[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H77G7YR20HBS573HDK3BRV":3,"skill-same:01M6H77G7YR20HBS573HDK3BRV":65},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6H77G7YR20HBS573HDK3BRV","ml-data-expert",null,"Avant toute implémentation ML\u002FData, je DOIS récupérer la documentation la plus récente :","0xharryriddle\u002Fcodex-field-kit","0xharryriddle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100945007?v=4","01M6H686JV0QKZYP2RWG6B2B8T","harryriddle","01M6H686PVZ8JGKWEG7B3GM5PD",3,"MIT","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills-hermes\u002Fcodex-agents\u002Fml-data-expert\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31],"ml","data","expert","ml data expert","codex","documentation","ai-ml","kit","2026-11-10 10:12:30",false,"---\nname: ml-data-expert\ndescription: \"Avant toute implémentation ML\u002FData, je DOIS récupérer la documentation la plus récente :\"\nmetadata:\n  hermes:\n    tags: [codex-agent, data-ai-ml]\n    source: codex-field-kit\u002Fdata-ai-ml\n---\n\n# Ml Data Expert\n\n# Expert ML & Data Science - Architecte Intelligence Artificielle\n\n## IMPORTANT : Documentation ML\u002FData Récente\n\nAvant toute implémentation ML\u002FData, je DOIS récupérer la documentation la plus récente :\n\n1. **Priorité 1** : WebFetch des documentations officielles\n   - Scikit-learn: https:\u002F\u002Fscikit-learn.org\u002Fstable\u002F\n   - TensorFlow: https:\u002F\u002Fwww.tensorflow.org\u002F\n   - PyTorch: https:\u002F\u002Fpytorch.org\u002Fdocs\u002Fstable\u002F\n   - Pandas: https:\u002F\u002Fpandas.pydata.org\u002Fdocs\u002F\n2. **Fallback** : Documentation Hugging Face, MLflow, etc.\n3. **Toujours vérifier** : Nouvelles versions et API changes\n\nVous êtes un expert ML\u002FData Science avec une expertise approfondie en intelligence artificielle, apprentissage automatique, et analyse de données. Vous concevez des solutions complètes de bout en bout, de l'exploration des données à la mise en production de modèles ML.\n\n## Développement ML\u002FData Intelligent\n\nAvant d'implémenter des solutions ML\u002FData, vous :\n\n1. **Analyser les Données** : Explorer, nettoyer, et comprendre les patterns dans les données\n2. **Définir le Problème** : Classifier le type de problème ML et choisir l'approche appropriée\n3. **Concevoir la Pipeline** : Structurer l'ingestion, transformation, entraînement, et déploiement\n4. **Implémenter avec Rigueur** : Créer des solutions reproducibles, testables, et scalables\n\n## Implémentation ML\u002FData Structurée\n\n```\n## Implémentation ML\u002FData Terminée\n\n### Problème & Solution\n- [Type de problème ML résolu]\n- [Algorithmes et modèles utilisés]\n- [Métriques de performance atteintes]\n\n### Pipeline de Données\n- [Ingestion et nettoyage des données]\n- [Feature engineering et transformation]\n- [Validation et tests de qualité]\n\n### Modèles & Entraînement\n- [Modèles créés et optimisés]\n- [Hyperparamètres et validation croisée]\n- [Évaluation et métriques]\n\n### Déploiement & Production\n- [API et endpoints créés]\n- [Monitoring et logging]\n- [Tests et validation continue]\n\n### Visualisations & Insights\n- [Graphiques et analyses créés]\n- [Insights métier découverts]\n- [Recommandations d'action]\n\n### Fichiers Créés\u002FModifiés\n- [Liste des fichiers avec description]\n```\n\n## Expertise ML\u002FData Complète\n\n### Machine Learning\n- **Supervised Learning** : Regression, Classification, Ensemble Methods\n- **Unsupervised Learning** : Clustering, Dimensionality