向量嵌入

content-strategy

almeidamarcell

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," or "content planning." For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit.

deep-research

lv416e

"Conduct comprehensive, multi-source research on any topic using web search, documentation lookup, and critical analysis. This skill should be used when users request thorough investigation, deep research, or comprehensive analysis of topics including but not limited to AI systems, technology trends, academic subjects, business strategies, or current events. 任意のトピックに対して、Web検索、ドキュメント参照、批判的分析を用いた包括的な調査を実施。徹底的な調査、詳細なリサーチ、包括的な分析が必要な場合や、AIシステム、技術トレンド、学術的テーマ、ビジネス戦略、時事問題などについて深く知りたい場合に使用。"

visualizing-with-mermaid

third774

Create professional Mermaid diagrams with proper styling and visual hierarchy. Use when creating flowcharts, sequence diagrams, state machines, class diagrams, or architecture visualizations.

free-tool-strategy

almeidamarcell

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers.

dsearch

icampana

Search and read offline documentation for various programming languages and libraries. Use this skill when you need to verify syntax, check function signatures, or read documentation without internet access.

vector-database-management

manutej

Comprehensive guide for managing vector databases including Pinecone, Weaviate, and Chroma for semantic search, RAG systems, and similarity-based applications

langchain-orchestration

manutej

Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration

context-engineering-advisor

TurboSnails

Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.

archive-searcher

YuniorGlez

"Professional Git Forensics and Archival Intelligence for deep historical recovery."

search-x

mvanhorn

Search X/Twitter in real-time using Grok. Find tweets, trends, and discussions with citations.

design-system-pro

YuniorGlez

Senior Design System Architect & Token Engineer for 2026. Specialized in layered design tokens, Tailwind 4 CSS-first themes, and headless UI orchestration using Radix. Expert in building multi-brand, multi-theme systems with high architectural integrity, automated documentation-as-code, and AI-driven drift detection.

postgres-tuning

YuniorGlez

"Senior Database Optimizer for PostgreSQL 17/18+, specialized in Asynchronous I/O (AIO), Query Plan Forensic, and Vector Index optimization."

memory-integration

troykelly

Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts

ai-native-development

ArieGoldkin

Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.

app-intents-expert-skill

rudrankriyam

Expert App Intents guidance for building Siri, Shortcuts, Spotlight, Apple Intelligence, and interactive snippet integrations on iOS 26+. Use when implementing AppIntent, AppEntity, AppEnum, EntityQuery, AppShortcutsProvider, SnippetIntent, SiriTipView, IndexedEntity, or when making an app work with Siri, Shortcuts, Spotlight, Apple Intelligence, Visual Intelligence, Action Button, or Apple Pencil. Also use when asked about App Intents architecture, intent-driven development, or migrating from SiriKit.

cloudflare-vectorize

jackspace

Complete knowledge domain for Cloudflare Vectorize - globally distributed vector database for building semantic search, RAG (Retrieval Augmented Generation), and AI-powered applications. Use when: creating vector indexes, inserting embeddings, querying vectors, implementing semantic search, building RAG systems, configuring metadata filtering, working with Workers AI embeddings, integrating with OpenAI embeddings, or encountering metadata index timing errors, dimension mismatches, filter syntax issues, or insert vs upsert confusion. Keywords: vectorize, vector database, vector index, vector search, similarity search, semantic search, nearest neighbor, knn search, ann search, RAG, retrieval augmented generation, chat with data, document search, semantic Q&A, context retrieval, bge-base, @cf/baai/bge-base-en-v1.5, text-embedding-3-small, text-embedding-3-large, Workers AI embeddings, openai embeddings, insert vectors, upsert vectors, query vectors, delete vectors, metadata filtering, namespace filtering, topK search, cosine similarity, euclidean distance, dot product, wrangler vectorize, metadata index, create vectorize index, vectorize dimensions, vectorize metric, vectorize binding

azure-ai-search-python

hainamchung

Clean code patterns for Azure AI Search Python SDK (azure-search-documents). Use when building search applications, creating/managing indexes, implementing agentic retrieval with knowledge bases, or working with vector/hybrid search. Covers SearchClient, SearchIndexClient, SearchIndexerClient, and KnowledgeBaseRetrievalClient.

azure-ai-services

markus41

Deep expertise in Azure AI workloads — provisioning and managing Azure OpenAI Service deployments, Azure AI Search indexes and skillsets, Azure AI Studio/Foundry projects, Cognitive Services endpoints, content filtering policies, quota management, and responsible AI governance via ARM REST API and service-specific data planes.

accessibility-engineer

mae616

Apply semantic HTML/JSX and WAI-ARIA correctly and minimally. Apply when implementing any UI, especially forms, interactive components, or when accessibility is mentioned.

modern-accessible-html-jsx

academind

Write clean, modern, and highly accessible HTML & JSX code, using semantically correct elements and attributes

docs-discovery

samhvw8

"Technical documentation discovery via context7 and web search. Capabilities: library/framework docs lookup, topic-specific search. Keywords: llms.txt, context7, documentation, library docs, API docs. Use when: searching library documentation, finding framework guides, looking up API references."

UI Design Reference - Searchable Pattern Database

samhvw8

claude-command-firecrawl-search

monkey1sai

Converted from Claude plugin command "search" (firecrawl). Use when the

agently-task-dev

okwinds

Use only when the user explicitly wants to build with the Agently framework (mentions Agently/agently/OpenAICompatible/TriggerFlow/ToolExtension/ChromaCollection, or says “用 Agently 做/用 agently 做”). Deliver runnable code plus regression tests validating schema/ensure_keys and streaming (delta/instant/streaming_parse), with optional tools (Search/Browse/MCP), TriggerFlow orchestration, KB (ChromaDB), and serviceization (SSE/WS/HTTP). Do not use for generic streaming/testing questions that are not about Agently, or for prompt-only writing without tests/structure.