Embeddings
Vector embeddings and similarity
model-extraction
by pluginagentmarketplace
Techniques to extract model weights, architecture, and training data through API queries
rag-exploitation
by pluginagentmarketplace
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
modern-accessible-html-jsx
by academind
Write clean, modern, and highly accessible HTML & JSX code, using semantically correct elements and attributes
airweave-search
by airweave-ai
Search and retrieve context from Airweave collections. Use when users ask about their data in connected apps (Slack, GitHub, Notion, Jira, Confluence, Google Drive, Salesforce, databases, etc.), need to find documents or information from their workspace, want answers based on their company data, or need you to check app data for context to complete a task.
Web Search
by WingsZeng
This skill should be used when needs to search for unknown information, verify understanding, or avoid hallucination. or when detects knowledge gaps during task execution. Also trigger when the user asks to "search online", "look up information", "verify facts", "check documentation", "find latest version".
iconify-skill
by bingal
Search Iconify collections and generate SVG icons with size/color customization; use for requests about finding icon IDs, suggesting icons by intent, retrieving SVG markup, or working offline with a bundled icon index.
ielts-speaking
by KaichenCurry
雅思口语AI教学助手。核心理念：无标准答案，逐句个性化反馈（语法/词汇/时态/逻辑/思路）。
lobster-radio
by Jayden-X-L
"个性化资讯电台生成服务。使用场景：(1) 生成特定主题的电台，(2) 设置每日定时推送，(3) 配置TTS音色，(4) 收听历史电台。不适用：音乐播放、实时广播、视频内容。"
ddgr
by ysm-dev
Search the web using DuckDuckGo via the ddgr CLI tool. Use when the user asks to search the web, look something up online, find information on the internet, get instant answers, or needs current/real-time data. Also use for DuckDuckGo Bang searches (e.g., "!w" for Wikipedia, "!so" for StackOverflow).
browser-automation
by femto
Control Chrome browser with AI using MCP protocol. Use when users want to automate browser tasks, take screenshots, fill forms, click elements, navigate pages, search browsing history, manage bookmarks, or perform any browser-based automation. Works with your existing Chrome browser and login sessions.
embedding-service
by Lin-A1
文本向量化（Embedding）基础服务。将自然语言转换为高维稠密向量，为语义搜索、聚类分析、推荐系统等下游任务提供核心数据支持。
nexi-search
by lirrensi
Web search CLI that uses LLMs to search, read pages, and synthesize answers with citations. Use when you need current information from the web - news, documentation, recent events, or any topic requiring up-to-date sources. Invoke with nexi --plain "query" for programmatic use.
websearch-service
by Lin-A1
基于 SearXNG 与 VLM 的实时联网搜索服务。专用于获取最新新闻、实时事件及特定事实。内置智能双层缓存（向量+数据库）与网页内容自动提取分析功能。
jira
by avantmedialtd
Manage Jira issues from the command line. Use when working with Jira issues, creating tasks, updating status, assigning work, or searching for issues.
skanetrafiken
by rezkam
Skåne public transport trip planner (Skånetrafiken). Plans bus/train journeys with real-time delays. Supports stations, addresses, landmarks, and cross-border trips to Copenhagen.
gui-screenshot-loop
by Idate96
General GUI screenshot loop via MCP. Use for any screen/window/region capture while debugging UI or visual tools.
triage
by alienfast
Triage and prioritize Linear backlog. Analyzes issues for staleness, blockers, and suggests priorities based on dependencies and capacity.
variation-theory
by dbosk
Apply variation theory of learning to structure instructional content using contrast, generalization, and fusion patterns. Variation must target the critical aspects of the learning objective. Use when writing educational materials, explanations, tutorials, literate programming documentation (.nw files), structuring lecture slides, designing exercises, or when user mentions variation theory, learning theory, pedagogy, or critical aspects of learning. Works alongside the literate-programming skill for .nw files.
Linear Issue Tracking - Complete Reference
by alienfast
Linear issue tracking - MUST READ before using Linear commands
building-adk-agents
by 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
by 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.
visual-design
by teslasoft-de
Create visual designs, design systems, and UI specifications. Use for typography scales, color systems, layout grids, component design, and accessibility compliance. Covers OKLCH color spaces, variable fonts, fluid typography, design tokens (W3C DTCG), and Atomic Design methodology. Keywords: UI design, color palette, design tokens, WCAG contrast, component library.
literature-review
by 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
by 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.