[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F96XY1HV201P9PQ79577PE":3,"skill-same:01M7F96XY1HV201P9PQ79577PE":66},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F96XY1HV201P9PQ79577PE","profiling-workflows",null,"Guides core fg-data-profiling ProfileReport workflows for pandas DataFrames, exports, time-series, type schemas, and report smoke checks.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: profiling-workflows\ndescription: \"Guides core fg-data-profiling ProfileReport workflows for pandas\n  DataFrames, exports, time-series, type schemas, and report smoke checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Profiling Workflows\n\nUse this sub-skill when the user wants to create, inspect, or export an\nfg-data-profiling report with the Python API. This covers the current public\nimport `data_profiling`, `ProfileReport`, and the pandas `df.profile_report()`\nconvenience method.\n\n## Read first\n\n- Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for verified\n  signatures, output methods, and summary accessors.\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for task-oriented\n  recipes: minimal EDA, full\u002Fexplorative reports, time-series, type schemas,\n  notebook display, and large-dataset sampling.\n- Read [references\u002Fdata-formats.md](references\u002Fdata-formats.md) when the user is\n  starting from files, pandas readers, or DataFrame shape constraints.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for empty\n  DataFrames, `sortby`, `minimal`\u002F`config_file`, deprecated imports, and widget\n  display failures.\n- Run [scripts\u002Fprofile_dataframe_smoke.py](scripts\u002Fprofile_dataframe_smoke.py)\n  when you need a safe no-network API smoke test that writes a tiny HTML\u002FJSON\n  report.\n\n## Core API pattern\n\n```python\nimport pandas as pd\nfrom data_profiling import ProfileReport\n\ndf = pd.DataFrame({\"amount\": [1.0, 2.5, 3.0], \"segment\": [\"a\", \"b\", \"b\"]})\nprofile = ProfileReport(df, title=\"Dataset profile\", minimal=True, progress_bar=False)\nprofile.to_file(\"profile.html\")\n```\n\nIf the user already has a pandas DataFrame and has imported `data_profiling`,\nthe package also registers:\n\n```python\nprofile = df.profile_report(title=\"Dataset profile\", minimal=True)\n```\n\nPrefer `minimal=True` or a sampled DataFrame for first-pass profiling of large\nor unfamiliar data. Move performance tuning and report-section controls to\n[..\u002Fconfiguration-and-output\u002FSKILL.md](..\u002Fconfiguration-and-output\u002FSKILL.md)\nwhen the user asks for exact settings.\n\n## Choose the right mode\n\n| User intent | Recommended start |\n| --- | --- |\n| Quick EDA report for a pandas DataFrame | `ProfileReport(df, minimal=True)` then `to_file(\"report.html\")` |\n| Full exploratory report with URL\u002Ffile\u002Fimage\u002Ftext detection | `ProfileReport(df, explorative=True)` and review optional dependencies |\n| Time-series EDA | `ProfileReport(df, tsmode=True, sortby=\"time_column\")` if chronological order is a column |\n| Known semantic column types | Pass `type_schema={\"col\": \"categorical\"}` or a time-series type schema |\n| JSON profile values for automation | `json.loads(profile.to_json())` or `profile.get_description()` |\n| Sensitive dataset | Route to [..\u002Fcomparison-and-quality\u002FSKILL.md](..\u002Fcomparison-and-quality\u002FSKILL.md) before exposing samples\u002Fduplicates |\n| Spark DataFrame | Route to [..\u002Fintegrations-and-backends\u002FSKILL.md](..\u002Fintegrations-and-backends\u002FSKILL.md) first |\n\n## Important boundaries\n\n- This sub-skill is API-first. For shell commands, read\n  [..\u002Fcli-and-automation\u002FSKILL.md](..\u002Fcli-and-automation\u002FSKILL.md).\n- For YAML files, environment variables, HTML assets, cache invalidation, and\n  serialization, read\n  [..\u002Fconfiguration-and-output\u002FSKILL.md](..\u002Fconfiguration-and-output\u002FSKILL.md).\n- For report comparison, privacy redaction, custom samples, metadata, and\n  Great Expectations caveats, read\n  [..\u002Fcomparison-and-quality\u002FSKILL.md](..\u002Fcomparison-and-quality\u002FSKILL.md).\n- For Spark, notebooks, Bytewax, dashboards, and optional dependency readiness,\n  read [..\u002Fintegrations-and-backends\u002FSKILL.md](..\u002Fintegrations-and-backends\u002FSKILL.md).\n\n## Safety and validation\n\n- Start with tiny local fixtures before profiling private, very large, or\n  expensive datasets.\n- Do not rely on the original repository's examples at runtime; use the bundled\n  smoke script or adapt the API snippets in this sub-skill.\n- If a report has already rendered and the configuration changes, either create\n  a fresh `ProfileReport` or use cache invalidation from the configuration\n  sub-skill.\n- Treat notebook widget rendering as optional; HTML export is the most portable\n  output for sharing.