向量嵌入
向量检索与嵌入工作流
Linear Issue Tracking - Complete Reference
alienfast
Linear issue tracking - MUST READ before using Linear commands
building-adk-agents
sumik5
Google ADK (Agent Development Kit) for building intelligent AI agents with Python. MUST load when google-adk is detected in requirements or pyproject.toml. Covers Agent taxonomy, Agent types (LlmAgent/Sequential/Parallel/Loop/Base), Tools (FunctionTool/OpenAPI/MCP), Multi-Agent orchestration, A2A Protocol (JSON-RPC/REST), Runner, Session, Artifact, Memory, State lifecycle, Context (Caching/Compaction), RAG (Corpus/Vector Search/Agentic), Grounding, Plugin System, Callbacks/Guardrails (6 types), SSE Streaming, Live API, UI Integration (CopilotKit/Streamlit/Slack), Code Execution, LLM Models (Gemini/LiteLLM/Anthropic), Deployment (Cloud Run/Vertex/GKE), CI/CD, Cost optimization, Security (IAM/Data privacy), Responsible AI. Distinct from developing-python (general) by focusing on ADK patterns.
prd
alienfast
Create agent-friendly Linear tickets with PRDs, sub-issues, and clear success criteria. Use when planning features or breaking down work for agentic coding.
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）。
building-rag-systems
sumik5
Comprehensive RAG (Retrieval-Augmented Generation) system building guide covering data loading pipelines (11 source types including Word, PDF, CSV, audio, video, multimodal), data preparation (metadata enrichment, text quality enhancement, 5 chunking strategies from character to agentic), and full RAG architecture overview with Python. Use when building RAG applications, designing data ingestion pipelines, or implementing text chunking strategies. For Python language best practices, use developing-python instead. For LLMOps operational framework, use practicing-llmops. For JavaScript/LangChain.js RAG in web apps with Vercel AI SDK, see integrating-ai-web-apps.
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.
memory-systems
eyadsibai
Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"
vibium-browser-automation
trotsky1997
Comprehensive guide for using Vibium browser automation tool via MCP. Use when (1) Automating web interactions in Cursor IDE, (2) Navigating web pages, (3) Taking screenshots, (4) Clicking buttons or links, (5) Filling forms or input fields, (6) Finding elements on web pages, (7) Web scraping tasks, (8) Testing websites, or any task requiring programmatic browser control within Cursor IDE
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.
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。
neurograph
greatnorthernfishguy-hub
"NeuroGraph is a cognitive memory system that remembers context across conversations using a spiking neural network substrate. Invoke when the user asks about memory, remember, context, what was learned, what the system knows, Syl, graph associations, knowledge, or wants to ingest or feed content into the knowledge base."
web-research
Tempuss
Use when researching markets, analyzing competitors, comparing technologies, or finding case studies. Ensures all findings include credible sources and URLs.
dataset-curator
famaoai-creator
Prepares and audits high-quality datasets for AI/RAG applications. Cleans noise, structure data, and ensures privacy compliance in knowledge bases.
syncing-submodules
eyadsibai
Use when running /ltk:sync-submodules, updating submodules, or needing to "sync", "merge", "adapt", "learn from" other Claude Code plugins or repos
skiplagged-travel-search
skiplagged
This skill should be used when the user asks to "find flights", "compare itineraries", "search hidden-city routes", "check cheapest dates", "explore destinations anywhere", "search hotels", or "plan a trip". Ground outputs in Skiplagged MCP tool results for flights, fare calendars, anywhere discovery, and hotels.
@tank/gmail
tankpkg
"Send, read, search, label, and manage email through the Gmail API. Covers composing (plain text, HTML, attachments), thread-aware replies, Gmail search query syntax (from:, to:, has:attachment, after:), label management, filter automation, and draft workflows. Triggers: gmail, email, send email, read email, search email, attachment, label, filter, thread, draft, Gmail API, compose, reply, forward, inbox, MIME."
@tank/llm-app-patterns
tankpkg
Build production-grade LLM-powered applications — RAG systems, tool-using agents, structured output extraction, streaming responses, and cost optimization. Covers the full engineering stack for apps built on top of foundation models, not model training. Synthesizes Huyen (AI Engineering), Brousseau & Sharp (LLMs in Production), Bouchard & Peters (Building LLMs for Production), Lanham (AI Agents in Action), Arsanjani & Bustos (Agentic Architectural Patterns), Rothman (RAG-Driven Generative AI). Trigger phrases: "RAG", "retrieval-augmented generation", "vector search", "chunking strategy", "embedding", "reranking", "hybrid search", "tool use", "function calling", "tool calling", "agent", "agentic", "multi-agent", "orchestrator", "structured output", "JSON mode", "Instructor", "Pydantic", "streaming", "server-sent events", "SSE", "token streaming", "LLM cost", "model routing", "semantic cache", "prompt caching", "LLM evaluation", "LLM-as-judge", "RAGAS", "hallucination", "faithfulness", "golden dataset", "LLM in production", "LLMOps", "build with LLMs", "LLM application"
master-ba
truongnat
Elite business analysis standards focused on requirements deconstruction, stakeholder value alignment, Gherkin acceptance criteria, and risk analysis. Use when defining new features, complex system migrations, or strategic planning.
deps
alienfast
Visualize and analyze issue dependencies in Linear. Finds blocking chains, circular dependencies, and critical path items.
ast-grep
trotsky1997
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
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.
applying-semantic-versioning
sumik5
Semantic Versioning 2.0.0仕様に基づくバージョン判断ガイド。MAJOR/MINOR/PATCH判定、プレリリース・ビルドメタデータ、範囲指定を提供。 REQUIRED for all version-related decisions. Use when determining version bumps, creating releases, or managing dependencies.
context-optimization
eyadsibai
Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgeting", "context partitioning"
multimodal-models
eyadsibai
Use when "CLIP", "Whisper", "Stable Diffusion", "SDXL", "speech-to-text", "text-to-image", "image generation", "transcription", "zero-shot classification", "image-text similarity", "inpainting", "ControlNet"