Skill 全量检索

数据工程389,030cloud-image-bakeSkillsMP@openclawBake, 选择, prove, safely retire 云端工作进程图片 crabbox 配置一个-liners.Bake, select, prove, and safely retire a Cloud Worker image with crabbox and config one-liners.#data-engineeringopenclaw/openclawGit 克隆查看详情与安装步骤 → 数据工程253,169crosspostSkillsMP@affaan-m多-平台内容 distribution 跨 X, LinkedIn, 线程, Bluesky. Adapts 内容按 平台使用内容-引擎模式. 帖子 identical 内容跨平台. 使用用户需求 distribute 内容跨 sociMulti-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across soci#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169claude-devfleetSkillsMP@affaan-mClaude DevFleet経由でマルチエージェントコーディングタスクをオーケストレーション — プロジェクトを計画し、分離された作業ツリー内で平行エージェントを派遣し、進捗を監視し、構造化レポートを読む。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169clickhouse-ioSkillsMP@affaan-mClickHouse 数据库模式, 查询优化, 分析, 数据工程最佳实践 high-performance analytical workloads.ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169docker-patternsSkillsMP@affaan-mDocker イメージの構築、最適化、マルチステージビルド、ネットワーク、ボリューム管理。本番環境デプロイメント用のベストプラクティス。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169ralphinho-rfc-pipelineSkillsMP@affaan-mRFC駆動の複数エージェントDAG実行パターン、品質ゲート、マージキュー、ワークユニットオーケストレーション。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169clickhouse-ioSkillsMP@affaan-m고성능 분석 워크로드를 위한 ClickHouse 데이터베이스 패턴, 쿼리 최적화, 분석 및 데이터 엔지니어링 모범 사례.#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169ai-first-engineeringSkillsMP@affaan-m团队中人工智能代理生成大部分实施输出的工程运营模型。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169architecture-decision-recordsSkillsMP@affaan-m在Claude 代码会话期间，将做出的架构决策捕获为结构化的架构决策记录（ADR）。自动检测决策时刻，记录上下文、考虑的替代方案和理由。维护一个ADR日志，以便未来的开发人员理解代码库为何以当前方式构建。在Claude Code会话期间，将做出的架构决策捕获为结构化的架构决策记录（ADR）。自动检测决策时刻，记录上下文、考虑的替代方案和理由。维护一个ADR日志，以便未来的开发人员理解代码库为何以当前方式构建。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169claude-devfleetSkillsMP@affaan-m通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169clickhouse-ioSkillsMP@affaan-mClickHouse数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169dashboard-builderSkillsMP@affaan-m为 Grafana、SigNoz 等平台构建能够回答实际运维人员问题的监控仪表板。适用于将指标转化为可用的仪表板，而非华而不实的展示板。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169healthcare-cdss-patternsSkillsMP@affaan-m临床决策支持系统（CDSS）开发模式。药物相互作用检查、剂量验证、临床评分（NEWS2、qSOFA）、警报严重性分类以及集成到电子病历工作流程中。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169kotlin-exposed-patternsSkillsMP@affaan-mJetBrains Exposed ORM 模式，包括 DSL 查询、DAO 模式、事务、HikariCP 连接池、Flyway 迁移和仓库模式。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169ralphinho-rfc-pipelineSkillsMP@affaan-m基于RFC驱动的多智能体DAG执行模式，包含质量门、合并队列和工作单元编排。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169terminal-opsSkillsMP@affaan-m基于证据优先的仓库执行工作流，适用于ECC。当用户需要运行命令、检查仓库、调试CI失败或推送带有精确执行和验证证明的窄修复时使用。#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169clickhouse-ioSkillsMP@affaan-mClickHouse 数据库模式, 查询优化, 分析, 数据工程最佳实践 high-performance analytical workloads.ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169content-hash-cache-patternSkillsMP@affaan-m缓存 expensive 文件处理结果使用 SHA-256 内容 hashes — 路径-independent, 自动-invalidating, 服务层 separation.Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169claude-devfleetSkillsMP@affaan-mOrchestrate 多-智能体编码任务通过 Claude DevFleet — 计划项目, dispatch 并行智能体隔离 worktrees, 监控进度, 读取结构化报告. 使用 dispatching 并行编码智能体跨 隔离 worktreesOrchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports. Use when dispatching parallel coding agents across isolated worktrees a#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169clickhouse-ioSkillsMP@affaan-mClickHouse 数据库模式, 查询优化, 分析, 数据工程最佳实践 high-performance analytical workloads. 使用编写 ClickHouse 结构查询, analytical 查询缓慢.ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. Use when writing ClickHouse schemas or queries, or when an analytical query is too slow.#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169content-hash-cache-patternSkillsMP@affaan-m缓存 expensive 文件处理结果使用 SHA-256 内容 hashes — 路径-independent, 自动-invalidating, 服务层 separation. 使用 repeated 文件处理缓慢结果 cached invalidated 内容 ratCache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation. Use when repeated file processing is slow and results should be cached and invalidated by content rat#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169crosspostSkillsMP@affaan-m多-平台内容 distribution 跨 X, LinkedIn, 线程, Bluesky. Adapts 内容按 平台使用内容-引擎模式. 帖子 identical 内容跨平台. 使用用户需求 distribute 内容跨 sociMulti-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across soci#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169data-throughput-acceleratorSkillsMP@affaan-m使用 large 数据 ingestion, backfill, 导出, ETL, 仓库加载, manifest catch-up, 表格 synchronization 需要 become much 更快 preserving 数据 correctness.Use when large data ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, or table synchronization needs to become much faster while preserving data correctness.#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169evm-token-decimalsSkillsMP@affaan-m防止 silent decimal mismatch 缺陷跨 EVM chains. 覆盖运行时 decimal 查找, chain-aware 缓存, bridged-词元 precision drift, 安全 normalization bots, 仪表盘, DeFi 工具. 使用 handling 词元 amounts 跨 EPrevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools. Use when handling token amounts across E#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169kotlin-exposed-patternsSkillsMP@affaan-mJetBrains Exposed ORM 模式包括 DSL 查询, DAO 模式, transactions, HikariCP connection pooling, Flyway 迁移, 仓库模式. 使用处理 Exposed ORM — DSL DAO 查询, transactions, pooling, mJetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern. Use when working with the Exposed ORM — DSL or DAO queries, transactions, pooling, or m#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169latency-critical-systemsSkillsMP@affaan-m使用延迟-sensitive 系统 realtime 仪表盘, 市场数据, streaming 智能体, 执行 gateways, 队列, 缓存, HFT-例如基础设施 freshness p95 延迟 matter. 