Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Local CLI guide for the ListenAI (聆思) platform, covering installation and login, basic AI capabilities, platform app and knowledge base management, end-cloud request/trace debugging, real-device app binding, and initialization, build, and test pipeline deployment for custom Agent projects. Use when users mention ling, 小聆, 聆思, LSPlatform, product_id, listenai.toml, voice, wake word, wake response, prompt copy, end-cloud debugging, SID lookup, or need to operate the ListenAI platform in a terminal.
Develops reactive UI components using KnockoutJS for Magento 2. Use when working with UI components, implementing MVVM patterns, or building interactive frontend features. Masters observable patterns, data binding, and custom bindings.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Build project documentation sites with MkDocs static site generator. Use when the user mentions mkdocs, documentation site, docs site, project documentation, or wants to create, configure, build, or deploy documentation using Markdown. Covers installation, configuration, theming, plugins, and deployment
Apply and diagnose Rust style, rustfmt, Clippy, compiler diagnostics, Edition migrations, lint policy, idiomatic control flow, error handling, allocation behavior, production Rust conventions, and the Rust API Guidelines ↔ Clippy lint mapping. Use when users ask to format or lint Rust, fix warning or error codes, migrate editions, review unwrap or clone usage, improve idioms, map a C-* API guideline rule to the enforcing Clippy lint, or establish CI quality gates. Route API shape decisions (naming conventions, type/trait design, module layout, full C-* guideline review) to the rust-api-design skill.
Write documentation for a code library through an iterative top-down workflow with user review at each layer. Use whenever the user asks to document a codebase, library, or package — including phrases like "write docs for…", "document this library", "write technical docs", or any request to produce sustained documentation rather than inline code comments. The skill organizes output into Getting Started, Diving Deeper, and Reference sections, builds them progressively (structure → headers → topic sentences → paragraphs), and pauses for user review between each pass. Includes embedded prose-style guidance (Strunk & White) applied during every prose pass. Also use to update or refresh existing docs after code changes — phrases like "update the docs", "the docs are stale", or "sync the docs with the code" — which runs the update workflow in Phase 5.
Use this skill when the user asks about "Server Components", "Client Components", the "'use client'" directive, "when to use server vs client", "RSC patterns", "component composition", "data fetching in components", or needs guidance on React Server Components architecture in Next.js.
Screenshot-to-HTML prototype generator with iterative refinement and learning memory. Use this skill whenever the user provides a screenshot, mockup, wireframe, or image of any UI and wants it reproduced as a working HTML prototype — or when they want to modify an existing prototype they previously generated. Also triggers on: "照这个做原型", "参考这个图", "把这个页面画出来", "this UI needs to be prototyped", "replicate this design", "convert this mockup to HTML", "帮我出个原型", "根据截图输出 HTML", or any image attachment combined with requests like "输出 HTML", "做成页面", "帮我实现". Even if the user just sends a screenshot with a brief instruction like "加一个字段" or "这个也一样", this skill applies — it means they want you to modify or replicate the UI shown. When in doubt, if there's a UI screenshot in the conversation, use this skill.
企业微信 飞书 钉钉 淘宝 小红书 抖音电商 微信小程序 微信小店 拼多多 有赞 微信支付 支付宝 京东 SHEIN 得物 火山引擎 阿里云百炼 泛微 北森 API文档搜索。 WeCom Feishu Lark DingTalk Taobao Xiaohongshu Douyin WeChat Pinduoduo Youzan Alipay JD SHEIN Dewu Volcengine Bailian Weaver eTeams Beisen iTalent API docs search. 67,000+ API docs across 20 Chinese open platforms with full-text search. 搜索20个开放平台的API开发文档，支持中文全文检索。 wecom feishu lark dingtalk taobao xiaohongshu xhs douyin jinritemai wechat miniprogram wechat-shop wechat-pay pinduoduo youzanyun alipay jd shein dewu poizon volcengine ecs bailian dashscope qwen doubao weaver eteams e-teams ecology beisen italent openapi webhook access_token 抖店 小程序 小店 pdd 京东开放平台 得物开放平台 火山引擎云服务器 火山引擎文档中心 电商开放平台 接口文档 开放平台 火山方舟 对象存储 容器服务 豆包 豆包大模型 百炼 千问 通义千问 通义 大模型 DashScope 泛微 泛微OA ecology e-cology e-teams eteams 北森 北森云 iTalent 招聘 绩效 薪酬 人事
Use when adding camera controls to a Three.js scene: orbit, pan, zoom, fly, first-person, or object manipulation. Prevents the common mistake of forgetting controls.update() in the render loop, not calling dispose(), or mixing controls. Covers OrbitControls, MapControls, FlyControls, PointerLockControls, TransformControls. Keywords: OrbitControls, controls, camera controls, orbit, pan, zoom, MapControls, FlyControls, PointerLockControls, TransformControls, rotate view, move camera, mouse controls, drag to rotate.
