[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QWW503VEF9SHT192T71XNP":3,"skill-same:01M6QWW503VEF9SHT192T71XNP":104},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6QWW503VEF9SHT192T71XNP","sap-hana-ml",null,"SAP HANA Machine Learning Python Client (hana-ml) development skill.\n\nUse when: Building ML solutions with SAP HANA's in-database machine learning\nusing Python hana-ml library for PAL\u002FAPL algorithms, DataFrame operations,\nAutoML, model persistence, and visualization.\n\nKeywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics,\nHANA DataFrame, ConnectionContext, classification, regression, clustering,\ntime series, ARIMA, gradient boosting, AutoML, SHAP, model storage","VRIL-LABS\u002Fskill-jam","VRIL-LABS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F272046472?v=4","01M6QR9PNWM28WZYJJASER1RG2","𝗩𝗥𝗜𝗟 𝗟𝗔𝗕𝗦","01M6QR9PT6Q6JDCQ97EQBDX6E4",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"sap hana ml","ml","sap","regression","gradient","2025","predictive analytics","gradient boosting","arima","algorithms","time","storage","model","clustering","time series","library","dataframe","database","visualization","analytics","2026-11-10 10:12:30",false,"---\nname: sap-hana-ml\ndescription: |\n  SAP HANA Machine Learning Python Client (hana-ml) development skill.\n  \n  Use when: Building ML solutions with SAP HANA's in-database machine learning\n  using Python hana-ml library for PAL\u002FAPL algorithms, DataFrame operations,\n  AutoML, model persistence, and visualization.\n  \n  Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics,\n  HANA DataFrame, ConnectionContext, classification, regression, clustering,\n  time series, ARIMA, gradient boosting, AutoML, SHAP, model storage\nlicense: GPL-3.0\nmetadata:\n  version: 1.1.0\n  last_verified: 2025-11-27\n  package_version: 2.22.241011\n---\n\n# SAP HANA ML Python Client (hana-ml)\n\n**Package Version**: 2.22.241011  \n**Last Verified**: 2025-11-27\n\n## Table of Contents\n\n- [Installation & Setup](#installation--setup)\n- [Quick Start](#quick-start)\n- [Core Libraries](#core-libraries)\n- [Common Patterns](#common-patterns)\n- [Best Practices](#best-practices)\n- [Bundled Resources](#bundled-resources)\n\n---\n\n## Installation & Setup\n\n```bash\npip install hana-ml\n```\n\n**Requirements**: Python 3.8+, SAP HANA 2.0 SPS03+ or SAP HANA Cloud\n\n---\n\n## Quick Start\n\n### Connection & DataFrame\n\n```python\nfrom hana_ml import ConnectionContext\n\n# Connect\nconn = ConnectionContext(\n    address='\u003Chostname>',\n    port=443,\n    user='\u003Cusername>',\n    password='\u003Cpassword>',\n    encrypt=True\n)\n\n# Create DataFrame\ndf = conn.table('MY_TABLE', schema='MY_SCHEMA')\nprint(f\"Shape: {df.shape}\")\ndf.head(10).collect()\n```\n\n### PAL Classification\n\n```python\nfrom hana_ml.algorithms.pal.unified_classification import UnifiedClassification\n\n# Train model\nclf = UnifiedClassification(func='RandomDecisionTree')\nclf.fit(train_df, features=['F1', 'F2', 'F3'], label='TARGET')\n\n# Predict & evaluate\npredictions = clf.predict(test_df, features=['F1', 'F2', 'F3'])\nscore = clf.score(test_df, features=['F1', 'F2', 'F3'], label='TARGET')\n```\n\n### APL AutoML\n\n```python\nfrom hana_ml.algorithms.apl.classification import AutoClassifier\n\n# Automated classification\nauto_clf = AutoClassifier()\nauto_clf.fit(train_df, label='TARGET')\npredictions = auto_clf.predict(test_df)\n```\n\n### Model Persistence\n\n```python\nfrom hana_ml.model_storage import ModelStorage\n\nms = ModelStorage(conn)\nclf.name = 'MY_CLASSIFIER'\nms.save_model(model=clf, if_exists='replace')\n```\n\n---\n\n## Core Libraries\n\n### PAL (Predictive Analysis Library)\n- **100+ algorithms** executed in-database\n- Categories: Classification, Regression, Clustering, Time Series, Preprocessing\n- **Key classes**: `UnifiedClassification`, `UnifiedRegression`, `KMeans`, `ARIMA`\n- See: `references\u002FPAL_ALGORITHMS.md` for complete list\n\n### APL (Automated Predictive Library)\n- **AutoML capabilities** with automatic feature engineering\n- **Key classes**: `AutoClassifier`, `AutoRegressor`, `GradientBoostingClassifier`\n- See: `references\u002FAPL_ALGORITHMS.md` for details\n\n### DataFrames\n- **Lazy evaluation** - builds SQL until `collect()` called\n- **In-database processing** for optimal performance\n- See: `references\u002FDATAFRAME_REFERENCE.md` for complete API\n\n### Visualizers\n- **EDA plots**, model explanations, metrics\n- **SHAP integration** for model interpretability\n- See: `references\u002FVISUALIZERS.md` for 14 visualization modules\n\n---\n\n## Common Patterns\n\n### Train-Test Split\n```python\nfrom hana_ml.algorithms.pal.partition import train_test_val_split\n\ntrain, test, val = train_test_val_split(\n    data=df,\n    training_percentage=0.7,\n    testing_percentage=0.2,\n    validation_percentage=0.1\n)\n```\n\n### Feature Importance\n```python\n# APL models\nimportance = auto_clf.get_feature_importances()\n\n# PAL models\nfrom hana_ml.algorithms.pal.preprocessing import FeatureSelection\nfs = FeatureSelection()\nfs.fit(train_df, features=features, label='TARGET')\n```\n\n### Pipeline\n```python\nfrom hana_ml.algorithms.pal.pipeline import Pipeline\nfrom hana_ml.algorithms.pal.preprocessing import Imputer, FeatureNormalizer\n\npipeline = Pipeline([\n    ('imputer', Imputer(strategy='mean')),\n    ('normalizer', FeatureNormalizer()),\n    ('classifier', UnifiedClassification(func='RandomDecisionTree'))\n])\n```\n\n---\n\n## Best Practices\n\n1. **Use lazy evaluation** - Operations build SQL without execution until `collect()`\n2. **Leverage in-database processing** - Keep data in HANA for performance\n3. **Use Unified interfaces** - Consistent APIs across algorithms\n4. **Save models** - Use `ModelStorage` for persistence\n5. **Explain predictions** - Use SHAP explainers for interpretability\n6. **Monitor AutoML** - Use `PipelineProgressStatusMonitor` for long-running jobs\n\n---\n\n## Bundled Resources\n\n### Reference Files\n- **`references\u002FDATAFRAME_REFERENCE.md`** (479 lines)\n  - ConnectionContext API, DataFrame operations, SQL generation\n  \n- **`references\u002FPAL_ALGORITHMS.md`** (869 lines)\n  - Complete PAL algorithm reference (100+ algorithms)\n  - Classification, Regression, Clustering, Time Series, Preprocessing\n  \n- **`references\u002FAPL_ALGORITHMS.md`** (534 lines)\n  - AutoML capabilities, automated feature engineering\n  - AutoClassifier, AutoRegressor, GradientBoosting classes\n  \n- **`references\u002FVISUALIZERS.md`** (704 lines)\n  - 14 visualization modules (EDA, SHAP, metrics, time series)\n  - Plot types, configuration, export options\n  \n- **`references\u002FSUPPORTING_MODULES.md`** (626 lines)\n  - Model storage, spatial analytics, graph algorithms\n  - Text mining, statistics, error handling\n\n---\n\n## Error Handling\n\n```python\nfrom hana_ml.ml_exceptions import Error\n\ntry:\n    clf.fit(train_df, features=features, label='TARGET')\nexcept Error as e:\n    print(f\"HANA ML Error: {e}\")\n```\n\n---\n\n## Documentation\n\n- **Official Docs**: [https:\u002F\u002Fhelp.sap.com\u002Fdoc\u002F1d0ebfe5e8dd44d09606814d83308d4b\u002F2.0.07\u002Fen-US\u002Fhana_ml.html](https:\u002F\u002Fhelp.sap.com\u002Fdoc\u002F1d0ebfe5e8dd44d09606814d83308d4b\u002F2.0.07\u002Fen-US\u002Fhana_ml.html)\n- **PyPI Package**: [https:\u002F\u002Fpypi.org\u002Fproject\u002Fhana-ml\u002F](https:\u002F\u002Fpypi.org\u002Fproject\u002Fhana-ml\u002F)\n","# SAP HANA ML Python Client (hana-ml)\n\n**Package Version**: 2.22.241011  \n**Last Verified**: 2025-11-27\n\n## Table of Contents\n\n- [Installation & Setup](#installation--setup)\n- [Quick Start](#quick-start)\n- [Core Libraries](#core-libraries)\n- [Common Patterns](#common-patterns)\n- [Best Practices](#best-practices)\n- [Bundled Resources](#bundled-resources)\n\n---\n\n## Installation & Setup\n\n```bash\npip install hana-ml\n```\n\n**Requirements**: Python 3.8+, SAP HANA 2.0 SPS03+ or SAP HANA Cloud\n\n---\n\n## Quick Start\n\n### Connection & DataFrame\n\n```python\nfrom hana_ml import ConnectionContext\n\n# Connect\nconn = ConnectionContext(\n    address='\u003Chostname>',\n    port=443,\n    user='\u003Cusername>',\n    password='\u003Cpassword>',\n    