向量嵌入
向量检索与嵌入工作流
ui-ux-pro-max
atxinsky
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
memory-management
richfrem
"Tiered memory system for cognitive continuity across agent sessions. Manages hot cache (session context loaded at boot) and deep storage (loaded on demand). Use when: (1) starting a session and loading context, (2) deciding what to remember vs forget, (3) promoting/demoting knowledge between tiers, (4) user says 'remember this' or asks about project history."
gui-screenshot-loop
Idate96
General GUI screenshot loop via MCP. Use for any screen/window/region capture while debugging UI or visual tools.
ask-shadcn-architect
NavanithanS
Enforce shadcn/ui patterns, imports, and CLI-first component usage.
pinecone
magnetoid
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
literature-review
Victory-Hugo
使用多个学术数据库（如 PubMed、arXiv、bioRxiv、Semantic Scholar 等）开展全面、系统化的文献综述。适用于系统综述、Meta 分析、研究综合，或跨生物医学、科学和技术领域的全面文献检索。可生成包含已验证引用的专业格式 Markdown 文档和 PDF，支持多种引用格式（如 APA、Nature、Vancouver 等）。
dspy
magnetoid
"DSPy: declarative LM programs, auto-optimize prompts, RAG."
mem-skill
Lilily58
Hybrid conversational memory management using SQLite and a vector database for retrieval-augmented user context. Use when building or updating assistants that need persistent user facts, lexical plus semantic retrieval, conflict arbitration, confidence scoring, temporal validity, and profile injection across turns.
qmd
magnetoid
Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.
rag
Kiki276
Use when the user has already provided source material and needs a cited, evidence-constrained answer from that material. Not for external retrieval.
faiss
magnetoid
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
pubmed-database
Victory-Hugo
直接访问PubMed REST API。高级布尔/MeSH查询、E-utilities API、批量处理、引文管理。对于Python工作流，建议使用biopython (Bio.Entrez)。此技能适用于直接HTTP/REST操作或自定义API实现。
clip
magnetoid
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
chroma
magnetoid
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
pageindex-rag
mmtmr
Build reasoning-based RAG systems using PageIndex architecture. Replaces vector databases with hierarchical table-of-contents indices and LLM-driven navigation. Use when (1) implementing RAG for long structured documents (financial reports, legal contracts, technical manuals), (2) improving existing vector-based RAG systems with poor accuracy on structured content, (3) designing document indexing strategies with semantic coherence, (4) explaining PageIndex concepts including reasoning-based retrieval, hierarchical navigation, and cross-reference following, or (5) handling documents with internal references and multi-turn conversations. Focuses on technical architecture, core research insights, and practical implementation patterns rather than using the PageIndex package directly.
indx-search
indxSearch
Indx Search integration skill for AI coding agents. Use when building search functionality with Indx — a high-performance search engine using pattern recognition instead of tokenizers or stemmers. Covers C# NuGet (IndxSearchLib) and HTTP API (IndxCloudApi) integration, field configuration, querying, filters, boosts, coverage tuning, and search UX patterns.
qdrant-vector-search
magnetoid
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
Intelligence Router
AmnadTaowsoam
The Intelligence Router implements the "Twin-Engine" Intelligence Architecture
parallel-search
otrebu
Comprehensive web research via Parallel Search API. Use when user requests parallel search for deep multi-source research, technical analysis, learning new topics, current events, or comparative studies. Returns LLM-ready ranked URLs with extended excerpts (up to 30K chars). Single API call handles multiple query angles with automatic deduplication.
skillsmp-search
koryaga
Search and discover AI skills using the SkillsMP API. Supports keyword search and AI semantic search powered by Cloudflare AI. Use when users want to find AI skills, search for specific capabilities, or explore community-built AI tools. Triggers on "search skills", "find AI skills", "look up skills", "skills marketplace", "AI skills database".
bid-manager
youyouhe
投标全流程管理器。编排所有 bid skills 按流水线自动执行，支持一键投标、 断点续跑、指定阶段启动。10个阶段：分析→核实→信息收集→商务标→技术标→ 图表→扫描件→质检→自动修复→生成Word。 当用户要求一键投标、全流程投标、管理投标进度、继续投标流程时触发。 前置条件：需要有招标/磋商/采购文件。
ollama
balloob
Use this if the user wants to connect to Ollama or leverage Ollama in any shape or form inside their project. Guide users integrating Ollama into their projects for local AI inference. Covers installation, connection setup, model management, and API usage for both Python and Node.js. Helps with text generation, chat interfaces, embeddings, streaming responses, and building AI-powered applications using local LLMs.
skill-system-memory
arthur0824hao
Persistent shared memory for AI agents backed by PostgreSQL (fts + pg_trgm, optional pgvector). Includes compaction logging and maintenance scripts.
web-search
koryaga
Web search capability using DuckDuckGo API by default, with Tavily API fallback when TRAVILY_TOKEN is provided. Use when you need to search the web for current information, research topics, find URLs, or gather data from online sources. Supports queries for news, technical information, research papers, company data, and general web content.