使用 p95 延迟数据 freshness mattUse for latency-sensitive systems such as realtime dashboards, market data, streaming agents, execution gateways, queues, caches, or HFT-like infrastructure where freshness and p95 latency matter. Use when p95 latency or data freshness matt#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169orch-build-mvpSkillsMP@affaan-mOrchestrate bootstrapping 处理 MVP 设计规格说明文档 — ingest 文档, 计划 thin 纵向 slices, 脚手架首先端到端 slice, TDD-实现, 评审, gated 提交. 使用转换 SDD/PRD running staOrchestrate bootstrapping a working MVP from a design or spec document — ingest the doc, plan thin vertical slices, scaffold the first end-to-end slice, then TDD-implement, review, and gated commit. Use to turn an SDD/PRD into a running sta#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169redis-patternsSkillsMP@affaan-mRedis 数据结构模式, 缓存策略, 分布式 locks, 频率限制, pub/sub, connection 管理生产环境应用. 使用新增缓存, 分布式锁, 频率限制, pub/sub Redis,Redis data structure patterns, caching strategies, distributed locks, rate limiting, pub/sub, and connection management for production applications. Use when adding caching, a distributed lock, rate limiting, or pub/sub with Redis, or when #data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169uspto-databaseSkillsMP@affaan-mUSPTO 专利商标数据工作流程官方记录查找, PatentSearch 查询, TSDR 检查, assignment 数据, reproducible IP 研究日志. 使用任务需要官方 United 状态专利商标记录 USPTOUSPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs. Use when a task needs official United States patent or trademark records from USPTO #data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程253,169tasteforge-videoSkillsMP@affaan-m使用文件-driven multimodal 图片, 视频, 3D-asset discovery; taste interviews; distill 应用工作流程; 风格-包校验; editable EDL/FCPXML 导出; provenance 审计; 离线规划 fail closed 在…之前 proviUse for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workflows; style-pack validation; editable EDL/FCPXML export; provenance audits; and offline planning that must fail closed before provi#data-engineeringaffaan-m/eccGit 克隆查看详情与安装步骤 → 数据工程243,171pineconeSkillsMP@NousResearch托管 vector DB 生产环境 RAG 搜索.Managed vector DB for production RAG and search.#data-engineeringnousresearch/hermes-agentGit 克隆查看详情与安装步骤 → 数据工程178,908flutter-cherry-pickSkillsMP@flutter如何 land formal cherry-pick merged PR flutter/flutter 仓库稳定测试版通道. 使用 flutter/flutter landed 拉取请求. 使用 cherry pick 请求 "稳定", "测试版" 分支How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel. Only use for flutter/flutter landed pull requests. Only use when the cherry pick request is into "stable", "beta" or a branch that has the #data-engineeringflutter/flutterGit 克隆查看详情与安装步骤 → 数据工程132,003autoplanSkillsMP@garrytan自动-评审流水线 — 读取完整 CEO, 设计, eng, DX 评审技能 disk 运行 sequentially 自动-决策使用 6 决策原则. (gstack)Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)#data-engineeringgarrytan/gstackGit 克隆查看详情与安装步骤 → 数据工程132,003landing-reportSkillsMP@garrytan读取- 队列仪表盘工作区-aware ship. (gstack)Read-only queue dashboard for workspace-aware ship. (gstack)#data-engineeringgarrytan/gstackGit 克隆查看详情与安装步骤 → 数据工程94,749html-ppt-testing-safety-alertSkillsMP@nexu-iohospital 数据-governance briefing: 患者-数据风险, 控制框架, accountability, approval board give. 构建决策-grade 政策 briefing 演示文稿健康-系统 board, regulators.A hospital data-governance briefing: patient-data risk, the control framework, accountability, and the approval the board must give. Built as a decision-grade policy briefing deck for health-system board, regulators.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749worker-visualizerSkillsMP@nexu-io实时 data/particle/simulation visualizer heavy compute 运行网页工作进程 (off main 线程), optionally sharing 记忆 UI 通过 SharedArrayBuffer, 渲染 canvas 60fps. 产出单个 self-包含A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contain#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749token-mapSkillsMP@nexu-io映射提取 Figma / 来源-代码词元 bag 活动 OD 设计系统, producing deterministic 映射生成阶段 consume.Map an extracted Figma / source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749card-twitterSkillsMP@nexu-ioTwitter quote 数据 card designed pair 帖子.Twitter quote or data card designed to pair with a post.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749html-ppt-testing-safety-alertSkillsMP@nexu-iohospital 数据-governance briefing: 患者-数据风险, 控制框架, accountability, approval board give. 构建决策-grade 政策 briefing 演示文稿健康-系统 board, regulators.A hospital data-governance briefing: patient-data risk, the control framework, accountability, and the approval the board must give. Built as a decision-grade policy briefing deck for health-system board, regulators.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749worker-visualizerSkillsMP@nexu-io实时 data/particle/simulation visualizer heavy compute 运行网页工作进程 (off main 线程), optionally sharing 记忆 UI 通过 SharedArrayBuffer, 渲染 canvas 60fps. 产出单个 self-包含A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contain#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749create-prototype-dashboardSkillsMP@nexu-io创建 polished 运维仪表盘原型 dense KPIs, 状态表格, 聚焦命令-居中布局.Create a polished operations dashboard prototype with dense KPIs, status tables, and a focused command-center layout.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749card-twitterSkillsMP@nexu-ioTwitter quote 数据 card designed pair 帖子.Twitter quote or data card designed to pair with a post.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程94,749digits-fintech-swiss-templateSkillsMP@nexu-ioSwiss-grid fintech 演示文稿模板 black / warm 论文 / neon-lime contrast. 