[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F96E6WM4M8W97V77PMC7RS":3,"skill-same:01M7F96E6WM4M8W97V77PMC7RS":70},{"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},"01M7F96E6WM4M8W97V77PMC7RS","fg-data-profiling",null,"Guides fg-data-profiling data profiling, report generation, configuration, CLI, comparison, privacy, and optional Spark\u002Fnotebook integration workflows.","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\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: fg-data-profiling\ndescription: \"Guides fg-data-profiling data profiling, report generation,\n  configuration, CLI, comparison, privacy, and optional Spark\u002Fnotebook\n  integration workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# fg-data-profiling\n\nUse this repo skill when a task involves the `fg-data-profiling` Python package\nor its public import `data_profiling`: exploratory data analysis reports,\ndata-quality profiling, HTML\u002FJSON export, command-line report generation,\ncomparison reports, sensitive-data-safe reports, configuration, or optional\nSpark\u002Fnotebook integrations.\n\nDo not use this skill as proof that the original repository checkout is present.\nAll runnable helpers and operational references needed by future agents are\nbundled in this skill tree.\n\n## Install and import check\n\nFor normal package usage, install the public distribution and import the current\nmodule name:\n\n```bash\npython -m pip install -U fg-data-profiling\npython - \u003C\u003C'PY'\nimport data_profiling\nfrom data_profiling import ProfileReport, compare\nprint(data_profiling.__version__)\nprint(ProfileReport)\nprint(compare)\nPY\n```\n\nThe repository also exposes a deprecated compatibility import named\n`ydata_profiling` and a legacy CLI name `pandas_profiling`; prefer the\n`data_profiling` import and `data_profiling` CLI for new work.\n\nRun [scripts\u002Fcheck_environment.py](scripts\u002Fcheck_environment.py) when you need a\nsafe package\u002Fimport\u002FCLI diagnostic before deciding which sub-skill to read.\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\nrefreshing this skill or comparing it with a new checkout.\n\n## Route by task\n\n- Read [sub-skills\u002Fprofiling-workflows\u002FSKILL.md](sub-skills\u002Fprofiling-workflows\u002FSKILL.md)\n  for core pandas `ProfileReport` usage, `df.profile_report()`, HTML\u002FJSON\u002Fnotebook\n  output calls, time-series mode, type schemas, supported file shapes, and a\n  tiny report-generation smoke helper.\n- Read [sub-skills\u002Fcli-and-automation\u002FSKILL.md](sub-skills\u002Fcli-and-automation\u002FSKILL.md)\n  for `data_profiling` \u002F `pandas_profiling` command-line usage, supported input\n  extensions, parser flags, default output naming, and automation in DAGs or IDE\n  tasks.\n- Read [sub-skills\u002Fconfiguration-and-output\u002FSKILL.md](sub-skills\u002Fconfiguration-and-output\u002FSKILL.md)\n  for `Settings`, YAML config files, `PROFILE_` environment variables,\n  minimal\u002Fexplorative section controls, HTML assets\u002Fthemes, cache invalidation,\n  and serialization.\n- Read [sub-skills\u002Fcomparison-and-quality\u002FSKILL.md](sub-skills\u002Fcomparison-and-quality\u002FSKILL.md)\n  for comparing profile reports, sensitive-data redaction, custom samples,\n  dataset metadata, data dictionaries, type schema, quality output access, and\n  Great Expectations caveats.\n- Read [sub-skills\u002Fintegrations-and-backends\u002FSKILL.md](sub-skills\u002Fintegrations-and-backends\u002FSKILL.md)\n  for optional Spark, notebook widgets, Bytewax\u002Fstreaming snapshots, interactive\n  app embedding, other DataFrame libraries, PyCharm integration, optional\n  dependencies, and backend readiness checks.\n\n## Shared references\n\n- [references\u002Fpackage-overview.md](references\u002Fpackage-overview.md) summarizes\n  package identity, primary APIs, extras, migration naming, and capability\n  boundaries shared across sub-skills.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers\n  cross-cutting install\u002Fimport, optional dependency, data, rendering, and stale\n  version issues.\n- [references\u002Fdevelopment-and-maintenance.md](references\u002Fdevelopment-and-maintenance.md)\n  is for maintainers editing or testing a checkout; package users usually do\n  not need it.