[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78S92E14HEPNWZWMPC6FD45":3,"skill-same:01M78S92E14HEPNWZWMPC6FD45":70},{"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},"01M78S92E14HEPNWZWMPC6FD45","ai-data-science-team",null,"Operate the ai-data-science-team package for AI-assisted data loading, EDA, pandas transformations, SQL analysis, H2O\u002FMLflow modeling, multi-agent teams, and Streamlit app workflows.","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\u002Fai-data-science-team\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ai-data-science-team\ndescription: \"Operate the ai-data-science-team package for AI-assisted data\n  loading, EDA, pandas transformations, SQL analysis, H2O\u002FMLflow modeling,\n  multi-agent teams, and Streamlit app workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# AI Data Science Team repo skill\n\nUse this repo skill when a task names `ai-data-science-team`, `ai_data_science_team`, AI Data Science Team, AI Pipeline Studio, or asks for AI-assisted data-science agents that load data, clean\u002Fwrangle\u002Fvisualize DataFrames, query SQL databases, run H2O AutoML\u002FMLflow tools, or compose data-science agent teams.\n\nThis skill is self-contained: read the bundled references and scripts here instead of reopening the original repository checkout, notebooks, or app source.\n\n## Quick package context\n\n- Distribution name: `ai-data-science-team`.\n- Import package: `ai_data_science_team`.\n- Verified version baseline: `0.0.0.9017`.\n- Public install floor from package metadata: Python 3.9+; Python 3.10+ is recommended for app workflows.\n- Common LLM backends: OpenAI chat models through `langchain_openai.ChatOpenAI`, or local Ollama models through `langchain_ollama.ChatOllama` when an Ollama service\u002Fmodel is available.\n- Optional extras: `machine_learning` installs `h2o` and `mlflow`; `data_science` installs `pytimetk`, `missingno`, and `sweetviz`; D-Tale report support needs `dtale` separately.\n\nMinimal import check:\n\n```python\nfrom ai_data_science_team import DataCleaningAgent, SQLDatabaseAgent, PandasDataAnalyst\n```\n\nIf that import fails with `ModuleNotFoundError: IPython`, install `ipython`; the source imports `IPython.display` but the package metadata may not declare it.\n\n## Route by task\n\n| Task signal | Read |\n| --- | --- |\n| Discover files, load CSV\u002FExcel\u002FJSON\u002FParquet, summarize DataFrames, use file tools, run basic EDA summaries, or opt into Sweetviz\u002FD-Tale\u002Fmissingno\u002Fcorrelation-funnel reports | [`sub-skills\u002Fdata-access-and-eda\u002FSKILL.md`](sub-skills\u002Fdata-access-and-eda\u002FSKILL.md) |\n| Use `DataCleaningAgent`, `DataWranglingAgent`, `DataVisualizationAgent`, or `FeatureEngineeringAgent`; retrieve generated code\u002Ffunctions; handle retries\u002Flogs\u002Fhuman review | [`sub-skills\u002Fdataframe-code-agents\u002FSKILL.md`](sub-skills\u002Fdataframe-code-agents\u002FSKILL.md) |\n| Query SQL databases, inspect database metadata, protect read-only SQL, use `SQLDatabaseAgent`, or troubleshoot schema\u002Ftoken pressure | [`sub-skills\u002Fsql-analysis\u002FSKILL.md`](sub-skills\u002Fsql-analysis\u002FSKILL.md) |\n| Train or inspect H2O AutoML workflows, evaluate models, manage MLflow experiments\u002Fruns\u002Fartifacts\u002FUI\u002Fregistry, or check optional ML dependencies | [`sub-skills\u002Fmodeling-and-mlflow\u002FSKILL.md`](sub-skills\u002Fmodeling-and-mlflow\u002FSKILL.md) |\n| Compose agents with `PandasDataAnalyst`, `SQLDataAnalyst`, `SupervisorDSTeam`, `WorkflowPlannerAgent`, or understand AI Pipeline Studio \u002F Streamlit app patterns | [`sub-skills\u002Fmultiagent-and-app-workflows\u002FSKILL.md`](sub-skills\u002Fmultiagent-and-app-workflows\u002FSKILL.md) |\n\n## First actions for future agents\n\n1. Identify whether the user wants deterministic helper functions, LLM-backed agents, optional report\u002Fmodel services, or Streamlit apps.\n2. Check installed prerequisites before invoking agents. Use [`scripts\u002Fcheck_env.py`](scripts\u002Fcheck_env.py) for package import\u002Fsignature and optional dependency visibility.