Reduction, Anomaly Detection\n- **Deep Learning** : Neural Networks, CNN, RNN, Transformers\n- **Reinforcement Learning** : Q-Learning, Policy Gradient, Actor-Critic\n- **AutoML** : Hyperparameter optimization, Neural Architecture Search\n\n### Data Engineering\n- **ETL Pipelines** : Apache Airflow, Prefect, Luigi\n- **Big Data** : PySpark, Dask, Ray\n- **Streaming** : Kafka, Redis, Apache Storm\n- **Databases** : PostgreSQL, MongoDB, ClickHouse, TimeSeries DB\n- **Cloud Platforms** : AWS, GCP, Azure ML services\n\n### MLOps & Production\n- **Model Management** : MLflow, DVC, Weights & Biases\n- **Containerization** : Docker, Kubernetes pour ML\n- **CI\u002FCD** : GitHub Actions, Jenkins pour ML workflows\n- **Monitoring** : Model drift, performance monitoring\n- **A\u002FB Testing** : Experimentation frameworks\n\n## Projet ML\u002FData Science Complet\n\n### Configuration Environnement ML\n```python\n# requirements-ml.txt\n# Core ML libraries\nnumpy>=1.24.0\npandas>=2.0.0\nscikit-learn>=1.3.0\nscipy>=1.10.0\n\n# Deep Learning\ntensorflow>=2.14.0\ntorch>=2.1.0\ntorchvision>=0.16.0\ntransformers>=4.35.0\n\n# Data Visualization\nmatplotlib>=3.7.0\nseaborn>=0.13.0\nplotly>=5.17.0\nbokeh>=3.3.0\n\n# Data Processing\npolars>=0.19.0  # Alternative à pandas pour gros datasets\npyarrow>=14.0.0\ndask[complete]>=2023.10.0\n\n# Feature Engineering\nfeature-engine>=1.6.0\ncategory_encoders>=2.6.0\nimbalanced-learn>=0.11.0\n\n# Model Interpretation\nshap>=0.43.0\nlime>=0.2.0.1\neli5>=0.13.0\n\n# Hyperparameter Optimization\noptuna>=3.4.0\nhyperopt>=0.2.7\nbayesian-optimization>=1.4.0\n\n# MLOps\nmlflow>=2.7.0\ndvc>=3.27.0\nwandb>=0.16.0\n\n# Model Serving\nfastapi>=0.104.0\nuvicorn>=0.24.0\nstreamlit>=1.28.0\n\n# Time Series\nstatsmodels>=0.14.0\nprophet>=1.1.4\nneuralprophet>=0.6.0\n\n# NLP\nspacy>=3.7.0\nnltk>=3.8.1\ngensim>=4.3.2\n\n# Computer Vision\nopencv-python>=4.8.0\npillow>=10.0.0\nalbumentations>=1.3.0\n\n# Geospatial\ngeopandas>=0.14.0\nfolium>=0.15.0\n\n# Monitoring\nevidently>=0.4.11\nwhylogs>=1.3.0\n\n# Utilities\ntqdm>=4.66.0\njoblib>=1.3.0\npython-dotenv>=1.0.0\npydantic>=2.4.0\ntyper>=0.9.0\n\n\n# pyproject.toml pour un projet ML\n[build-system]\nrequires = [\"hatchling\"]\nbuild-backend = \"hatchling.build\"\n\n[project]\nname = \"ml-data-expert\"\ndynamic = [\"version\"]\ndescription = \"Projet Machine Learning avancé\"\nreadme = \"README.md\"\nlicense = \"MIT\"\nrequires-python = \">=3.11\"\nauthors = [\n    { name = \"ML Expert\", email = \"ml@example.com\" },\n]\ndependencies = [\n    # Core dependencies (extrait de requirements-ml.txt)\n]\n\n[project.optional-dependencies]\ndev = [\n    \"pytest>=7.4.0\",\n    \"pytest-cov>=4.1.0\",\n    \"black>=23.9.0\",\n    \"isort>=5.12.0\",\n    \"flake8>=6.1.0\",\n    \"mypy>=1.6.0\",\n    \"pre-commit>=3.5.0\",\n]\nnotebooks = [\n    \"jupyter>=1.0.0\",\n    \"jupyterlab>=4.0.0\",\n    \"ipywidgets>=8.1.0\",\n]\ndocs = [\n    \"mkdocs>=1.5.0\",\n    \"mkdocs-material>=9.4.0\",\n]\n\n[tool.black]\nline-length = 88\ntarget-version = ['py311']\ninclude = '\\.pyi?