\n","# Profiling Workflows\n\nUse this sub-skill when the user wants to create, inspect, or export an\nfg-data-profiling report with the Python API. This covers the current public\nimport `data_profiling`, `ProfileReport`, and the pandas `df.profile_report()`\nconvenience method.\n\n## Read first\n\n- Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for verified\n  signatures, output methods, and summary accessors.\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for task-oriented\n  recipes: minimal EDA, full\u002Fexplorative reports, time-series, type schemas,\n  notebook display, and large-dataset sampling.\n- Read [references\u002Fdata-formats.md](references\u002Fdata-formats.md) when the user is\n  starting from files, pandas readers, or DataFrame shape constraints.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for empty\n  DataFrames, `sortby`, `minimal`\u002F`config_file`, deprecated imports, and widget\n  display failures.\n- Run [scripts\u002Fprofile_dataframe_smoke.py](scripts\u002Fprofile_dataframe_smoke.py)\n  when you need a safe no-network API smoke test that writes a tiny HTML\u002FJSON\n  report.\n\n## Core API pattern\n\n```python\nimport pandas as pd\nfrom data_profiling import ProfileReport\n\ndf = pd.DataFrame({\"amount\": [1.0, 2.5, 3.0], \"segment\": [\"a\", \"b\", \"b\"]})\nprofile = ProfileReport(df, title=\"Dataset profile\", minimal=True, progress_bar=False)\nprofile.to_file(\"profile.html\")\n```\n\nIf the user already has a pandas DataFrame and has imported `data_profiling`,\nthe package also registers:\n\n```python\nprofile = df.profile_report(title=\"Dataset profile\", minimal=True)\n```\n\nPrefer `minimal=True` or a sampled DataFrame for first-pass profiling of large\nor unfamiliar data. Move performance tuning and report-section controls to\n[..\u002Fconfiguration-and-output\u002FSKILL.md](..\u002Fconfiguration-and-output\u002FSKILL.md)\nwhen the user asks for exact settings.\n\n## Choose the right mode\n\n| User intent | Recommended start |\n| --- | --- |\n| Quick EDA report for a pandas DataFrame | `ProfileReport(df, minimal=True)` then `to_file(\"report.html\")` |\n| Full exploratory report with URL\u002Ffile\u002Fimage\u002Ftext detection | `ProfileReport(df, explorative=True)` and review optional dependencies |\n| Time-series EDA | `ProfileReport(df, tsmode=True, sortby=\"time_column\")` if chronological order is a column |\n| Known semantic column types | Pass `type_schema={\"col\": \"categorical\"}` or a time-series type schema |\n| JSON profile values for automation | `json.loads(profile.to_json())` or `profile.get_description()` |\n| Sensitive dataset | Route to [..\u002Fcomparison-and-quality\u002FSKILL.md](..\u002Fcomparison-and-quality\u002FSKILL.md) before exposing samples\u002Fduplicates |\n| Spark DataFrame | Route to [..\u002Fintegrations-and-backends\u002FSKILL.md](..\u002Fintegrations-and-backends\u002FSKILL.md) first |\n\n## Important boundaries\n\n- This sub-skill is API-first. For shell commands, read\n  [..\u002Fcli-and-automation\u002FSKILL.md](..\u002Fcli-and-automation\u002FSKILL.md).\n- For YAML files, environment variables, HTML assets, cache invalidation, and\n  serialization, read\n  [..\u002Fconfiguration-and-output\u002FSKILL.md](..\u002Fconfiguration-and-output\u002FSKILL.md).\n- For report comparison, privacy redaction, custom samples, metadata, and\n  Great Expectations caveats, read\n  [..\u002Fcomparison-and-quality\u002FSKILL.md](..\u002Fcomparison-and-quality\u002FSKILL.md).\n- For Spark, notebooks, Bytewax, dashboards, and optional dependency readiness,\n  read [..\u002Fintegrations-and-backends\u002FSKILL.md](..\u002Fintegrations-and-backends\u002FSKILL.md).\n\n## Safety and validation\n\n- Start with tiny local fixtures before profiling private, very large, or\n  expensive datasets.\n- Do not rely on the original repository's examples at runtime; use the bundled\n  smoke script or adapt the API snippets in this sub-skill.\n- If a report has already rendered and the configuration changes, either create\n  a fresh `ProfileReport` or use cache invalidation from the configuration\n  sub-skill.\n- Treat notebook widget rendering as optional; HTML export is the most portable\n  output for sharing.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill profiling-workflows",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill profiling-workflows",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill profiling-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-reference.md","REFERENCE","参考文档",4153,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows\u002Freferences\u002Fapi-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdata-formats.md",2808,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows\u002Freferences\u002Fdata-formats.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",2542,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fworkflows.md",3494,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Fsub-skills\u002Fprofiling-workflows\u002Freferences\u002Fworkflows.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]