Provides battle-tested patterns, best practices, and code examples for building Phaser 3 games. Use when writing game code, implementing game mechanics, setting up scenes, handling physics, animations, input, or any Phaser-related development. Covers architecture, performance, algorithms, and common pitfalls.
Use when training, fine-tuning, or validating Ultralytics YOLO models in Platform, cloud GPUs, or local code — model.train(), yolo train/val, remote metric streaming, epochs, batch, imgsz, devices, augmentation, multi-GPU, resumes, results, and fixing OOM, NaN loss, low mAP, or overfitting. For hyperparameter search and systematic improvement loops, see yolo-tuning.
Agentic ObjectARX project scaffolding for AutoCAD 2027 / Visual Studio 2026. Replaces the broken .vsz VsWizardEngine wizard with a PowerShell script that generates identical C++ project files. Works for new ARX/DBX/CRX projects and add-on class wizards (Jig, Reactors, Custom Object, MFC, .NET Wrapper, COM Wrapper, Dynamic Property).
Use when needing to fetch Android source code — AOSP platform internals (@hide APIs, framework classes, system services) or AndroidX/Jetpack library source and samples. Also use when public docs are insufficient to complete a task and implementation details must be read directly from source.
Use when writing, fixing, or refactoring Android/KMP code in Kotlin — a test-first (RED-GREEN-REFACTOR) foundation plus the Android/KMP test traps: Compose-test dispatching (StandardTestDispatcher default, the two-schedulers trap), semantics-first selectors, choosing the smallest test shape, test-clock vs wall-clock, animation/screenshot determinism, and a `commonTest` name that fails the iOS compile while `jvmTest` stays green.
Call 400+ AI models (GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM, MiniMax, plus image, video, embedding and rerank models) through APIYI's single OpenAI-compatible gateway at api.apiyi.com. Use this when the user mentions APIYI, API易, api.apiyi.com or an APIYI_API_KEY; wants one API key across multiple model vendors; is repointing an OpenAI, Anthropic or Google SDK base_url at a relay; or asks about APIYI base URLs, model IDs, token groups (分组), pricing, balance (余额), call logs, or gateway error codes.
Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables.
Avalonia UI 12 for cross-platform .NET desktop apps: compiled bindings (x:DataType, on by default in 12), StyledProperty/DirectProperty, custom and templated controls, ControlThemes, DataTemplates/ViewLocator, Generic Host + DI, StorageProvider/Clipboard, Native AOT/trimming, and packaging. Load when the user mentions "Avalonia", "AXAML", "x:DataType", "compiled binding", "StyledProperty", "TemplatedControl", "ViewLocator", or "cross-platform desktop"
Deploy serverless applications with AWS SAM and AWS CDK. Triggers on phrases like: use SAM, SAM template, SAM init, SAM deploy, CDK serverless, CDK Lambda construct, NodejsFunction, PythonFunction, SAM and CDK together, serverless CI/CD pipeline. For general app deployment with service selection, use the deploy-on-aws plugin instead.
Bulletproof React architecture patterns for scalable, maintainable applications. Covers feature-based project structure, component patterns, state management boundaries, API layer design, error handling, security, and testing strategies. Use when structuring a React project, designing application architecture, organizing features, or when the user asks about React project structure or scalable patterns.