encrypt=True\n)\n\n# Create DataFrame\ndf = conn.table('MY_TABLE', schema='MY_SCHEMA')\nprint(f\"Shape: {df.shape}\")\ndf.head(10).collect()\n```\n\n### PAL Classification\n\n```python\nfrom hana_ml.algorithms.pal.unified_classification import UnifiedClassification\n\n# Train model\nclf = UnifiedClassification(func='RandomDecisionTree')\nclf.fit(train_df, features=['F1', 'F2', 'F3'], label='TARGET')\n\n# Predict & evaluate\npredictions = clf.predict(test_df, features=['F1', 'F2', 'F3'])\nscore = clf.score(test_df, features=['F1', 'F2', 'F3'], label='TARGET')\n```\n\n### APL AutoML\n\n```python\nfrom hana_ml.algorithms.apl.classification import AutoClassifier\n\n# Automated classification\nauto_clf = AutoClassifier()\nauto_clf.fit(train_df, label='TARGET')\npredictions = auto_clf.predict(test_df)\n```\n\n### Model Persistence\n\n```python\nfrom hana_ml.model_storage import ModelStorage\n\nms = ModelStorage(conn)\nclf.name = 'MY_CLASSIFIER'\nms.save_model(model=clf, if_exists='replace')\n```\n\n---\n\n## Core Libraries\n\n### PAL (Predictive Analysis Library)\n- **100+ algorithms** executed in-database\n- Categories: Classification, Regression, Clustering, Time Series, Preprocessing\n- **Key classes**: `UnifiedClassification`, `UnifiedRegression`, `KMeans`, `ARIMA`\n- See: `references\u002FPAL_ALGORITHMS.md` for complete list\n\n### APL (Automated Predictive Library)\n- **AutoML capabilities** with automatic feature engineering\n- **Key classes**: `AutoClassifier`, `AutoRegressor`, `GradientBoostingClassifier`\n- See: `references\u002FAPL_ALGORITHMS.md` for details\n\n### DataFrames\n- **Lazy evaluation** - builds SQL until `collect()` called\n- **In-database processing** for optimal performance\n- See: `references\u002FDATAFRAME_REFERENCE.md` for complete API\n\n### Visualizers\n- **EDA plots**, model explanations, metrics\n- **SHAP integration** for model interpretability\n- See: `references\u002FVISUALIZERS.md` for 14 visualization modules\n\n---\n\n## Common Patterns\n\n### Train-Test Split\n```python\nfrom hana_ml.algorithms.pal.partition import train_test_val_split\n\ntrain, test, val = train_test_val_split(\n    data=df,\n    training_percentage=0.7,\n    testing_percentage=0.2,\n    validation_percentage=0.1\n)\n```\n\n### Feature Importance\n```python\n# APL models\nimportance = auto_clf.get_feature_importances()\n\n# PAL models\nfrom hana_ml.algorithms.pal.preprocessing import FeatureSelection\nfs = FeatureSelection()\nfs.fit(train_df, features=features, label='TARGET')\n```\n\n### Pipeline\n```python\nfrom hana_ml.algorithms.pal.pipeline import Pipeline\nfrom hana_ml.algorithms.pal.preprocessing import Imputer, FeatureNormalizer\n\npipeline = Pipeline([\n    ('imputer', Imputer(strategy='mean')),\n    ('normalizer', FeatureNormalizer()),\n    ('classifier', UnifiedClassification(func='RandomDecisionTree'))\n])\n```\n\n---\n\n## Best Practices\n\n1. **Use lazy evaluation** - Operations build SQL without execution until `collect()`\n2. **Leverage in-database processing** - Keep data in HANA for performance\n3. **Use Unified interfaces** - Consistent APIs across algorithms\n4. **Save models** - Use `ModelStorage` for persistence\n5. **Explain predictions** - Use SHAP explainers for interpretability\n6. **Monitor AutoML** - Use `PipelineProgressStatusMonitor` for long-running jobs\n\n---\n\n## Bundled Resources\n\n### Reference Files\n- **`references\u002FDATAFRAME_REFERENCE.md`** (479 lines)\n  - ConnectionContext API, DataFrame operations, SQL generation\n  \n- **`references\u002FPAL_ALGORITHMS.md`** (869 lines)\n  - Complete PAL algorithm reference (100+ algorithms)\n  - Classification, Regression, Clustering, Time Series, Preprocessing\n  \n- **`references\u002FAPL_ALGORITHMS.md`** (534 lines)\n  - AutoML capabilities, automated feature engineering\n  - AutoClassifier, AutoRegressor, GradientBoosting classes\n  \n- **`references\u002FVISUALIZERS.md`** (704 lines)\n  - 14 visualization modules (EDA, SHAP, metrics, time series)\n  - Plot types, configuration, export options\n  \n- **`references\u002FSUPPORTING_MODULES.md`** (626 lines)\n  - Model storage, spatial analytics, graph algorithms\n  - Text mining, statistics, error handling\n\n---\n\n## Error Handling\n\n```python\nfrom hana_ml.ml_exceptions import Error\n\ntry:\n    clf.fit(train_df, features=features, label='TARGET')\nexcept Error as e:\n    print(f\"HANA ML Error: {e}\")\n```\n\n---\n\n## Documentation\n\n- **Official Docs**: [https:\u002F\u002Fhelp.sap.com\u002Fdoc\u002F1d0ebfe5e8dd44d09606814d83308d4b\u002F2.0.07\u002Fen-US\u002Fhana_ml.html](https:\u002F\u002Fhelp.sap.com\u002Fdoc\u002F1d0ebfe5e8dd44d09606814d83308d4b\u002F2.0.07\u002Fen-US\u002Fhana_ml.html)\n- **PyPI Package**: [https:\u002F\u002Fpypi.org\u002Fproject\u002Fhana-ml\u002F](https:\u002F\u002Fpypi.org\u002Fproject\u002Fhana-ml\u002F)\n",{"name":5,"license":15,"metadata":49,"description":53},{"version":50,"last_verified":51,"package_version":52},"1.1.0",1764201600000,"2.22.241011","SAP HANA Machine Learning Python Client (hana-ml) development skill.\n\nUse when: Building ML solutions with SAP HANA's in-database machine learning\nusing Python hana-ml library for PAL\u002FAPL algorithms, DataFrame operations,\nAutoML, model persistence, and visualization.\n\nKeywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics,\nHANA DataFrame, ConnectionContext, classification, regression, clustering,\ntime series, ARIMA, gradient boosting, AutoML, SHAP, model storage\n","main","5b00ad8b9f0787969474ff5e9ec417bb55f23827","skills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml",0,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam","https:\u002F\u002Fvril.li","https:\u002F\u002Fgithub.com\u002FVRIL-LABS","vril.li","𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗮𝗻𝗱 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗖𝗼𝗻𝘀𝗼𝗿𝘁𝗶𝘂𝗺","2026-08-24 09:21:38",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add VRIL-LABS\u002Fskill-jam --skill sap-hana-ml",{"tool":70,"command":71},"bunx","bunx skills add VRIL-LABS\u002Fskill-jam --skill sap-hana-ml",{"tool":73,"command":74},"pnpm","pnpm dlx skills add VRIL-LABS\u002Fskill-jam --skill sap-hana-ml","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002FSKILL.md",true,[78,84,88,92,96,100],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"README.md","REFERENCE","参考文档",4759,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002FREADME.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002FAPL_ALGORITHMS.md",12373,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002Freferences\u002FAPL_ALGORITHMS.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002FDATAFRAME_REFERENCE.md",11664,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002Freferences\u002FDATAFRAME_REFERENCE.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002FPAL_ALGORITHMS.md",18749,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002Freferences\u002FPAL_ALGORITHMS.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002FSUPPORTING_MODULES.md",14651,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002Freferences\u002FSUPPORTING_MODULES.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002FVISUALIZERS.md",13668,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-hana-ml\u002Fskills\u002Fsap-hana-ml\u002Freferences\u002FVISUALIZERS.md",[105,136,150,166,203,226],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":115,"publishedAt":44},"01M6R2CQRG190P09DAHMF8M5QP","three-best-practices","Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL\u002FWebGPU rendering, geometries, materials, textures, lighting, shaders, or TSL.","MIT","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fneversight-skills_feed-three-best-practices-1.0.2\u002FSKILL.md",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135],"best practices","three","three best practices","writing","performance","webgpu","guidelines","tasks","code","shaders","Optimization","3D","use","agent-skills","scenes","lighting","triggers","rendering","when","best practices guidelines",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":44},"01M6R2BPMDYK9XKWPARY0S5MS3","javascript-best-practices","Modern JavaScript best practices and performance optimization