向量嵌入
向量检索与嵌入工作流
ai-sdk
ma1orek
'Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".'
prd-draft
graemerycyk
"Draft a comprehensive PRD from customer evidence, analytics, and technical context. Use when a PM needs help with prd draft."
perigon-sdks
goperigon
Best practices for using the official Perigon SDKs (TypeScript, Python, Go). Use this skill when installing, configuring, or writing code with any Perigon SDK to search news, track stories, summarize content, perform vector search, query Wikipedia, or look up people, companies, journalists, and sources.
claude-command-notion-find
monkey1sai
Converted from Claude plugin command "find" (Notion). Use when the user
rag-systems
pluginagentmarketplace
Retrieval Augmented Generation systems with vector search, document processing, and hybrid retrieval.
perigon-api-best-practices
goperigon
Best practices for building with the Perigon News Intelligence API. Use this skill when searching or filtering news articles, tracking evolving stories, generating AI-powered summaries, performing semantic vector search over news or Wikipedia, querying people, companies, journalists, or sources databases, or integrating any Perigon API endpoint into an application.
ai-integration
mrsknetwork
Integrates AI language model capabilities into applications — OpenAI (GPT-4o), Anthropic (Claude), and Google Gemini APIs, including streaming responses, function calling/tool use, retrieval-augmented generation (RAG) with vector search, and prompt management. Use when adding any AI features: chatbots, document Q&A, content generation, classification, summarization, or agents. Trigger when user mentions "OpenAI", "Claude", "Anthropic", "GPT", "AI chat", "chatbot", "RAG", "embeddings", "vector search", "LLM", "AI-powered", or "generate content".
airweave-setup
airweave-ai
Set up and integrate Airweave into applications. Use when the user wants to install Airweave, create collections, connect data sources, configure MCP servers, or set up the SDK to integrate Airweave into their app. For developers building with Airweave.
project-onboarding
mindmorass
Onboard new projects with standardized configuration and documentation
web-search-pro
Zjianru
Multi-engine web search with full parameter control. Supports Tavily, Exa, Serper, and SerpAPI with domain filtering, date ranges, deep search, news mode, and content extraction. Auto-selects the best engine based on query type and available API keys. 多引擎精细化搜索：支持域名过滤、日期范围、深度搜索、新闻模式、内容提取。 根据查询类型和可用 API Key 自动选择最优引擎。
find-skills
costa-marcello
"Discovers and installs agent skills from the open ecosystem and CCPM registries. Use when users ask 'how do I do X', 'find a skill for X', 'is there a skill that can...', 'ccpm', 'claude code skill', 'installed skills', or want to extend capabilities."
code-refactoring-context-restore
liuchiawei
"Use when working with code refactoring context restore"
image-search
clearsmog
Search the web for images (photos, logos, graphics) and download them with Typst embedding code. Use when the user needs real-world images, company logos, or existing graphics for documents.
cve-lookup
Mearman
Search for Common Vulnerabilities and Exposures (CVEs) by ID (e.g., CVE-2024-1086) or by product name (e.g., OpenSSL, Apache Tomcat). Get detailed vulnerability information including severity scores, affected software versions, and references. Use when the user wants to look up CVE information, check if a product has known vulnerabilities, or research security issues.
rem-sleep
stewnight
Memory consolidation and defragmentation for long-term memory maintenance. Use when asked to consolidate memories, defrag memory, run REM sleep, clean up memory files, or process session logs into durable memory. Also use periodically during heartbeats for memory maintenance.
context7
trancong12102
Retrieve current library documentation and code examples from Context7. Use when looking up library APIs, "docs", specific library versions, or "how to use [library]". Prefer over training knowledge for library-specific questions. Do not use for general programming concepts.
aftermath
mcxross
This skill should be used when the user asks about Aftermath Finance, Aftermath AMM, afSUI liquid staking, Aftermath pools, weighted pools, or wants to integrate with Aftermath on Sui. Covers weighted AMM pools, multi-coin swaps, deposits, withdrawals, LP tokens, and afSUI liquid staking.
langchain-embeddings
christian-bromann
Guide to using embedding model integrations in LangChain including OpenAI, Azure, and local embeddings
npm-search
Mearman
Search for npm packages by keyword, name, or description. Use when the user asks to search npm packages, find packages related to a topic, or discover packages for a specific purpose.
x402-ecosystem
rawgroundbeef
x402 ecosystem directory skill. Use when the user asks about x402 SDKs, libraries, facilitators, services, infrastructure, tools, or learning resources. Provides a searchable index of all projects in the x402 payment protocol ecosystem.
using-perplexity-for-context
designnotdrum
"Automatically use Perplexity search for personalized context enrichment. Use when facing unfamiliar technologies, decision points, learning questions, or preference-dependent choices."
recall
Genuifx
"Search and browse past session summaries saved in ~/.claude-done/. Use when the user says /recall, 'search history', 'find previous session', 'what did we do last time', 'look up past discussions', or wants to find earlier work."
langchain-vector-stores
christian-bromann
Guide to using vector store integrations in LangChain including Chroma, Pinecone, FAISS, and memory vector stores
building-ui
gigs-slc
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.