Console apps and CLI tools on .NET 10: System.CommandLine 2.x (RootCommand, Option<T>, SetAction, InvokeAsync), Generic Host + DI in console apps, exit codes, stdout/stderr discipline, Ctrl+C cancellation, interactive vs piped use, dotnet tool packaging, and `dotnet run app.cs` file-based apps. Load when the user mentions "console app", "CLI", "command line", "System.CommandLine", "dotnet tool", "exit code", "stdin", "args parsing", or "file-based app"
Guidelines for introducing and using nullable reference types (NRT) and System.Diagnostics.CodeAnalysis nullable attributes in C# / .NET codebases. Covers the nullability model, flow analysis, the null-forgiving operator, API design rules, the full attribute catalog (AllowNull, DisallowNull, MaybeNull, NotNull, NotNullWhen, MaybeNullWhen, NotNullIfNotNull, MemberNotNull, MemberNotNullWhen, DoesNotReturn, DoesNotReturnIf), the C# 14 field keyword, incremental migration of legacy codebases, and a code-generation checklist.
Design system architecture: W3C design tokens, Style Dictionary pipelines, component library structure, theming, multi-brand token tiers, governance, versioning, and maturity models. Use when starting or scaling a design system, generating tokens, or setting up design-to-code distribution.
Use this skill when the user asks about domain modeling, primitive obsession, parse-don't-validate, semantic types, value objects, or making invalid states unrepresentable. Triggers on: “review for domain issues,” “primitive obsession,” “design domain types,” “value object,” “newtype wrapper,” “semantic type,” “make invalid states unrepresentable,” “bool-as-state,” requests to replace raw strings/ints with proper types, requests to fix swappable parameters, or any code review focusing on type safety and domain integrity. Also activates during TDD domain review phases. Not for general code review (style, formatting), debugging, database schema design, or design patterns unrelated to domain type modeling.
Fix pseudo module and implicit global issues that UI5 linter reports but cannot auto-fix. Use this skill when linter outputs: - `no-pseudo-modules` with messages about deprecated enum or DataType pseudo module access - `no-implicit-globals` with messages about module not exported by library or OData globals Trigger on: direct enum imports (sap/ui/core/BarColor), direct DataType imports (sap/ui/core/CSSSize), library.EnumName access, odata.compare/fillUriTemplate/uriEncode in bindings. Provides guidance on proper module imports for enums, DataTypes, and OData expression addons.
Implements the fixes a PR review asked for — maps each thread to the code it touches, edits that code, and drafts a reply per thread for approval before anything is posted. Starts from feedback that is already understood; producing the read-only digest is `pr-comments`.
Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners. Use this skill when the user wants to explain a project to beginners, create a tutorial from code, write documentation that teaches (not just documents), make a concept accessible, or says "make this teachable", "explain like im a beginner", "nano project version", "teaching version", "explain from scratch", "blog post about this". Based on Karpathy 243-line GPT and Eureka Labs posts.
Develops CSS and LESS for Magento 2 with responsive design and performance optimization. Use when styling themes, working with LESS, implementing responsive design, or optimizing CSS performance. Masters modern CSS techniques, LESS preprocessing, and cross-browser compatibility
Native AOT, trimming, and single-file publishing for .NET 10: PublishAot, IsAotCompatible analyzers, source-generated JSON/regex/logging/config binding, fixing IL2xxx/IL3xxx trim and AOT warnings, per-RID publishing, and when NOT to use AOT. Load when the user mentions "Native AOT", "PublishAot", "trimming", "PublishTrimmed", "single-file", "IL2026", "IL3050", "trim warning", "startup time", "self-contained", or "JsonSerializerContext"
(NS) Produce a codebase-grounded implementation brief for one GitLab issue or pasted scope. Blocking questions stay in chat (recommended answer, reply by number) and never go to GitLab. Use for enrich/expand requirements, grill-me, implementation brief, preview-then-post, ISSUE_URL before coding. Modes: Issue, Chat. Do NOT replace `/ns-spec-driven` Specify or version Clarify. Do NOT: PM intake, PRD, issue execution (`ns-execution-gitlab-issue`), start_execution_planning, code review (`ns-reviewer`).
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.