guidelines. Use when writing, reviewing, or refactoring JavaScript code to ensure optimal performance, maintainability, and modern patterns.","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fneversight-skills_feed-javascript-best-practices-1.0.2\u002FSKILL.md",[],[143,116,144,119,120,122,124,126,145,146,128,147,148,149,134],"javascript","JavaScript Best Practices","refactoring","performance optimization","patterns","maintainability","name",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":159,"publishedAt":44},"01M6R2B41BN09FYH76BAC5FT7X","css-best-practices","Guidelines for building modern, performant, and accessible CSS using MDN best practices. Use this when styling components, fixing layout shifts, or optimizing CSS performance.","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fneversight-skills_feed-css-best-practices-1.0.3\u002FSKILL.md",[156],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[160,116,161,120,162,122,128,163,164,165,134],"css","css best practices","components","styling","layout","for",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":184,"publishedAt":44},"01M6R2A1CEF123TZCNM1XJ2XQ4","frontend-dev","Full-stack frontend development combining premium UI design, cinematic animations,\nAI-generated media assets, persuasive copywriting, and visual art. Builds complete,\nvisually striking web pages with real media, advanced motion, and compelling copy.\nUse when: building landing pages, marketing sites, product pages, dashboards,\ngenerating media assets (image\u002Fvideo\u002Faudio\u002Fmusic), writing conversion copy,\ncreating generative art, or implementing cinematic scroll animations.","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fminimax-ai-skills-frontend-dev-1.0.1\u002FSKILL.md",[172,173,176,179],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":174,"categoryName":175,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":177,"categoryName":178,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":180,"categoryName":181,"taxonomyType":182,"taxonomyTypeDesc":183},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[185,186,187,188,119,189,160,190,191,192,193,194,195,196,197,198,199,200,201,202],"frontend","dev","frontend dev","design","image","react","ui","Video","Media","Audio","Tailwind","stack","music","aida","framer motion","implementing","framer","generative",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":209,"publishedAt":44},"01M6R20VQ98KDX4J37TGE0FNHW","exa-rate-limits","Implement Exa rate limiting, backoff, and idempotency patterns.\nUse when handling rate limit errors, implementing retry logic,\nor optimizing API request throughput for Exa.\nTrigger with phrases like \"exa rate limit\", \"exa throttling\",\n\"exa 429\", \"exa retry\", \"exa backoff\".","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-research\u002Fjeremylongshore-claude-code-plugins-plus-skills-exa-rate-limits-1.0.0\u002FSKILL.md",[],[210,211,212,213,214,215,216,217,218,147,219,220,221,222,223,200,165,224,225,134],"exa","exa rate limits","rate","limits","throttling","api","read","write","edit","io","throughput","retry","errors","limit","rate limit","request",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":235,"publishedAt":44},"01M6R20FV0TM7ZZTZNG7JQ1A82","exa-deploy-integration","Deploy Exa integrations to Vercel, Fly.io, and Cloud Run platforms.\nUse when deploying Exa-powered applications to production,\nconfiguring platform-specific secrets, or setting up deployment pipelines.\nTrigger with phrases like \"deploy exa\", \"exa Vercel\",\n\"exa production deploy\", \"exa Cloud Run\", \"exa Fly.io\".","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-research\u002Fjeremylongshore-claude-code-plugins-plus-skills-exa-deploy-integration-1.0.0\u002FSKILL.md",[232],{"categoryNo":233,"categoryName":234,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",[236,237,210,238,239,240,241,242,243,244,216,217,218,245,246,247,219,248,249,134],"deploy","integration","exa deploy integration","deployment","run","secrets","fly","Bash","integrations","vercel","up","platform","trigger","cloud run"]