使用用户要求 premium 数据-故事 slides strict 模块化布局, bold numeric cards, restrained 动效, keyboard/click 导航一个 HTML 文件.Swiss-grid fintech deck template in black / warm paper / neon-lime contrast. Use when users ask for premium data-story slides with strict modular layout, bold numeric cards, restrained motion, and keyboard/click navigation in one HTML file.#data-engineeringnexu-io/open-designGit 克隆查看详情与安装步骤 → 数据工程93,077agentdb-advanced-featuresSkillsMP@ruvnet主分支先进 AgentDB 功能包括 QUIC synchronization, 多-数据库管理, 自定义 distance 指标, 混合搜索, 分布式系统集成. 使用构建分布式 AI 系统, 多-智能体 coordination,Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or #data-engineeringruvnet/ruviewGit 克隆查看详情与安装步骤 → 数据工程93,077agentdb-performance-optimizationSkillsMP@ruvnet优化 AgentDB performance quantization (4-32x 记忆 reduction), HNSW indexing (150x 更快搜索), 缓存, 批量运维. 使用优化内存占用, improving 搜索提速, scaling millions vectors.Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.#data-engineeringruvnet/ruviewGit 克隆查看详情与安装步骤 → 数据工程93,077stream-chainSkillsMP@ruvnet流-JSON chaining 多-智能体流水线, 数据转换, sequential 工作流程Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows#data-engineeringruvnet/ruviewGit 克隆查看详情与安装步骤 → 数据工程93,077swarm-advancedSkillsMP@ruvnet先进 swarm orchestration 模式研究, 开发, testing, 复杂分布式工作流程Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows#data-engineeringruvnet/ruviewGit 克隆查看详情与安装步骤 → 数据工程93,077v3-deep-integrationSkillsMP@ruvnet深度 agentic-流程@内测版集成实现 ADR-001. Eliminates 10,000+ duplicate lines 构建 Claude-流程 specialized 扩展 rather 并行实现.Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.#data-engineeringruvnet/ruviewGit 克隆查看详情与安装步骤 → 数据工程93,077v3-memory-unificationSkillsMP@ruvnetUnify 6+ 记忆系统 AgentDB HNSW indexing 150x-12,500x 搜索 improvements. 实现 ADR-006 (Unified 记忆服务) ADR-009 (混合记忆后端).Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).#data-engineeringruvnet/ruviewGit 克隆查看详情与安装步骤 → 数据工程92,889incremental-implementationSkillsMP@addyosmaniDelivers 变更 incrementally thin, verifiable slices. 使用实现功能变更 touches 一个文件, picking up 接下来任务计划. 使用 rolling 变更输出 behind 功能 flag,Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a change out behind a feature flag, when #data-engineeringaddyosmani/agent-skillsGit 克隆查看详情与安装步骤 → 数据工程82,305store-data-structuresSkillsMP@lobehub显式 compatibility 入口 Zustand 数据-shape 指引.Explicit compatibility entry for Zustand data-shape guidance.#data-engineeringlobehub/lobehubGit 克隆查看详情与安装步骤 → 数据工程82,305upstash-workflowSkillsMP@lobehub使用 Upstash 工作流程/QStash 处理函数, 触发, durable 步骤异步 fan-输出.Use for Upstash Workflow/QStash handlers, triggers, durable steps and async fan-out.#data-engineeringlobehub/lobehubGit 克隆查看详情与安装步骤 → 数据工程71,554agentdb-advanced-featuresSkillsMP@ruvnet主分支先进 AgentDB 功能包括 QUIC synchronization, 多-数据库管理, 自定义 distance 指标, 混合搜索, 分布式系统集成. 使用构建分布式 AI 系统, 多-智能体 coordination,Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or #data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554agentdb-performance-optimizationSkillsMP@ruvnet优化 AgentDB performance quantization (4-32x 记忆 reduction), HNSW indexing (150x 更快搜索), 缓存, 批量运维. 使用优化内存占用, improving 搜索提速, scaling millions vectors.Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554memory-managementSkillsMP@ruvnetAgentDB 记忆系统 HNSW vector 搜索. 提供 150x-12,500x 更快模式 retrieval, 持久化存储, 语义搜索能力学习 knowledge 管理. 使用: need 存储成功模式, searchinAgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searchin#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554stream-chainSkillsMP@ruvnet流-JSON chaining 多-智能体流水线, 数据转换, sequential 工作流程Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554swarm-advancedSkillsMP@ruvnet先进 swarm orchestration 模式研究, 开发, testing, 复杂分布式工作流程Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554v3-deep-integrationSkillsMP@ruvnet深度 agentic-流程@内测版集成实现 ADR-001. Eliminates 10,000+ duplicate lines 构建 Claude-流程 specialized 扩展 rather 并行实现.Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554stream-chainSkillsMP@ruvnet流-JSON chaining 多-智能体流水线, 数据转换, sequential 工作流程Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554swarm-advancedSkillsMP@ruvnet先进 swarm orchestration 模式研究, 开发, testing, 复杂分布式工作流程Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554cost-summarySkillsMP@ruvnet单个-shot programmatic dump 成本数据 — total spend, 按-tier, 顶部会话, 预算状态, federation 聚合. JSON Markdown.Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate. JSON or markdown.#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程71,554swarm-advancedSkillsMP@ruvnet先进 swarm orchestration 模式研究, 开发, testing, 复杂分布式工作流程Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows#data-engineeringruvnet/rufloGit 克隆查看详情与安装步骤 → 数据工程68,043openspec-sync-specsSkillsMP@Fission-AI同步 delta 规格说明变更 main 规格说明. 使用用户需求更新 main 规格说明变更 delta 规格说明, 无需 archiving 变更.Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.#data-engineeringfission-ai/openspecGit 克隆查看详情与安装步骤 → 数据工程59,903jq-json-processorSkillsMP@penpot流程, 筛选, 转换 JSON 数据使用 jq - 轻量灵活命令行 JSON processor.Process, filter, and transform JSON data using jq - the lightweight and flexible command-line JSON processor.#data-engineeringpenpot/penpotGit 克隆查看详情与安装步骤 → 数据工程56,358syncable-entity-cache-and-transformSkillsMP@twentyhq创建缓存服务转换实用工具 syncable 实体 Twenty. 使用实现实体-to-flat 转化, 输入 DTO transpilation universal flat 实体, 缓存 recomputation syncable 实体.Create cache services and transformation utilities for syncable entities in Twenty. Use when implementing entity-to-flat conversions, input DTO transpilation to universal flat entities, or cache recomputation for syncable entities.#data-engineeringtwentyhq/twentyGit 克隆查看详情与安装步骤 → 数据工程56,358syncable-entity-types-and-constantsSkillsMP@twentyhqDefine types, 实体, 中心 constant registrations syncable 实体 Twenty's 工作区迁移系统. 