向量嵌入
向量检索与嵌入工作流
izakaya-search
danishi
Search and recommend izakaya (Japanese-style pubs) and restaurants based on party size, budget, area, and additional preferences. Aggregates reviews from gourmet sites (Tabelog, Hot Pepper Gourmet, Gurunavi) and Google Maps, calculates composite ratings, and provides reservation links and Google Maps directions for quick booking.
keyword-research
Growth4U-systems
"Strategic keyword research without expensive tools. Use when someone needs content strategy, topic ideas, SEO planning, or asks what should I write about. Uses the 6 Circles Method to expand from seed keywords, clusters into content pillars, and maps to a prioritized content plan. Triggers on: keyword research for X, content strategy for X, what topics should I cover, SEO strategy, content calendar, topic clusters. Outputs prioritized keyword clusters with content recommendations."
google-drive
minkhant1996
"Manage Google Drive - upload, download, share files, create folders"
omni-recall
ralph-wren
"Omni-Recall: Neural Knowledge & Long-Term Context Engine. Manages cross-session agent memory via Supabase (pgvector) and APIYI. Invoke to store/retrieve persistent context."
dify-llm-platform
aeonbridge
Build LLM applications using Dify's visual workflow platform. Use when creating AI chatbots, implementing RAG pipelines, developing agents with tools, managing knowledge bases, deploying LLM apps, or building workflows with drag-and-drop. Supports hundreds of LLMs, Docker/Kubernetes deployment.
search-analyze-report-template
djankies
[REPLACE] Search for patterns, analyze findings, generate structured reports. Use when [REPLACE with specific triggers].
create-ex
Lyricus233
Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution. 把前任蒸馏成 AI Skill，导入微信聊天记录、照片、朋友圈，生成 Relationship Memory + Persona，支持持续进化。
brave-search
blackhaj
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Knowledge Base Ingestion
srsubramanian
Ingest and manage documents in the vector knowledge base
always-on-agent-architecture
curiositech
Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastructure, vector stores, and framework selection. Provides concrete deployment patterns for agents that maintain identity and learn across sessions. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-patterns).
building-native-ui
kennethkeim
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
hydric-gateway-js-ts-sdk-user
hydric-org
Expert skill for integrating the hydric Gateway SDK (@hydric/gateway) in JavaScript and TypeScript. Use this skill to orchestrate multi-chain liquidity, resolve token identities, and build high-fidelity DeFi dashboards with institution-grade precision.
codebase-onboard
adilasif
This skill should be used when the user is new to a codebase and wants to understand its structure, architecture, or main components. Trigger phrases include "help me understand this codebase", "I'm new to this project", "give me an overview", "what are the main components", "how is this structured", or "onboard me". Use for initial exploration, not for specific questions.
gemini-search
takuan-osho
Web search using Google Gemini CLI. This skill should be used when performing web searches through the Gemini CLI tool instead of the built-in WebSearch tool. Requires the Gemini CLI to be installed and configured.
shareful-search
shareful-ai
Helps users discover and apply shared coding solutions when they ask "has anyone solved this", "search for a fix", "find a workaround", or want proven patterns before debugging from scratch. Uses npx shareful-ai search to find relevant shares, compare options, and recommend the best match.
glossary
TakaGoto
"Look up RAG terminology and concepts"
memory
harperreed
Semantic memory and context - store and retrieve information with embeddings for similarity search. Use for long-term memory, context recall, and knowledge persistence.
deep-research
Baphomet480
Conduct comprehensive, multi-round research that produces rich visual reports. Use when asked for "deep research", "comprehensive analysis", "compare frameworks", "evaluate options", "research the state of X", or any task requiring investigation across 10+ sources. NOT for quick lookups — this is a 5-15 minute deep dive that produces a briefing-quality artifact with screenshots, diagrams, tables, and cited findings.
qveris
hqman
Search and execute dynamic tools via QVeris API. Use when needing to find and call external APIs/tools dynamically (weather, search, data retrieval, stock trading analysis, etc.). Requires QVERIS_API_KEY environment variable.
supabase
leonaaardob
Complete Supabase platform documentation. Use when working with Supabase - covers authentication (email, OAuth, magic links, phone, SSO), database (PostgreSQL, RLS, migrations), storage (file uploads, CDN), edge functions, realtime subscriptions, AI/embeddings, cron jobs, queues, and platform management. Includes framework integrations (Next.js, React, SvelteKit, etc.).
semantic-video-clipper
seefreed
AI analyzes subtitles to identify optimal split points, then clips video segments using FFmpeg based on AI-provided cue indices. Use when asked to segment videos (e.g., .mp4) based on .vtt/.srt subtitles.
codebase-search
zhongjis
Search and navigate codebases — both local and remote. Use when finding specific code patterns, tracing function calls, understanding code structure, locating bugs, or searching GitHub repositories for implementations and examples. Handles semantic search, grep patterns, AST analysis, and remote code search via GitHub CLI and API. Also use when the user asks "how do other projects do X", "find examples of Y on GitHub", "search repo Z for", or wants to explore code in repositories they haven't cloned.
hence-search
hence-sh
Browse and search the Hence gallery (hence.sh) to discover projects built with AI coding agents. Use when the user wants inspiration, wants to see what others have built, asks about projects on Hence, or mentions searching for AI-built projects. Triggers on queries like "show me cool projects", "search Hence", "find CLI tools on Hence", or "what are people building with Claude Code".
codex-docs
adamelliotfields
Get OpenAI Codex documentation pages in Markdown. Use when you need to reference Codex CLI features, configuration options, or any other Codex functionality.