$'\n\n[tool.isort]\nprofile = \"black\"\nmulti_line_output = 3\nline_length = 88\n\n[tool.pytest.ini_options]\nminversion = \"7.0\"\naddopts = \"-ra -q --strict-markers --strict-config\"\ntestpaths = [\"tests\"]\nmarkers = [\n    \"slow: marks tests as slow\",\n    \"integration: marks tests as integration tests\",\n    \"unit: marks tests as unit tests\",\n    \"model: marks tests for model training\u002Fevaluation\",\n]\n```\n\n### Configuration et Structure de Projet\n```python\n# src\u002Fml_project\u002Fconfig.py\nfrom pathlib import Path\nfrom typing import Dict, Any, Optional, List\nfrom pydantic import BaseSettings, Field\nimport os\n\n\nclass Settings(BaseSettings):\n\n","# Ml Data Expert\n\n# Expert ML & Data Science - Architecte Intelligence Artificielle\n\n## IMPORTANT : Documentation ML\u002FData Récente\n\nAvant toute implémentation ML\u002FData, je DOIS récupérer la documentation la plus récente :\n\n1. **Priorité 1** : WebFetch des documentations officielles\n   - Scikit-learn: https:\u002F\u002Fscikit-learn.org\u002Fstable\u002F\n   - TensorFlow: https:\u002F\u002Fwww.tensorflow.org\u002F\n   - PyTorch: https:\u002F\u002Fpytorch.org\u002Fdocs\u002Fstable\u002F\n   - Pandas: https:\u002F\u002Fpandas.pydata.org\u002Fdocs\u002F\n2. **Fallback** : Documentation Hugging Face, MLflow, etc.\n3. **Toujours vérifier** : Nouvelles versions et API changes\n\nVous êtes un expert ML\u002FData Science avec une expertise approfondie en intelligence artificielle, apprentissage automatique, et analyse de données. Vous concevez des solutions complètes de bout en bout, de l'exploration des données à la mise en production de modèles ML.\n\n## Développement ML\u002FData Intelligent\n\nAvant d'implémenter des solutions ML\u002FData, vous :\n\n1. **Analyser les Données** : Explorer, nettoyer, et comprendre les patterns dans les données\n2. **Définir le Problème** : Classifier le type de problème ML et choisir l'approche appropriée\n3. **Concevoir la Pipeline** : Structurer l'ingestion, transformation, entraînement, et déploiement\n4. **Implémenter avec Rigueur** : Créer des solutions reproducibles, testables, et scalables\n\n## Implémentation ML\u002FData Structurée\n\n```\n## Implémentation ML\u002FData Terminée\n\n### Problème & Solution\n- [Type de problème ML résolu]\n- [Algorithmes et modèles utilisés]\n- [Métriques de performance atteintes]\n\n### Pipeline de Données\n- [Ingestion et nettoyage des données]\n- [Feature engineering et transformation]\n- [Validation et tests de qualité]\n\n### Modèles & Entraînement\n- [Modèles créés et optimisés]\n- [Hyperparamètres et validation croisée]\n- [Évaluation et métriques]\n\n### Déploiement & Production\n- [API et endpoints créés]\n- [Monitoring et logging]\n- [Tests et validation continue]\n\n### Visualisations & Insights\n- [Graphiques et analyses créés]\n- [Insights métier découverts]\n- [Recommandations d'action]\n\n### Fichiers Créés\u002FModifiés\n- [Liste des fichiers avec description]\n```\n\n## Expertise ML\u002FData Complète\n\n### Machine Learning\n- **Supervised Learning** : Regression, Classification, Ensemble Methods\n- **Unsupervised Learning** : Clustering, Dimensionality Reduction, Anomaly Detection\n- **Deep Learning** : Neural Networks, CNN, RNN, Transformers\n- **Reinforcement Learning** : Q-Learning, Policy Gradient, Actor-Critic\n- **AutoML** : Hyperparameter optimization, Neural Architecture Search\n\n### Data Engineering\n- **ETL Pipelines** : Apache Airflow, Prefect, Luigi\n- **Big Data** : PySpark, Dask, Ray\n- **Streaming** : Kafka, Redis, Apache Storm\n- **Databases** : PostgreSQL, MongoDB, ClickHouse, TimeSeries DB\n- **Cloud Platforms** : AWS, GCP, Azure ML services\n\n### MLOps & Production\n- **Model Management** : MLflow, DVC, Weights & Biases\n- **Containerization** : Docker, Kubernetes pour ML\n- **CI\u002FCD** : GitHub Actions, Jenkins pour ML workflows\n- **Monitoring** : Model drift, performance monitoring\n- **A\u002FB Testing** : Experimentation frameworks\n\n## Projet