使用创建新建 syncable 实体, defining TypeORM 实体, flat 实体 types, registering 中心 constaDefine types, entities, and central constant registrations for syncable entities in Twenty's workspace migration system. Use when creating new syncable entities, defining TypeORM entities, flat entity types, or registering in central consta#data-engineeringtwentyhq/twentyGit 克隆查看详情与安装步骤 → 数据工程47,562prisma-8SkillsMP@prisma全面指南构建 Prisma 8 (Prisma 接下来), 合同-首先数据层. 使用处理 Prisma 代码项目使用 — authoring editing 数据合同 (合同. prisma, PSL, TypeScript builders),Comprehensive guide for building with Prisma 8 (Prisma Next), the contract-first data layer. Use whenever working on Prisma code in a project that uses it — authoring or editing the data contract (contract.prisma, PSL, TypeScript builders),#data-engineeringprisma/prismaGit 克隆查看详情与安装步骤 → 数据工程46,836prepare-providers-documentationSkillsMP@apacheReplace 手册提交-by-提交分类步骤 `breeze release-management prepare-provider-documentation` AI-driven 分类. 提供方待处理变更, 分析 PR (batched 一个 sub-智能体按 拉取请求Replace the manual commit-by-commit classification step in `breeze release-management prepare-provider-documentation` with AI-driven classification. For each provider with pending changes, analyze every PR (batched into one sub-agent per pr#data-engineeringapache/airflowGit 克隆查看详情与安装步骤 → 数据工程44,806logseq-replSkillsMP@logseq启动 coordinate Logseq 开发 REPL 工作流程桌面渲染器 `: app`, Electron main-流程 `: electron`, `: db-worker-node` runtimes 一个 unified 工作流程.Start and coordinate Logseq development REPL workflows for the Desktop renderer `:app`, Electron main-process `:electron`, and `:db-worker-node` runtimes through one unified workflow.#data-engineeringlogseq/logseqGit 克隆查看详情与安装步骤 → 数据工程43,904bidsSkillsMP@K-Dense-AI使用技能处理 Brain Imaging 数据结构 (BIDS) 数据集: organizing neuroscience biomedical 数据 (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, 动效采集, EMG, MR spectroscopy, 行为), querying BIDS 布局Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904daskSkillsMP@K-Dense-AI分布式 computing larger-than-RAM pandas/NumPy 工作流程. 使用 need scale 现有 pandas/NumPy 代码 beyond 记忆跨 集群. Best 并行文件处理, 分布式 ML, 集成现有 pandas coDistributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas co#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904lamindbSkillsMP@K-Dense-AI使用处理 LaminDB, 开源 lineage-原生 lakehouse biological 数据集模型. 覆盖初始化设置, 产物注册, query/search, lineage 跟踪, 校验, ontology-backed 注解 Bionty, 合集Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904pathmlSkillsMP@K-Dense-AI使用 PathML 本地, 研究- computational pathology 工作流程: 加载 tile slides, 构建 preprocessing QC 流水线, 管理 h5path 数据, quantify multiplex 图片, construct spatial 图谱, 计划 bounded 模型推理计算.Use PathML for local, research-only computational pathology workflows: load and tile slides, build preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904polars-bioSkillsMP@K-Dense-AIHigh-performance genomic interval 运维 bioinformatics 文件 I/O Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract BED/VCF/BAM/GFF intervals. Streaming, 云端-原生, 更快 bioframe alternative.High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904polarsSkillsMP@K-Dense-AIHigh-performance DataFrame 函数库 Python ETL, 分析, pandas 迁移. 使用 expression-基于数据 manipulation lazy 查询优化, 并行执行, streaming 输出-of-核心处理, Arrow interoperability, oHigh-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and o#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904pyhealthSkillsMP@K-Dense-AI构建 clinical/healthcare 深度-学习流水线 PyHealth — 加载 EHR/signal/imaging 数据集 (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining 任务 (mortality, readmission, length-of-stay, 药物推荐, sBuild clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, s#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904pytdcSkillsMP@K-Dense-AI使用 Therapeutics 数据 Commons PyTDC Python 软件包注册中心 discovery, approved 数据集访问, 任务-aware splits, evaluator 指标, 基准测试分组, bounded molecular-oracle 工作流程.Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits, evaluator metrics, benchmark groups, and bounded molecular-oracle workflows.#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904vaexSkillsMP@K-Dense-AI使用技能处理分析 large tabular 数据集 (billions rows) exceed 可用 RAM. Vaex excels 输出-of-核心 DataFrame 运维, lazy evaluation, 快速 aggregations, 高效 visualization big 数据, mUse this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and m#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程43,904zarr-pythonSkillsMP@K-Dense-AIChunked N-D 数组云端存储 (Zarr-Python 3). Compressed 数组, 并行 I/O, S3/GCS 通过 fsspec, NumPy/Dask/Xarray compatible, large-scale scientific computing 流水线.Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I/O, S3/GCS via fsspec, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.#data-engineeringk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 数据工程39,677openspec-sync-specsSkillsMP@halo-dev同步 delta 规格说明变更 main 规格说明. 使用用户需求更新 main 规格说明变更 delta 规格说明, 无需 archiving 变更.Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.#data-engineeringhalo-dev/haloGit 克隆查看详情与安装步骤 → 数据工程39,613django-migrationsSkillsMP@PostHogDjango 迁移模式安全工作流程 PostHog. 使用创建, adjusting, 评审 Django/Postgres 迁移, 包括 non-blocking index/constraint 变更, 多-阶段结构变更, 数据 backfills, 迁移 conflicDjango migration patterns and safety workflow for PostHog. Use when creating, adjusting, or reviewing Django/Postgres migrations, including non-blocking index/constraint changes, multi-phase schema changes, data backfills, migration conflic#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613merging-prsSkillsMP@PostHogMerge PR `master` Trunk merge 队列 babysit until lands. Enqueue `/trunk merge` 评论, watch `trunk merge status` PR 状态 until MERGED 队列 kicks 输出, 报告 Trunk's owMerge a PR into `master` through the Trunk merge queue and babysit it until it lands. Enqueue with a `/trunk merge` comment, then watch `trunk merge status` and the PR state until it is MERGED or the queue kicks it out, reporting Trunk's ow#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613writing-dataclassesSkillsMP@PostHogHouse 规则 Python dataclasses PostHog: reach 一个 instead tuple `dict[str, Any]`, 装饰器使用 (`@frozen` `posthog. dataclasses`), 如何名称, construct, consume evolve, 如何 keep secretsHouse rules for Python dataclasses in PostHog: when to reach for one instead of a tuple or `dict[str, Any]`, which decorator to use (`@frozen` from `posthog.dataclasses`), how to name, construct, consume and evolve them, how to keep secrets#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613setting-up-warehouse-propertiesSkillsMP@PostHogPopulate person 分组房产数据仓库表格 materialized 视图, 仓库 columns become 房产 usable 功能 flags, cohorts, insights. 