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json)\n  stores structured scenario metadata for future managed repo-skill imports.\n\n## High-value entry points\n\n- `from data_profiling import ProfileReport, compare`\n- `ProfileReport(df, minimal=True, progress_bar=False).to_file(\"report.html\")`\n- `df.profile_report(...)` after importing `data_profiling`\n- `data_profiling --minimal --silent data.csv report.html`\n- `profile.to_json()`, `profile.to_html()`, `profile.get_description()`\n- `profile_a.compare(profile_b)` or `compare([profile_a, profile_b])`\n\n## Backend and optional dependency honesty\n\nThe verified core scope is CPU\u002FPandas package usage. Spark support is a\nfirst-class optional workflow, but it requires Java plus PySpark and was not\nverified in the production environment used to create this skill. Notebook\nwidgets require the notebook extra and active widget support. Great Expectations\nsupport remains in source APIs, but the public docs state that current versions\nno longer support that integration; treat it as a legacy\u002Fcompatibility surface\nunless the user pins compatible versions.\n\n## Default response pattern\n\n1. Identify whether the user wants API, CLI, configuration, comparison\u002Fprivacy,\n   or optional integration guidance.\n2. Read the matching sub-skill and its nearest references\u002Fscripts.\n3. Prefer tiny local fixtures and bundled helpers for validation before running\n   expensive profiles on real data.\n4. Avoid source-checkout dependencies: do not tell the user to open or run\n   repository examples, docs, or tests unless they explicitly ask to maintain a\n   repo checkout.\n5. Preserve privacy: for sensitive datasets, route to `comparison-and-quality`\n   before suggesting samples, duplicates, or numeric treatment of identifiers.\n","# fg-data-profiling\n\nUse this repo skill when a task involves the `fg-data-profiling` Python package\nor its public import `data_profiling`: exploratory data analysis reports,\ndata-quality profiling, HTML\u002FJSON export, command-line report generation,\ncomparison reports, sensitive-data-safe reports, configuration, or optional\nSpark\u002Fnotebook integrations.\n\nDo not use this skill as proof that the original repository checkout is present.\nAll runnable helpers and operational references needed by future agents are\nbundled in this skill tree.\n\n## Install and import check\n\nFor normal package usage, install the public distribution and import the current\nmodule name:\n\n```bash\npython -m pip install -U fg-data-profiling\npython - \u003C\u003C'PY'\nimport data_profiling\nfrom data_profiling import ProfileReport, compare\nprint(data_profiling.__version__)\nprint(ProfileReport)\nprint(compare)\nPY\n```\n\nThe repository also exposes a deprecated compatibility import named\n`ydata_profiling` and a legacy CLI name `pandas_profiling`; prefer the\n`data_profiling` import and `data_profiling` CLI for new work.\n\nRun [scripts\u002Fcheck_environment.py](scripts\u002Fcheck_environment.py) when you need a\nsafe package\u002Fimport\u002FCLI diagnostic before deciding which sub-skill to read.\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\nrefreshing this skill or comparing it with a new checkout.\n\n## Route by task\n\n- Read [sub-skills\u002Fprofiling-workflows\u002FSKILL.md](sub-skills\u002Fprofiling-workflows\u002FSKILL.md)\n  for core pandas `ProfileReport` usage, `df.profile_report()`, HTML\u002FJSON\u002Fnotebook\n  output calls, time-series mode, type schemas, supported file shapes, and a\n  tiny report-generation smoke helper.\n- Read [sub-skills\u002Fcli-and-automation\u002FSKILL.md](sub-skills\u002Fcli-and-automation\u002FSKILL.md)\n  for `data_profiling` \u002F `pandas_profiling` command-line usage, supported input\n  extensions, parser flags, default output naming, and automation in DAGs or IDE\n  tasks.\n- Read [sub-skills\u002Fconfiguration-and-output\u002FSKILL.md](sub-skills\u002Fconfiguration-and-output\u002FSKILL.md)\n  for `Settings`, YAML config files, `PROFILE_` environment variables,\n  minimal\u002Fexplorative section controls, HTML assets\u002Fthemes, cache invalidation,\n  and serialization.