` for deterministic or wide smoke runs, `\"auto\"` for ordinary small reports, and `\"on\"` only when association cost is acceptable.\n5. Render with `report.show_html(..., open_browser=False)` for automated work and validate the output file exists and is non-empty. For layout\u002Fbrowser\u002Fnotebook choices, defer to `report-generation`.\n\n## Bundled references and helper\n\n- [Comparison workflows](references\u002Fworkflows.md): train\u002Ftest and `compare_intra` recipes with tiny schemas and deterministic output validation.\n- [API reference](references\u002Fapi-reference.md): verified signatures, accepted input shapes, naming, target\u002Fconfig interactions, pairwise behavior, and column mismatch notes.\n- [Troubleshooting](references\u002Ftroubleshooting.md): non-boolean conditions, empty splits, duplicate columns, target NaNs, missing `FeatureConfig` names, and pairwise threshold behavior.\n- [Smoke script](scripts\u002Fsweetviz_compare_smoke.py): offline argparse helper that builds tiny fixtures, runs `compare` and\u002For `compare_intra`, writes HTML without opening a browser, and can demonstrate invalid non-boolean conditions.\n\n## Non-goals and cautions\n\n- Do not pass `verbosity` to `sweetviz.compare()` or `sweetviz.compare_intra()`; their public signatures do not accept it. If progress output must be controlled, use Sweetviz configuration defaults or the lower-level report class guidance from the configuration\u002Freporting sub-skills.\n- Do not use maintainer or network-update helpers for end-user EDA comparison workflows.\n- Optional Comet.ml logging is credentialed external behavior owned by reporting guidance; do not require it for comparison verification.\n","# Dataset Comparison\n\nUse this sub-skill when the task asks for Sweetviz comparison, train\u002Ftest profiling, dataset drift\u002Fprofile comparison, or subgroup comparison such as \"male vs female\". It owns `sweetviz.compare()` and `sweetviz.compare_intra()` guidance only.\n\n## Route here when\n\n- Comparing two existing pandas DataFrames, usually train\u002Ftest, baseline\u002Fcurrent, or reference\u002Fcandidate.\n- Splitting one DataFrame into two named groups with a boolean condition and comparing the groups.\n- The comparison includes a target feature and needs validation before rendering.\n- The user mentions `compare`, `compare_intra`, subgroup split, non-boolean condition, empty split, or compare-only columns.\n\n## Route elsewhere\n\n- Single-DataFrame `sweetviz.analyze()` or render-only\u002Fbrowser\u002Fnotebook details: use the `report-generation` sub-skill.\n- Detailed `FeatureConfig`, type forcing, config override files, duplicate-column cleanup, or input preflight beyond comparison-specific checks: use the `configuration-and-data-handling` sub-skill.\n- Install\u002Fimport\u002Fpackage-data\u002Ffont issues: use the Sweetviz root troubleshooting reference.\n\n## Operating flow\n\n1. Choose the constructor:\n   - `sweetviz.compare([source_df, \"Source name\"], [compare_df, \"Compare name\"], target_feat=..., feat_cfg=..., pairwise_analysis=...)` for two DataFrames.\n   - `sweetviz.compare_intra(source_df, condition_series, [\"True group\", \"False group\"], target_feat=..., feat_cfg=..., pairwise_analysis=...)` for a split of one DataFrame.\n2. Validate comparison inputs before constructing the report:\n   - No duplicate columns in either DataFrame.\n   - `compare_intra` condition has the same length as `source_df`, has plain boolean dtype, and creates non-empty true and false groups.\n   - Target feature exists in the source, is not skipped, is numeric or boolean, and has no missing values. If the compare DataFrame also contains the target, it must also have no missing values.\n   - Any names used in `FeatureConfig` are case-sensitive and must be present in the source DataFrame.\n3. Prefer explicit dataset names (`[df, \"Training Data\"]` or `(df, \"Training Data\")`) so report sections are interpretable.\n4. Pick `pairwise_analysis`: use `\"off\"` for deterministic or wide smoke runs, `\"auto\"` for ordinary small reports, and `\"on\"` only when association cost is acceptable.\n5. Render with `report.show_html(..., open_browser=False)` for automated work and validate the output file exists and is non-empty. For layout\u002Fbrowser\u002Fnotebook choices, defer to `report-generation`.\n\n## Bundled references and helper\n\n- [Comparison workflows](references\u002Fworkflows.md): train\u002Ftest and `compare_intra` recipes with tiny schemas and deterministic output validation.\n- [API reference](references\u002Fapi-reference.md): verified signatures, accepted input shapes, naming, target\u002Fconfig interactions, pairwise behavior, and column mismatch notes.\n- [Troubleshooting](references\u002Ftroubleshooting.md): non-boolean conditions, empty splits, duplicate columns, target NaNs, missing `FeatureConfig` names, and pairwise threshold behavior.\n- [Smoke script](scripts\u002Fsweetviz_compare_smoke.py): offline argparse helper that builds tiny fixtures, runs `compare` and\u002For `compare_intra`, writes HTML without opening a browser, and can demonstrate invalid non-boolean conditions.\n\n## Non-goals and cautions\n\n- Do not pass `verbosity` to `sweetviz.compare()` or `sweetviz.compare_intra()`; their public signatures do not accept it. If progress output must be controlled, use Sweetviz configuration defaults or the lower-level report class guidance from the configuration\u002Freporting sub-skills.\n- Do not use maintainer or network-update helpers for end-user EDA comparison workflows.\n- Optional Comet.ml logging is credentialed external behavior owned by reporting guidance; do not require it for comparison verification.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-comparison",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-comparison",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-comparison","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",6386,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",7106,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",7416,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fsweetviz_compare_smoke.py","SCRIPT","脚本",8804,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsweetviz\u002Fsub-skills\u002Fdataset-comparison\u002Fscripts\u002Fsweetviz_compare_smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]