使用用户需求 "同步 PostgreSQL columns person propPopulate person or group properties from a data warehouse table or materialized view, so warehouse columns become properties usable in feature flags, cohorts, and insights. Use when the user wants to "sync my Postgres columns to person prop#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613adding-warehouse-person-propertiesSkillsMP@PostHog同步 columns synced 数据仓库表格 PostHog person 分组房产, 仓库数据 becomes usable anywhere person 分组房产 already 工作: 功能 flag targeting, cohorts, insight 筛选 breakdowns, suSync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data becomes usable anywhere person and group properties already work: feature flag targeting, cohorts, insight filters and breakdowns, su#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613modeling-dimension-tablesSkillsMP@PostHog构建可复用 dimension / 查找表格 star 结构 — country/region, timezone, currency, date, plan/product, 其他 descriptive attributes — PostHog 数据-仓库视图 (HogQL) 外部 dbt 项目. 使用Build reusable dimension / lookup tables for a star schema — country/region, timezone, currency, date, plan/product, and other descriptive attributes — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the #data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613modeling-warehouse-foundationsSkillsMP@PostHog共享 foundations 构建可复用数据模型 PostHog, two stacks: PostHog-原生数据-仓库视图 / materialized 视图 (HogQL, 通过视图-* MCP 工具), 外部 dbt 项目 (sources. yml + staging/marts +Shared foundations for building reusable data models in PostHog, on either of two stacks: PostHog-native data-warehouse views / materialized views (HogQL, via the view-* MCP tools), or an external dbt project (sources.yml + staging/marts + #data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613authoring-data-quality-checksSkillsMP@PostHog添加运行数据质量检查 (dbt-测试风格 assertions) 项目's 仓库表格 saved-查询视图: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, 自定义 HogQL. 使用要求Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Use when asked#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613turning-engineering-analytics-into-insightsSkillsMP@PostHog转换工程分析 (PR / CI) 数据 saved PostHog insights, 仪表盘, 订阅, explains 如何查询商品数据 directly SQL. 覆盖 discovering 按-团队 GitHub 仓库表格通过工程-analConverts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subscriptions, and explains how to query the product data directly with SQL. Covers discovering per-team GitHub warehouse tables via engineering-anal#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613diagnosing-failed-warehouse-syncsSkillsMP@PostHogDiagnose 数据仓库同步 failing 推荐正确 recovery 操作. 使用用户要求 " isn't Stripe/Postgres/Hubspot 同步处理?", " 表格 stuck hours", " 数据仓库 looks wronDiagnose why a data warehouse sync is failing and recommend the right recovery action. Use when the user asks "why isn't my Stripe/Postgres/Hubspot sync working?", "this table has been stuck for hours", "the data in the warehouse looks wron#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,613suggesting-data-importsSkillsMP@PostHog使用用户要求 revenue, 支付, 订阅, 账单, CRM deals, 支持 tickets, ad spend, 生产环境数据库表格, 其他数据 PostHog collect natively — 需求 join correlate PostHog 商品事件Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, ad spend, production database tables, or other data PostHog does not collect natively — or wants to join or correlate PostHog product events#data-engineeringposthog/posthogGit 克隆查看详情与安装步骤 → 数据工程39,583nature-literature-pipelineSkillsMP@Yuan1z0825完整自动化 literature discovery 流水线: 多-来源搜索 → six-dimension scoring → 精细读取 → formatted delivery → archival. Combines configurable 引擎每日定时任务-driven 应用层. 工作 Feishu, TelegrComplete automated literature discovery pipeline: multi-source search → six-dimension scoring → fine reading → formatted delivery → archival. Combines a configurable engine with daily cron-driven application layer. Works with Feishu, Telegr#data-engineeringyuan1z0825/nature-skillsGit 克隆查看详情与安装步骤 → 数据工程39,485airflow-dag-patternsSkillsMP@wshobson构建生产环境 Apache Airflow DAGs 最佳实践 operators, 传感器, testing, 部署. 使用创建数据流水线, orchestrating 工作流程, 排程批量作业.Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.#data-engineeringwshobson/agentsGit 克隆查看详情与安装步骤 → 数据工程39,485data-quality-frameworksSkillsMP@wshobson实现数据质量校验 Great Expectations, dbt 测试, 数据合同. 使用构建数据质量流水线, 实现校验规则, establishing 数据合同.Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.#data-engineeringwshobson/agentsGit 克隆查看详情与安装步骤 → 数据工程39,485dbt-transformation-patternsSkillsMP@wshobson主分支 dbt (数据构建 tool) 分析工程模型 organization, testing, 文档, incremental 策略. 使用构建数据 transformations, 创建数据模型, 实现分析工程 best praMaster dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best pra#data-engineeringwshobson/agentsGit 克隆查看详情与安装步骤 → 数据工程39,485spark-optimizationSkillsMP@wshobson优化 Apache Spark 作业 partitioning, 缓存, shuffle 优化, 记忆 tuning. 使用 improving Spark performance, 调试缓慢作业, scaling 数据处理流水线.Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.