\n- Read [sub-skills\u002Fcomparison-and-quality\u002FSKILL.md](sub-skills\u002Fcomparison-and-quality\u002FSKILL.md)\n  for comparing profile reports, sensitive-data redaction, custom samples,\n  dataset metadata, data dictionaries, type schema, quality output access, and\n  Great Expectations caveats.\n- Read [sub-skills\u002Fintegrations-and-backends\u002FSKILL.md](sub-skills\u002Fintegrations-and-backends\u002FSKILL.md)\n  for optional Spark, notebook widgets, Bytewax\u002Fstreaming snapshots, interactive\n  app embedding, other DataFrame libraries, PyCharm integration, optional\n  dependencies, and backend readiness checks.\n\n## Shared references\n\n- [references\u002Fpackage-overview.md](references\u002Fpackage-overview.md) summarizes\n  package identity, primary APIs, extras, migration naming, and capability\n  boundaries shared across sub-skills.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers\n  cross-cutting install\u002Fimport, optional dependency, data, rendering, and stale\n  version issues.\n- [references\u002Fdevelopment-and-maintenance.md](references\u002Fdevelopment-and-maintenance.md)\n  is for maintainers editing or testing a checkout; package users usually do\n  not need it.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json)\n  stores structured scenario metadata for future managed repo-skill imports.\n\n## High-value entry points\n\n- `from data_profiling import ProfileReport, compare`\n- `ProfileReport(df, minimal=True, progress_bar=False).to_file(\"report.html\")`\n- `df.profile_report(...)` after importing `data_profiling`\n- `data_profiling --minimal --silent data.csv report.html`\n- `profile.to_json()`, `profile.to_html()`, `profile.get_description()`\n- `profile_a.compare(profile_b)` or `compare([profile_a, profile_b])`\n\n## Backend and optional dependency honesty\n\nThe verified core scope is CPU\u002FPandas package usage. Spark support is a\nfirst-class optional workflow, but it requires Java plus PySpark and was not\nverified in the production environment used to create this skill. Notebook\nwidgets require the notebook extra and active widget support. Great Expectations\nsupport remains in source APIs, but the public docs state that current versions\nno longer support that integration; treat it as a legacy\u002Fcompatibility surface\nunless the user pins compatible versions.\n\n## Default response pattern\n\n1. Identify whether the user wants API, CLI, configuration, comparison\u002Fprivacy,\n   or optional integration guidance.\n2. Read the matching sub-skill and its nearest references\u002Fscripts.\n3. Prefer tiny local fixtures and bundled helpers for validation before running\n   expensive profiles on real data.\n4. Avoid source-checkout dependencies: do not tell the user to open or run\n   repository examples, docs, or tests unless they explicitly ask to maintain a\n   repo checkout.\n5. Preserve privacy: for sensitive datasets, route to `comparison-and-quality`\n   before suggesting samples, duplicates, or numeric treatment of identifiers.\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",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 fg-data-profiling",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill fg-data-profiling",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill fg-data-profiling","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\u002FSKILL.md",[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fdevelopment-and-maintenance.md","REFERENCE","参考文档",3360,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Freferences\u002Fdevelopment-and-maintenance.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fpackage-overview.md",4127,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Freferences\u002Fpackage-overview.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-provenance.md",2874,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Freferences\u002Frepo-provenance.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Frepo-routing-metadata.json",347,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Freferences\u002Frepo-routing-metadata.json",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Ftroubleshooting.md",4236,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ffg-data-profiling\u002Freferences\u002Ftroubleshooting.md",[71,78,83,90,97,104],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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",[],[]]