[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-related-ko-johnnyvizz-claude-kit":3},{"items":4,"total":103,"page":104,"pageSize":105},[5,25,47,67,86],{"slug":6,"name":7,"title":7,"skillCategorySlug":8,"summary":9,"description":10,"skillCategoryName":11,"sourceUrl":12,"downloadUrl":13,"cliCommand":14,"authorName":-1,"version":-1,"license":15,"stars":16,"trendScore":17,"qualityScore":18,"recommendedTools":19,"recommendedToolNames":19,"supportedClients":20,"clients":21,"tags":22,"installHint":14,"useCases":23,"updatedAt":24},"apache-airflow","apache\u002Fairflow","deployment-devops","Apache Airflow - A platform to programmatically author, schedule, and monitor workflows","Apache Airflow (or simply Airflow) is a platform to programmatically author, schedule, and monitor workflows.\n\nWhen workflows are defined as code, they become more maintainable, versionable, testable, and collaborative.\n\nUse Airflow to author workflows (Dags) that orchestrate tasks. The Airflow scheduler executes your tasks on an array of workers while following the specified dependencies. Rich command line utilities make performing complex surgeries on Dags a snap. The rich user interface makes it easy to visualize pipelines running in production, monitor progress, and troubleshoot issues when needed.\n\nAirflow works best with workflows that are mostly static and slowly changing. When the Dag structure is similar from one run to the next, it clarifies the unit of work and continuity. Other similar projects include Luigi, Oozie and Azkaban.","Deployment & DevOps","https:\u002F\u002Fgithub.com\u002Fapache\u002Fairflow","https:\u002F\u002Fgithub.com\u002Fapache\u002Fairflow\u002Farchive\u002FHEAD.zip","npx skillfish add apache\u002Fairflow","Apache-2.0",47182,100,75,[],[],[],[8,15],[],"2026-09-06T01:45:53.915499",{"slug":26,"name":27,"title":27,"skillCategorySlug":8,"summary":28,"description":29,"skillCategoryName":11,"sourceUrl":30,"downloadUrl":31,"cliCommand":32,"authorName":-1,"version":-1,"license":15,"stars":33,"trendScore":34,"qualityScore":35,"recommendedTools":36,"recommendedToolNames":36,"supportedClients":37,"clients":39,"tags":44,"installHint":32,"useCases":45,"updatedAt":46},"ariga-atlas","ariga\u002Fatlas","Declarative schema migrations with schema-as-code workflows","Atlas is a language-agnostic tool for managing and migrating database schemas using modern DevOps principles. It offers two workflows:\n\n- : Similar to Terraform, Atlas compares the current state of the database to the desired state, as defined in an [HCL], [SQL], or [ORM] schema. Based on this comparison, it generates and executes a migration plan to transition the database to its desired state.\n\n- : Unlike other tools, Atlas automatically plans schema migrations for you. Users can describe their desired database schema in [HCL], [SQL], or their chosen [ORM], and by utilizing Atlas, they can plan, lint, and apply the necessary migrations to the database.\n\nSee installation docs for all platforms.\n\n- : The atlas schema command offers various options for inspecting, diffing, comparing, planning and applying migrations using standard Terraform-like workflows. - : The atlas migrate command provides a state-of-the-art experience for planning, linting, and applying migrations.","https:\u002F\u002Fgithub.com\u002Fariga\u002Fatlas","https:\u002F\u002Fgithub.com\u002Fariga\u002Fatlas\u002Farchive\u002FHEAD.zip","npx skillfish add ariga\u002Fatlas",8774,87,80,[],[38],"cursor",[40],{"slug":38,"name":41,"summary":42,"count":43},"Cursor","개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.",0,[8,15],[],"2026-09-02T02:38:34.186002",{"slug":48,"name":49,"title":49,"skillCategorySlug":8,"summary":50,"description":51,"skillCategoryName":11,"sourceUrl":52,"downloadUrl":53,"cliCommand":54,"authorName":-1,"version":-1,"license":55,"stars":56,"trendScore":34,"qualityScore":57,"recommendedTools":58,"recommendedToolNames":58,"supportedClients":59,"clients":61,"tags":65,"installHint":54,"useCases":66,"updatedAt":46},"ai-dynamo-dynamo","ai-dynamo\u002Fdynamo","A Datacenter Scale Distributed Inference Serving Framework","Dynamo is the orchestration layer above inference engines — it doesn't replace SGLang, TensorRT-LLM, or vLLM, it turns them into a coordinated multi-node inference system. Disaggregated serving, intelligent routing, multi-tier KV caching, and automatic scaling work together to maximize throughput and minimize latency for LLM, reasoning, multimodal, and video generation workloads.