#data-engineeringwshobson/agentsGit 克隆查看详情与安装步骤 → 数据工程39,485pptx-deck-contextSkillsMP@wshobson使用准备叙事, sources, 设计上下文新建 editable PPTX 演示文稿.Use when preparing the narrative, sources, and design context for a new editable PPTX deck.#data-engineeringwshobson/agentsGit 克隆查看详情与安装步骤 → 数据工程39,049graphSkillsMP@Yeachan-HeoDeterministic orchestration 图谱运行时 - 声明式 DAG 流水线日志记录-基于崩溃 recoveryDeterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery#data-engineeringyeachan-heo/oh-my-claudecodeGit 克隆查看详情与安装步骤 → 数据工程38,754az-cost-optimizeSkillsMP@github分析 Azure 资源用于应用 (IaC 文件 and/or 资源目标 rg) 优化成本 - 创建 GitHub 工单识别优化.Analyze Azure resources used in the app (IaC files and/or resources in a target rg) and optimize costs - creating GitHub issues for identified optimizations.#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754bigquery-pipeline-auditSkillsMP@github审计 Python + BigQuery 流水线成本安全, 幂等性, 生产环境 readiness. Returns 结构化报告 exact 补丁 locations.Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754create-architectural-decision-recordSkillsMP@github创建架构决策记录 (ADR) 文档 AI-已优化决策文档.Create an Architectural Decision Record (ADR) document for AI-optimized decision documentation.#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754create-specificationSkillsMP@github创建新建 specification 文件解决方案, 已优化 Generative AI consumption.Create a new specification file for the solution, optimized for Generative AI consumption.#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754dataverse-python-advanced-patternsSkillsMP@github生成生产环境代码 Dataverse SDK 使用先进模式, 错误处理, 优化 techniques.Generate production code for Dataverse SDK using advanced patterns, error handling, and optimization techniques.#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754dataverse-python-production-codeSkillsMP@github生成生产环境-就绪 Python 代码使用 Dataverse SDK 错误处理, 优化, 最佳实践Generate production-ready Python code using Dataverse SDK with error handling, optimization, and best practices#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754diagnoseSkillsMP@githubPerform systematic 诊断扫描 AI 工作流程跨 5 质量 dimensions — 提示词质量, 上下文效率, tool 健康, 架构健身, 安全 — producing scored 报告 prioritized remediation 操作.Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report with prioritized remediation actions.#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754dotnet-timezoneSkillsMP@github. NET timezone handling 指引 C# 应用. 使用处理 TimeZoneInfo, DateTimeOffset, NodaTime, UTC 转化, daylight saving 时间, 排程跨 timezones, 跨平台 Windows/IANA timezone IDs,. NET u.NET timezone handling guidance for C# applications. Use when working with TimeZoneInfo, DateTimeOffset, NodaTime, UTC conversion, daylight saving time, scheduling across timezones, cross-platform Windows/IANA timezone IDs, or when a .NET u#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754efcore-d2-db-diagramSkillsMP@github生成 D2 数据库示意图实体框架核心模型. USE FOR: EF 核心数据库示意图, 实体框架核心 ERD, DbContext 示意图, C# 实体 relationship 示意图, PostgreSQL 结构 visualization, 生成. d2 文件 EF CorGenerate D2 database diagrams from Entity Framework Core models. USE FOR: EF Core database diagram, Entity Framework Core ERD, DbContext diagram, C# entity relationship diagram, PostgreSQL schema visualization, generate .d2 file from EF Cor#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754planning-oracle-to-postgres-migration-integration-testingSkillsMP@github创建集成 testing 计划. NET 数据访问产物在…期间 Oracle-to-PostgreSQL 数据库迁移. Analyzes 单个项目识别仓库, DAOs, 服务分层交互数据库, 产出Creates an integration testing plan for .NET data access artifacts during Oracle-to-PostgreSQL database migrations. Analyzes a single project to identify repositories, DAOs, and service layers that interact with the database, then produces #data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754powerbi-modelingSkillsMP@githubPower BI 语义 modeling 助手构建已优化数据模型. 使用处理 Power BI 语义模型, 创建 measures, 设计 star 结构, 配置 relationships, 实现 RLS, 优化模型 performancePower BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程38,754terraform-azurerm-set-diff-analyzerSkillsMP@github分析 Terraform 计划 JSON 输出 AzureRM 提供方 distinguish false-positive diffs (订单- 变更集合-type attributes) actual 资源变更. 使用评审 terraform 计划输出 Azure 资源例如Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like A#data-engineeringgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 数据工程35,034competition-container-runtimeSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程线上容器运行时分析, mounted secrets, sidecars, namespaces, 初始化容器, entrypoint drift, 路由-to-容器解决. 使用用户Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for live container runtime analysis, mounted secrets, sidecars, namespaces, init containers, entrypoint drift, and route-to-container resolution. Use when the user#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-custom-protocol-replaySkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程自定义 binary 文本协议 recovery, handshake reconstruction, framing, sequence 控制, checksums, stateful replay, accepted-会话 reproduction. UsInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for custom binary or text protocol recovery, handshake reconstruction, framing, sequence control, checksums, stateful replay, and accepted-session reproduction. Us#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-file-parser-chainSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程文件 uploads, 导入, previews, archive extraction, 格式化转化, 解析器 invocation, 反序列化 chains. 使用用户要求检查 uplInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for file uploads, imports, previews, archive extraction, format conversion, parser invocation, and deserialization chains. Use when the user asks to inspect an upl#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-firmware-layoutSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程固件图片, partition 表格, boot chains, 更新软件包, 提取 filesystems, 嵌入式 configs, 设备-facing trust 边界. 