Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for…
Apply modern JavaScript patterns including async/await, modules, iterators, generators, and functional composition. Use when the user needs ES6+ refactors, cleaner JavaScript structure, or performance-oriented modern syntax.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Read, extract, merge, split, rotate, watermark, create, fill, encrypt, decrypt, and OCR PDF files. Use when the user mentions PDFs or needs any document workflow centered on .pdf files.
Organize complex work with file-based planning artifacts such as taskplan.md, findings.md, and progress.md. Use when the user needs a multi-step task, project, or research effort broken down and tracked across many tool calls.
Complete browser automation with Playwright. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, and automate browser tasks. Use when the user wants browser-based testing or scripted web automation.
Create professional slide decks from topics or source documents, including structured content, charts, speaker notes, and complete PPTX outputs. Use when the user needs presentations, pitches, slide decks, or keynote-style materials.
Create, read, edit, split, combine, and extract content from .pptx presentation files. Use when the user mentions slides, decks, presentations, or any workflow where a PowerPoint file is the primary artifact.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Build, optimize, and debug cross-platform mobile applications with React Native and Expo. Use when the user needs navigation setup, native-module integration, mobile performance work, or platform-specific iOS and Android handling.
Work safely on rememb MCP tools, schemas, and compatibility-sensitive server behavior. Use when the task changes MCP contracts, tool definitions, response formats, or backward-compatibility-sensitive server logic.
Design and review software architecture, scalability strategy, dependency boundaries, and technical decisions. Use when the user asks for system design, architecture reviews, database choices, microservice tradeoffs, or architecture diagrams.
Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends AI capabilities with specialized knowledge, workflows, or tool integrations.
Search, retrieve, and install Agent Skills from a registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for an AI assistant, or extend AI capabilities with reusable AI agent components.
Guide users through creating portable AI skills. Use when the user wants to create, write, author, or redesign a skill, or needs help with SKILL.md files, frontmatter, portability, or skill structure.
Search for and install portable AI skills that extend specialized capabilities. Use when the task may already have a reusable skill, or when the user explicitly asks to find, install, or manage skills.
Optimize SQL queries with indexing strategies, EXPLAIN analysis, and database performance tuning patterns. Use when the user needs to diagnose slow queries, design efficient schemas, or improve database-backed application performance.
Execute a written implementation plan through independent task workers in the current session. Use when the plan can be split into isolated tasks with explicit review gates.
Diagnose bugs, test failures, and unexpected behavior before proposing fixes. Use when the user reports a defect and root cause needs to be established before editing code.
Generate test cases for code. Use when writing unit tests, integration tests, or verifying acceptance criteria.
★not rated 4 1mo agoA23 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: