向量嵌入
向量检索与嵌入工作流
gog
malue-ai
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
local-places
malue-ai
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
gifgrep
malue-ai
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
redteam
neurofoo
Red team adversarial analysis to find weaknesses, vulnerabilities, and failure modes. Use before launches, for security review, or when a plan feels too perfect.
searxng-search
walterra
Web search and content extraction via SearXNG metasearch engine. Use when you need to search the web, look up documentation, research APIs, find current information, or extract content from URLs. No API keys required, no rate limits, privacy-preserving.
mcp-setup
spences10
Setup guide for essential MCP servers. Use when configuring MCP servers or when user asks about search, SQLite, or MCP management.
parallel
mvanhorn
High-accuracy web search and research via Parallel.ai API. Optimized for AI agents with rich excerpts and citations.
ui-ux-pro-max
julianromli
"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."
llm-application-dev
julianromli
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
seedhub
CaliCastle
"搜索 SeedHub (seedhub.cc) 影视资源，提取夸克网盘、百度网盘、阿里云盘、UC网盘、磁力链接等下载地址。触发词：seedhub、影视资源、找片、找电影、找剧、下载链接、夸克网盘。"
company-intelligence
Salesably
Generates comprehensive company research reports for sales preparation. Use this skill when preparing for executive meetings, researching target accounts, creating account plans, or understanding competitive landscape.
seo-content
Salesably
Creates search-optimized articles that rank well and read naturally for humans. This skill should be used when writing blog posts, pillar content, guides, or any content where organic search traffic is a goal - balancing search engine requirements with genuine reader value.
Getting Started with Research Superpowers
kthorn
Introduction to literature search & review skills - systematic paper finding, screening, extraction, and citation traversal
shopping-browser-automation
MassLab-SII
This skill provides tools and techniques for e-commerce website automation. Includes advanced search, product comparison, cart management, checkout process and other common shopping scenarios. Suitable for tasks requiring complex operations on e-commerce websites.
shopping-admin-browser-automation
MassLab-SII
This skill provides tools and techniques for Magento Admin panel automation. Includes admin login, customer management, search term analysis, and other common admin scenarios. Suitable for tasks requiring complex operations on e-commerce admin backends.
design-tokens-structure
dylantarre
Architects token systems with primitive, semantic, and component layers. Use when structuring tokens from scratch, adding multi-theme support, setting up token aliasing, or organizing token hierarchies.
surrealdb
mikkelkrogsholm
"SurrealDB — multi-model database supporting document, graph, relational, key-value, time-series, and vector search in a single engine using SurrealQL. Use when building with SurrealDB or asking about schema design (schemafull vs schemaless), SurrealQL queries, graph relations with RELATE, live queries, full-text search, JS/TS SDK setup, namespace and database hierarchy, record IDs, authentication with DEFINE ACCESS, or connecting with WebSocket vs HTTP. Fetch live documentation for up-to-date details."
meilisearch
mikkelkrogsholm
"Meilisearch — fast, open-source search engine with typo tolerance, faceted search, and AI-powered hybrid search. Use when building with Meilisearch or asking about its index configuration, search parameters, filters, facets, API keys, geosearch, ranking rules, or integration with JavaScript/TypeScript clients. Fetch live documentation for up-to-date details."
tanstack-router
mikkelkrogsholm
"TanStack Router — fully type-safe router for React with file-based routing, search params validation, loaders, and built-in caching. Use when building with TanStack Router or asking about its route configuration, file-based routing, type-safe links, search params, loaders, or navigation patterns. Fetch live documentation for up-to-date details."
upstash
mikkelkrogsholm
"Upstash — serverless Redis, QStash, and Vector database with per-request pricing optimized for edge and serverless environments. Use when building with Upstash or asking about its Redis client, QStash message queuing, rate limiting, workflows, or vector search. Fetch live documentation for up-to-date details."
chroma
L-yifan
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.
faion-rag-engineer
faionfaion
"RAG engineering: embeddings, chunking, vector databases, hybrid search, reranking."
aio-youtube
aiocean
This skill should be used when the user asks to "search YouTube", "get video transcript", "summarize video", "extract subtitles", or mentions YouTube, video search, captions, yt-dlp, or provides youtube.com/youtu.be URLs.
web-search
lodekeeper
Multi-source web search orchestrator. Use when web_search/web_fetch are insufficient and you need query classification, parallel provider search, ranking, deduplication, and optional synthesis across web/code/academic/social sources.