使用用户Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-forensic-timelineSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 DFIR chronology, cross-产物 correlation, 持久化 chains, incident 时间线 reconstruction. 使用用户要求构建 forensic 时间线, corInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for DFIR chronology, cross-artifact correlation, persistence chains, and incident timeline reconstruction. Use when the user asks to build a forensic timeline, cor#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-kerberos-delegationSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 Kerberos delegation, SPN trust edges, S4U abuse, RBCD, constrained unconstrained delegation, 服务-ticket acceptance. 使用用户要求 conInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kerberos delegation, SPN trust edges, S4U abuse, RBCD, constrained or unconstrained delegation, and service-ticket acceptance. Use when the user asks about con#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-pcap-protocolSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 packet 采集分析, 会话 reconstruction, 应用-协议 decoding, 流 reassembly, beacon timing, packet-to-流程 correlation. 使用 tInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for packet capture analysis, session reconstruction, application-protocol decoding, stream reassembly, beacon timing, and packet-to-process correlation. Use when t#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-queue-worker-driftSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程队列, 异步工作进程, 定时任务作业, delayed 任务, 重试行为, 工作进程- 配置 drift, 载荷-to-端-effect chains. 使用用户要求链路追踪Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for queues, async workers, cron jobs, delayed tasks, retry behavior, worker-only config drift, and payload-to-side-effect chains. Use when the user asks to trace a#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-race-condition-state-driftSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 race Windows, ordering 缺陷, 幂等性失败, 锁 gaps, 并发工作进程 drift, 状态 inconsistencies 产出 decisive effects. 使用 usInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for race windows, ordering bugs, idempotency failures, lock gaps, concurrent worker drift, and state inconsistencies that produce decisive effects. Use when the us#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-stego-mediaSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程图片, 音频, 视频, 文档, 容器 steganography. 使用用户要求检查元数据, 内测版 palette 通道, LSBs, 缩略图, appended tInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for image, audio, video, document, and container steganography. Use when the user asks to inspect metadata, alpha or palette channels, LSBs, thumbnails, appended t#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-supply-chainSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 CI/CD, 注册中心, 依赖 drift, 产物 provenance, 图片构建, 发布版本流水线, 运行时消费方 challenges. 使用用户要求链路追踪 dependeInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for CI/CD, registry, dependency drift, artifact provenance, image build, release pipeline, and runtime consumer challenges. Use when the user asks to trace depende#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034competition-zip-archiveSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 ZIP PKZIP archive challenges, 遗留 ZipCrypto identification, known-plaintext recovery bkcrack, 关键-基于 decryption, reproducible extraction. UsInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for ZIP and PKZIP archive challenges, legacy ZipCrypto identification, known-plaintext recovery with bkcrack, key-based decryption, and reproducible extraction. Us#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程35,034threat-huntingSkillsMP@zhaoxuya520使用 blue-团队 threat hunting, 检测工程 Sigma/YARA, SIEM 查询设计, incident 检测校验.Use for blue-team threat hunting, detection engineering with Sigma/YARA, SIEM query design, and incident detection validation.#data-engineeringzhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 数据工程34,264infra-scalingSkillsMP@langfuseTune 评审 Langfuse autoscaling 网页, 网页-iso, 网页-ingestion. 使用 Terraform scale 设置, RPM 目标, scaling bounds, 任务 counts, cost/performance tradeoffs, Datadog 证据基础设施仓库.Tune and review Langfuse autoscaling for web, web-iso, and web-ingestion. Use for Terraform scale settings, RPM targets, scaling bounds, task counts, cost/performance tradeoffs, or Datadog evidence in the infrastructure repo.#data-engineeringlangfuse/langfuseGit 克隆查看详情与安装步骤 → 数据工程33,024ccxtSkillsMP@HKUDSCCXT unified 加密货币 exchange 函数库 (100+ exchanges). Free 公开市场数据. Fallback OKX unavailable.CCXT unified crypto exchange library (100+ exchanges). Free public market data. Fallback when OKX is unavailable.#data-engineeringhkuds/vibe-tradingGit 克隆查看详情与安装步骤 → 数据工程32,452system-table-changeSkillsMP@cockroachdb使用新增, removing, 修改 columns/indexes 系统表格. 提供检查清单覆盖结构 definitions, 迁移, 版本 gates, golden 文件, 测试 hashes.Use when adding, removing, or modifying columns/indexes on system tables. Provides a checklist covering schema definitions, migrations, version gates, golden files, and test hashes.