\n\nBuilt in Rust for performance, Python for extensibility.\n\nEvents are updated automatically. Subscribe to our public calendar.\n\n- You're serving LLMs across and need to coordinate them - You want to avoid redundant prefill computation - You need to (disaggregated serving) - You want that meets latency SLAs at minimum total cost of ownership (TCO) - You need when spinning up new replicas\n\nIf you're running a single model on a single GPU, your inference engine alone is probably sufficient.\n\n— LoRA, request migration, speculative decoding, and feature interactions.","https:\u002F\u002Fgithub.com\u002Fai-dynamo\u002Fdynamo","https:\u002F\u002Fgithub.com\u002Fai-dynamo\u002Fdynamo\u002Farchive\u002FHEAD.zip","npx skillfish add ai-dynamo\u002Fdynamo","NOASSERTION",8299,68,[],[60],"vscode",[62],{"slug":60,"name":63,"summary":64,"count":43},"VS Code","MCP 서버로 코딩과 로컬 자동화를 지원하는 편집기 생태계.",[8,55],[],{"slug":68,"name":69,"title":69,"skillCategorySlug":8,"summary":70,"description":71,"skillCategoryName":11,"sourceUrl":72,"downloadUrl":73,"cliCommand":74,"authorName":-1,"version":-1,"license":75,"stars":76,"trendScore":77,"qualityScore":78,"recommendedTools":79,"recommendedToolNames":79,"supportedClients":80,"clients":81,"tags":83,"installHint":74,"useCases":84,"updatedAt":85},"xixu-me-xget","xixu-me\u002Fxget","Ultra-high-performance, secure, all-in-one acceleration engine for developer resources","An ultra-high-performance, secure, all-in-one acceleration engine for developer resources. It provides unified, efficient acceleration for code hosting, model and dataset hubs, package registries, container registries, AI inference providers, and more, while handling caching, retries, security headers, and protocol-specific compatibility behavior for you.\n\nXget was invited onto GitCode and recognized as a G-Star graduation project. As \"a widely used public project\", it receives support from OpenAI's Codex for Open Source and has also been spontaneously recommended by several tech creators, including Ruan Yifeng, GitHubDaily, FishC, and Xuanli 199. Thanks to every individual, team, and community that supports, shares, recommends, or actively uses Xget.\n\nThe badges below point to the relevant usage or deployment sections in this README.","https:\u002F\u002Fgithub.com\u002Fxixu-me\u002Fxget","https:\u002F\u002Fgithub.com\u002Fxixu-me\u002Fxget\u002Farchive\u002FHEAD.zip","npx skillfish add xixu-me\u002Fxget","AGPL-3.0",8192,81,86,[],[60],[82],{"slug":60,"name":63,"summary":64,"count":43},[8,75],[],"2026-10-12T02:49:30.059399",{"slug":87,"name":88,"title":88,"skillCategorySlug":8,"summary":89,"description":90,"skillCategoryName":11,"sourceUrl":91,"downloadUrl":92,"cliCommand":93,"authorName":-1,"version":-1,"license":94,"stars":95,"trendScore":96,"qualityScore":97,"recommendedTools":98,"recommendedToolNames":98,"supportedClients":99,"clients":100,"tags":101,"installHint":93,"useCases":102,"updatedAt":46},"deusyu-harness-engineering","deusyu\u002Fharness-engineering","Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案","一个从概念理解到独立实践的 Harness Engineering 深度学习档案\n\n封面取自仓库自产的 项目介绍 PPT + 海报 ——open-kimi-ppt skill 生成，PPTD 源同仓可编辑\n\n这是一个不断生长的学习项目。（驭缰工程）是 OpenAI 在 2026 年 2 月提出的工程范式：工程师不再写代码，而是设计环境、明确意图、构建反馈回路，让 AI 智能体可靠地完成工作。\n\n本仓库记录了从阅读原文、拆解概念、形成思考、动手实践到输出作品的完整学习过程。希望对同样关注 AI 工程化的朋友有所帮助。\n\n来源：OpenAI — Harness Engineering: Harnessing Codex in an Agent-First World\n\nSlack 讨论、Google Docs、脑子里的知识 = 对智能体不可见。一切决策、规范、计划都必须以版本化工件提交到仓库。\n\n→ 详见 concepts\u002F01-repo-as-source-of-truth.md\n\n~100 行的入口文件，指向更深层的文档。渐进式披露：智能体从小入口点开始，被指导下一步该看什么。巨型指令文件的三个死因：挤占上下文、无法维护、无法机械验证。","https:\u002F\u002Fgithub.com\u002Fdeusyu\u002Fharness-engineering","https:\u002F\u002Fgithub.com\u002Fdeusyu\u002Fharness-engineering\u002Farchive\u002FHEAD.zip","npx skillfish add deusyu\u002Fharness-engineering","MIT",6119,78,66,[],[],[],[8,94],[],139,1,5]