\n3. For deterministic data\u002FSQL helper tasks, prefer bundled smoke scripts from the owning sub-skill before any LLM call.\n4. For LLM-backed agents, confirm the user has configured a LangChain-compatible model object and any provider credentials\u002Fservice.\n5. For optional H2O\u002FMLflow\u002FEDA reports or app workflows, read the owning troubleshooting reference before installing extras, launching services, or starting long-running training\u002FUI processes.\n\n## Shared references and helpers\n\n- [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) explains package modules, public objects, optional dependency groups, and common response\u002Fgetter patterns.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers cross-cutting install\u002Fimport, model-provider, optional dependency, service, generated-code, and app issues.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) records the source baseline used to create this skill; read it before deciding whether to refresh the skill.\n- [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json) is structured metadata for managed repo-skill routing.\n- [`scripts\u002Fcheck_env.py`](scripts\u002Fcheck_env.py) is a safe no-credential environment\u002Fimport checker.\n\n## Safety and verification boundaries\n\n- Do not run notebook workflows, LLM-backed agents, H2O training, MLflow UI, or Streamlit apps unless the user explicitly wants that side effect and has provided credentials\u002Fservices\u002Fbudget.\n- Treat generated code from cleaning\u002Fwrangling\u002Fvisualization\u002Ffeature-engineering agents as code to review, log, and validate on small data before using on production data.\n- Keep `SQLDatabaseAgent(safe_mode=True)` unless the user intentionally authorizes non-read-only SQL. The bundled SQL sub-skill describes what the validator does and does not guarantee.\n- Optional extras are not required for base imports. Install only the extra needed by the selected workflow, not `all` by default.\n- Runtime guidance here must remain independent of the original checkout; if you need an example, use the bundled references\u002Fscripts.\n","# AI Data Science Team repo skill\n\nUse this repo skill when a task names `ai-data-science-team`, `ai_data_science_team`, AI Data Science Team, AI Pipeline Studio, or asks for AI-assisted data-science agents that load data, clean\u002Fwrangle\u002Fvisualize DataFrames, query SQL databases, run H2O AutoML\u002FMLflow tools, or compose data-science agent teams.\n\nThis skill is self-contained: read the bundled references and scripts here instead of reopening the original repository checkout, notebooks, or app source.\n\n## Quick package context\n\n- Distribution name: `ai-data-science-team`.\n- Import package: `ai_data_science_team`.\n- Verified version baseline: `0.0.0.9017`.\n- Public install floor from package metadata: Python 3.9+; Python 3.10+ is recommended for app workflows.\n- Common LLM backends: OpenAI chat models through `langchain_openai.ChatOpenAI`, or local Ollama models through `langchain_ollama.ChatOllama` when an Ollama service\u002Fmodel is available.\n- Optional extras: `machine_learning` installs `h2o` and `mlflow`; `data_science` installs `pytimetk`, `missingno`, and `sweetviz`; D-Tale report support needs `dtale` separately.\n\nMinimal import check:\n\n```python\nfrom ai_data_science_team import DataCleaningAgent, SQLDatabaseAgent, PandasDataAnalyst\n```\n\nIf that import fails with `ModuleNotFoundError: IPython`, install `ipython`; the source imports `IPython.display` but the package metadata may not declare it.