#data-engineeringcockroachdb/cockroachGit 克隆查看详情与安装步骤 → 数据工程32,390building-ioc-defanging-and-sharing-pipelineSkillsMP@mukul975构建自动化流水线 ingests raw IOCs (URLs, IPs, 域名, 邮件), normalizes deduplicates, 产出 defanged renderings 安全 human 读取 alongside 规范 STIX 2.1 打包合集分布式通过 TAXII 服务器, MBuild an automated pipeline that ingests raw IOCs (URLs, IPs, domains, emails), normalizes and deduplicates them, then produces defanged renderings for safe human reading alongside canonical STIX 2.1 bundles distributed via TAXII servers, M#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程32,390building-threat-hunt-hypothesis-frameworkSkillsMP@mukul975构建 systematic threat-hunt 工作流程 turns threat intelligence ATT&CK gap 分析 testable hypotheses, 执行校验通过 EDR/SIEM 查询 (CrowdStrike, Defender, Splunk, Elastic, Sysmon, Velociraptor, SiBuild a systematic threat-hunt workflow that turns threat intelligence and ATT&CK gap analysis into testable hypotheses, then executes and validates them via EDR/SIEM queries (CrowdStrike, Defender, Splunk, Elastic, Sysmon, Velociraptor, Si#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程32,390implementing-cloud-dlp-for-data-protectionSkillsMP@mukul975实现云端 DLP 使用 Amazon Macie, Google 云端 DLP API, Microsoft Purview, Azure 信息防护, Nightfall AI 发现, classify, 标签, de-识别, 保护 sensitive 数据 (PII, PHI, 财务数据) 跨云端 stImplement cloud DLP using Amazon Macie, Google Cloud DLP API, Microsoft Purview, Azure Information Protection, and Nightfall AI to discover, classify, label, de-identify, and protect sensitive data (PII, PHI, financial data) across cloud st#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程32,390implementing-endpoint-dlp-controlsSkillsMP@mukul975实现接口数据 Loss Prevention (DLP) 控件检测防止 sensitive 数据 exfiltration 邮件, USB, 云端存储, printing. 使用 deploying DLP 智能体, 创建内容 inspection 政策, preventing unImplements endpoint Data Loss Prevention (DLP) controls to detect and prevent sensitive data exfiltration through email, USB, cloud storage, and printing. Use when deploying DLP agents, creating content inspection policies, or preventing un#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程32,390performing-log-source-onboarding-in-siemSkillsMP@mukul975Perform 结构化日志来源新手引导 SIEM 平台 (Splunk, Elastic, Sentinel, QRadar, similar) prioritizing sources tiered value 框架, 配置 collectors, 构建 parsers, normalizing fields 通用 schPerform structured log source onboarding into SIEM platforms (Splunk, Elastic, Sentinel, QRadar, or similar) by prioritizing sources with a tiered value framework, configuring collectors, building parsers, normalizing fields to a common sch#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程32,390performing-threat-modeling-with-owasp-threat-dragonSkillsMP@mukul975使用 OWASP Threat Dragon (网页桌面) 构建数据流程示意图, 识别 threats STRIDE, LINDDUN, CIA, DIE, PLOT4ai methodologies 通过自动-generation 规则引擎, 产出 PDF 威胁建模报告. 使用在…期间安全 deUses OWASP Threat Dragon (web or desktop) to build data flow diagrams, identify threats with STRIDE, LINDDUN, CIA, DIE, or PLOT4ai methodologies via its auto-generation rule engine, and produce PDF threat model reports. Use during secure de#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程32,390securing-historian-server-in-ot-environmentSkillsMP@mukul975审计 hardens 流程 historian 服务器 (OSIsoft PI, Honeywell PHD, GE Proficy, AVEVA Historian) OT environments: Purdue-级别网络 placement, 接口定义访问控制, 安全 DMZ replication 通过数据 diodes PI-to-PI connectorAudits and hardens process historian servers (OSIsoft PI, Honeywell PHD, GE Proficy, AVEVA Historian) in OT environments: Purdue-level network placement, interface access control, secure DMZ replication via data diodes or PI-to-PI connector#data-engineeringmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 数据工程30,563llamaindexSkillsMP@davila7数据框架构建 LLM 应用 RAG. Specializes 文档 ingestion (300+ connectors), indexing, querying. 功能 vector 索引, 查询 engines, 智能体, 多-弹窗支持. 使用文档 Q&, 聊天机器人, knoData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, kno#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563data-engineerSkillsMP@davila7构建可扩展数据流水线, 现代数据仓库, 实时 streaming architectures. 实现 Apache Spark, dbt, Airflow, 云端-原生数据平台.Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563ray-dataSkillsMP@davila7可扩展数据处理 ML workloads. Streaming 执行跨 CPU/GPU, 支持 Parquet/CSV/JSON/图片. 集成 Ray Train, PyTorch, TensorFlow. Scales 单个 machine 100s 节点. 使用批量推理计算, 数据 prepScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data prep#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563deepspeedSkillsMP@davila7专家指引分布式训练 DeepSpeed - ZeRO 优化阶段, 流水线 parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attentionExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563llm-opsSkillsMP@davila7LLM 运维 -- RAG, 向量嵌入, vector 数据库, 精细-tuning, 提示词工程 avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563stable-diffusion-image-generationSkillsMP@davila7状态-of-the-art 文本-to-图像生成稳定 Diffusion 模型通过 HuggingFace Diffusers. 使用生成图片文本提示词, performing 图片-to-图片翻译, inpainting, 构建自定义 diffusion 流水线.State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563pineconeSkillsMP@davila7托管向量数据库生产环境 AI 应用. Fully 托管, 自动-scaling, 混合搜索 (dense + sparse), 元数据筛选, namespaces. Low 延迟 (<100ms p95). 使用生产环境 RAG, 推荐系统, semanManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or seman#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563database-architectSkillsMP@davila7专家数据库 architect specializing 数据层 设计 scratch, technology 选择, 结构 modeling, 可扩展数据库 architectures.Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563database-migrationSkillsMP@davila7主分支数据库结构数据迁移跨 ORMs (Sequelize, TypeORM, Prisma), 包括回滚策略 zero-停机部署.Master database schema and data migrations across ORMs (Sequelize, TypeORM, Prisma), including rollback strategies and zero-downtime deployments.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563sql-proSkillsMP@davila7主分支现代 SQL 云端-原生数据库, OLTP/OLAP 优化, 先进查询 techniques. 专家 performance tuning, 数据 modeling, 混合 analytical 系统.Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 数据工程30,563clickhouse-ioSkillsMP@davila7ClickHouse 数据库模式, 查询优化, 分析, 数据工程最佳实践 high-performance analytical workloads.ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.#data-engineeringdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 →