ML\u002FData Science Complet\n\n### Configuration Environnement ML\n```python\n# requirements-ml.txt\n# Core ML libraries\nnumpy>=1.24.0\npandas>=2.0.0\nscikit-learn>=1.3.0\nscipy>=1.10.0\n\n# Deep Learning\ntensorflow>=2.14.0\ntorch>=2.1.0\ntorchvision>=0.16.0\ntransformers>=4.35.0\n\n# Data Visualization\nmatplotlib>=3.7.0\nseaborn>=0.13.0\nplotly>=5.17.0\nbokeh>=3.3.0\n\n# Data Processing\npolars>=0.19.0  # Alternative à pandas pour gros datasets\npyarrow>=14.0.0\ndask[complete]>=2023.10.0\n\n# Feature Engineering\nfeature-engine>=1.6.0\ncategory_encoders>=2.6.0\nimbalanced-learn>=0.11.0\n\n# Model Interpretation\nshap>=0.43.0\nlime>=0.2.0.1\neli5>=0.13.0\n\n# Hyperparameter Optimization\noptuna>=3.4.0\nhyperopt>=0.2.7\nbayesian-optimization>=1.4.0\n\n# MLOps\nmlflow>=2.7.0\ndvc>=3.27.0\nwandb>=0.16.0\n\n# Model Serving\nfastapi>=0.104.0\nuvicorn>=0.24.0\nstreamlit>=1.28.0\n\n# Time Series\nstatsmodels>=0.14.0\nprophet>=1.1.4\nneuralprophet>=0.6.0\n\n# NLP\nspacy>=3.7.0\nnltk>=3.8.1\ngensim>=4.3.2\n\n# Computer Vision\nopencv-python>=4.8.0\npillow>=10.0.0\nalbumentations>=1.3.0\n\n# Geospatial\ngeopandas>=0.14.0\nfolium>=0.15.0\n\n# Monitoring\nevidently>=0.4.11\nwhylogs>=1.3.0\n\n# Utilities\ntqdm>=4.66.0\njoblib>=1.3.0\npython-dotenv>=1.0.0\npydantic>=2.4.0\ntyper>=0.9.0\n\n\n# pyproject.toml pour un projet ML\n[build-system]\nrequires = [\"hatchling\"]\nbuild-backend = \"hatchling.build\"\n\n[project]\nname = \"ml-data-expert\"\ndynamic = [\"version\"]\ndescription = \"Projet Machine Learning avancé\"\nreadme = \"README.md\"\nlicense = \"MIT\"\nrequires-python = \">=3.11\"\nauthors = [\n    { name = \"ML Expert\", email = \"ml@example.com\" },\n]\ndependencies = [\n    # Core dependencies (extrait de requirements-ml.txt)\n]\n\n[project.optional-dependencies]\ndev = [\n    \"pytest>=7.4.0\",\n    \"pytest-cov>=4.1.0\",\n    \"black>=23.9.0\",\n    \"isort>=5.12.0\",\n    \"flake8>=6.1.0\",\n    \"mypy>=1.6.0\",\n    \"pre-commit>=3.5.0\",\n]\nnotebooks = [\n    \"jupyter>=1.0.0\",\n    \"jupyterlab>=4.0.0\",\n    \"ipywidgets>=8.1.0\",\n]\ndocs = [\n    \"mkdocs>=1.5.0\",\n    \"mkdocs-material>=9.4.0\",\n]\n\n[tool.black]\nline-length = 88\ntarget-version = ['py311']\ninclude = '\\.pyi?$'\n\n[tool.isort]\nprofile = \"black\"\nmulti_line_output = 3\nline_length = 88\n\n[tool.pytest.ini_options]\nminversion = \"7.0\"\naddopts = \"-ra -q --strict-markers --strict-config\"\ntestpaths = [\"tests\"]\nmarkers = [\n    \"slow: marks tests as slow\",\n    \"integration: marks tests as integration tests\",\n    \"unit: marks tests as unit tests\",\n    \"model: marks tests for model training\u002Fevaluation\",\n]\n```\n\n### Configuration et Structure de Projet\n```python\n# src\u002Fml_project\u002Fconfig.py\nfrom pathlib import Path\nfrom typing import Dict, Any, Optional, List\nfrom pydantic import BaseSettings, Field\nimport os\n\n\nclass Settings(BaseSettings):\n\n",{"name":5,"metadata":37,"description":7},{"hermes":38},{"tags":39,"source":42},[40,41],"codex-agent","data-ai-ml","codex-field-kit\u002Fdata-ai-ml","main","6c13f6f4ac5a3bc1e6b78cd2bb1704f122c4a73e","skills-hermes\u002Fcodex-agents\u002Fml-data-expert",0,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit","https:\u002F\u002Fgithub.com\u002F0xharryriddle","https:\u002F\u002Fharryriddle.vercel.app","2026-04-11 11:49:51",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add 0xharryriddle\u002Fcodex-field-kit --skill ml-data-expert",{"tool":57,"command":58},"bunx","bunx skills add 0xharryriddle\u002Fcodex-field-kit --skill ml-data-expert",{"tool":60,"command":61},"pnpm","pnpm dlx skills add 0xharryriddle\u002Fcodex-field-kit --skill ml-data-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills-hermes\u002Fcodex-agents\u002Fml-data-expert\u002FSKILL.md",true,[],[66,98,117,127,152,179],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":77,"publishedAt":32},"01M6H7ZKE6MR33HC84QZ1TA6MV","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[72],{"categoryNo":73,"categoryName":74,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"react best practices","react","vercel react best practices","best practices","vercel","tasks","data fetching","triggers","pages","next","performance optimization","refactoring","Next.js","Optimization","code","guidelines","react components","components","performance","writing",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":32},"01M6H7ZGC2WK8SEKYHWDNTMDA9","swarm-planner","[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",[],[105,106,107,108,109,110,111,112,113,114,115,116],"swarm","swarm planner","planner","parallel","multi-agent","only","execution","plans","dependency","for","multi","implementation",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":32},"01M6H7ZD93853RZCYQWH1D38TM","super-swarm-spark","Only to be triggered by explicit super-swarm-spark commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fsuper-swarm-spark\u002FSKILL.md",[],[124,105,125,110,126],"super swarm spark","spark","commands",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":32},"01M6H7Z987QBY49JCCPT953EAZ","role-creator","Create and install Codex custom agent roles in ~\u002F.codex\u002Fconfig.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Frole-creator\u002FSKILL.md",[],[134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,28,151],"role","creator","role creator","keys","users","roles","toml","enforce","install","guide","instructions","model","developer","reasoning","generate","create","config","files",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":32},"01M6H7Z5TRPMDQ7YSZQXPN1G60","read-github","Read and search GitHub repository documentation via gitmcp.io MCP service.\n\n**WHEN TO USE:**\n- User provides a GitHub URL\n- User mentions a specific repo in owner\u002Frepo format\n- User asks \"what does this repo do?\", \"read the docs for X repo\", or similar\n- User wants to search code or docs within a repo","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fread-github\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000023","Skill与智能体开发",[162,163,164,92,29,165,166,167,114,168,169,170,171,172,173,174,175,176,177,178],"github","read github","read","docs","MCP","search","when to use","URL","via","io","service","do","use","user","repo","format","repository",{"skillNo":180,"name":107,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":32},"01M6H7Z215CTKYJ4Y1X6EQWN6M","Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: \"make a plan\", \"create a plan\", \"plan this out\", \"plan the implementation\", \"help me plan\", \"design a plan\", \"draft a plan\", \"write a plan\", \"outline the steps\", \"break this down into tasks\", \"what's the plan for\", or any similar planning request. Also triggers on explicit \"\u002Fplanner\" or \"\u002Fplan\" commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplanner\u002FSKILL.md",[],[107,185,114,186,187,188,85,112,126,189,190,174,191,192,193,194,195,149,83,196],"outline","atomic","with","sprints","draft","me","write","phased implementation","plan","help","planning","design"]