\n\n## Route by task\n\n| Task signal | Read |\n| --- | --- |\n| Discover files, load CSV\u002FExcel\u002FJSON\u002FParquet, summarize DataFrames, use file tools, run basic EDA summaries, or opt into Sweetviz\u002FD-Tale\u002Fmissingno\u002Fcorrelation-funnel reports | [`sub-skills\u002Fdata-access-and-eda\u002FSKILL.md`](sub-skills\u002Fdata-access-and-eda\u002FSKILL.md) |\n| Use `DataCleaningAgent`, `DataWranglingAgent`, `DataVisualizationAgent`, or `FeatureEngineeringAgent`; retrieve generated code\u002Ffunctions; handle retries\u002Flogs\u002Fhuman review | [`sub-skills\u002Fdataframe-code-agents\u002FSKILL.md`](sub-skills\u002Fdataframe-code-agents\u002FSKILL.md) |\n| Query SQL databases, inspect database metadata, protect read-only SQL, use `SQLDatabaseAgent`, or troubleshoot schema\u002Ftoken pressure | [`sub-skills\u002Fsql-analysis\u002FSKILL.md`](sub-skills\u002Fsql-analysis\u002FSKILL.md) |\n| Train or inspect H2O AutoML workflows, evaluate models, manage MLflow experiments\u002Fruns\u002Fartifacts\u002FUI\u002Fregistry, or check optional ML dependencies | [`sub-skills\u002Fmodeling-and-mlflow\u002FSKILL.md`](sub-skills\u002Fmodeling-and-mlflow\u002FSKILL.md) |\n| Compose agents with `PandasDataAnalyst`, `SQLDataAnalyst`, `SupervisorDSTeam`, `WorkflowPlannerAgent`, or understand AI Pipeline Studio \u002F Streamlit app patterns | [`sub-skills\u002Fmultiagent-and-app-workflows\u002FSKILL.md`](sub-skills\u002Fmultiagent-and-app-workflows\u002FSKILL.md) |\n\n## First actions for future agents\n\n1. Identify whether the user wants deterministic helper functions, LLM-backed agents, optional report\u002Fmodel services, or Streamlit apps.\n2. Check installed prerequisites before invoking agents. Use [`scripts\u002Fcheck_env.py`](scripts\u002Fcheck_env.py) for package import\u002Fsignature and optional dependency visibility.\n3. For deterministic data\u002FSQL helper tasks, prefer bundled smoke scripts from the owning sub-skill before any LLM call.\n4. For LLM-backed agents, confirm the user has configured a LangChain-compatible model object and any provider credentials\u002Fservice.\n5. For optional H2O\u002FMLflow\u002FEDA reports or app workflows, read the owning troubleshooting reference before installing extras, launching services, or starting long-running training\u002FUI processes.\n\n## Shared references and helpers\n\n- [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) explains package modules, public objects, optional dependency groups, and common response\u002Fgetter patterns.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers cross-cutting install\u002Fimport, model-provider, optional dependency, service, generated-code, and app issues.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) records the source baseline used to create this skill; read it before deciding whether to refresh the skill.\n- [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json) is structured metadata for managed repo-skill routing.\n- [`scripts\u002Fcheck_env.py`](scripts\u002Fcheck_env.py) is a safe no-credential environment\u002Fimport checker.\n\n## Safety and verification boundaries\n\n- Do not run notebook workflows, LLM-backed agents, H2O training, MLflow UI, or Streamlit apps unless the user explicitly wants that side effect and has provided credentials\u002Fservices\u002Fbudget.\n- Treat generated code from cleaning\u002Fwrangling\u002Fvisualization\u002Ffeature-engineering agents as code to review, log, and validate on small data before using on production data.\n- Keep `SQLDatabaseAgent(safe_mode=True)` unless the user intentionally authorizes non-read-only SQL. The bundled SQL sub-skill describes what the validator does and does not guarantee.\n- Optional extras are not required for base imports. Install only the extra needed by the selected workflow, not `all` by default.\n- Runtime guidance here must remain independent of the original checkout; if you need an example, use the bundled references\u002Fscripts.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team",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 ai-data-science-team",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill ai-data-science-team",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill ai-data-science-team","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",6099,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2153,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",520,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",5814,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_env.py","SCRIPT","脚本",4756,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fai-data-science-team\u002Fscripts\u002Fcheck_env.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]