tavily-search
Web search and content extraction via the Tavily API. Use when you need real-time web results, citations, or raw article content without a browser. Requires…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-15 00:13
Coding & development
41,172 results
partner-dev-guide
Use when asked to write a one-off developer guide, integration guide, or implementation walkthrough for a named partner from a rough funds flow, numbered step…
v0-project-converter
Process specification for converting a Next.js project generated by V0 into this project's page components; use it when executing V0 project conversion, dependency cleanup, path alias replacement, style migration and acceptance.
avalonia-mvvm
Use when implementing the MVVM pattern in Avalonia, including ViewModels, INotifyPropertyChanged, ICommand, ReactiveUI, CommunityToolkit.Mvvm, or…
best-practices-researcher
A meta-skill for researching current best practices and making technology decisions. Use when the user asks about best practices, coding standards, patterns,…
cors-api
Architectural pattern for direct browser-to-Looker API calls via CORS using OAuth2 with PKCE for secure client-side authentication.
cangjie
Code generation, engineering design, issue fixing, and large repository analysis skills for the Cangjie programming language. Whenever the user mentions "仓颉 / Cangjie / .cj / cjpm / cjc / cjfmt / cjdb / LSP", or wants to generate/fix Cangjie functions, types, modules, workspaces, multi-module package design, concurrency, networking, macros, FFI…
tanstack-ai-code-mode
LLM-generated TypeScript execution in sandboxed environments: createCodeModeTool() with isolate drivers (createNodeIsolateDriver, createQuickJSIsolateDriver,…
tanstack-ai-core-chat-experience
End-to-end chat implementation: server endpoint with chat() and toServerSentEventsResponse(), client-side useChat hook with fetchServerSentEvents(), message…
tanstack-ai-core-structured-outputs
Type-safe JSON schema responses from LLMs using outputSchema on chat() and useChat(). Supports Zod, ArkType, and Valibot schemas. The adapter handles…
tanstack-ai-core-tool-calling
Isomorphic tool system: toolDefinition() with Zod schemas, .server() and .client() implementations, passing tools to both chat() on server and…
tanstack-db-core-custom-adapter
Building custom collection adapters for new backends. SyncConfig interface: sync function receiving begin, write, commit, markReady, truncate, metadata…
tanstack-db-core-live-queries
Query builder fluent API: from, where, join, leftJoin, rightJoin, innerJoin, fullJoin, select, fn.select, groupBy, having, orderBy, limit, offset, distinct,…
tanstack-highlight-extend-language-support
Extend @tanstack/highlight with defineLanguage, LanguageDefinition, TokenRange, HighlightTokenClass, and TokenizerContext. Load when adding a custom or shipped…
tanstack-markdown-custom-extensions
Implement MarkdownExtension block parsers, inline and document transforms, HTML hooks, and portable ComponentNode output. Load when adding deterministic custom…
tanstack-markdown-production-pipelines
Audit and ship a production Markdown pipeline with explicit trust boundaries, external syntax highlighting, parse-ahead caching, compatibility checks,…
tanstack-react-db
React bindings for TanStack DB. useLiveQuery hook with dependency arrays (8 overloads: query function, config object, pre-created collection, disabled state…
pr-summary
Add a concise Before/After/Solution block at the top of every new or refreshed pull request description. Use when opening a PR, writing or updating a PR…
ai-coding-discipline
Mandatory coding discipline rules that prevent common AI coding anti-patterns. MUST be loaded for ALL code writing, editing, reviewing, bug fixing, and testing…
llamacpp-tuner
Analyze and tune a running llama.cpp server for local coding agents: propose config (ctx, prompt cache, MTP), benchmark before/after, report deltas. Use to…
code-review-specialist
Comprehensive code review with security, performance, and quality analysis. Use when users ask to review code, analyze code quality, evaluate pull requests, or…
doc-generator
Generate comprehensive, accurate API documentation from source code. Use when creating or updating API documentation, generating OpenAPI specs, or when users…
lynx-tasm-codec
Via `agent-lynx tasm` convert (encode, decode) between template JSON and tasm binary. Trigger scenarios: - User explicitly mentions `agent-lynx tasm`、`lynx-tasm`、`@lynx-js/tasm`、`encode/decode tasm`、`json 转 tasm`, `tasm to...
review-this
Produces a structured code review or documentation review with category ratings, an overall score, a checklist, and actionable improvement suggestions. Use…