Claude Code AI Agent Skills

Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using excalidraw-brute-export-cli.

This skill should be used when the user says "why now", "is the timing right", "what's changed", "why didn't this exist before", "why is this possible now", "what's the tailwind", or needs to formalize whether there is a structural timing advantage for this idea — not just "AI is taking off.

Your AI forgets everything when you close the tab. Phloem fixes that. Phloem is a local MCP server that gives your AI persistent memory across sessions. It works with any tool that supports the Model Context Protocol — an open standard. Today that includes Claude Code, VS Code, Cursor, Windsurf, Zed, Neovim, Cline, Warp, Continue, JetBrains, and more arriving every week. You install it once. Every

A structural codebase indexer with an MCP server for AI-assisted development. Zero runtime dependencies — uses Python's ast module for Python analysis and regex-based parsing for TypeScript/JS, Go, and Rust. Requires Python 3.11+. Indexes codebases by parsing source files into structural metadata -- functions, classes, imports, dependency graphs, and cross-file call chains -- then exposes 18 query

Connect Claude Code to your Robinhood account. Analyze your portfolio, get real-time quotes, and execute trades—all through conversation. Then in Claude Code: 1. Type /mcp → select trayd → click Authorize 2. Sign in with Google 3. Say: "Link my Robinhood account" 4. Approve on your phone 5. Start trading! Instead of clicking through dozens of screens: Important to understand: - Your Robinhood emai

Free Local RAG for Claude Code - Save Tokens & Time 日本語版はこちら | Japanese Version DevRag is a lightweight RAG (Retrieval-Augmented Generation) system designed specifically for developers using Claude Code. Stop wasting tokens by reading entire documents - let vector search find exactly what you need. When using Claude Code, reading documents with the Read tool consumes massive amounts of tokens: - ❌

A Model Context Protocol (MCP) server that enables you to manage Gitea/Forgejo repositories through AI assistants like Claude, Gemini, and Copilot. If you want to: - Smart progress tracking: Let AI help you track project progress and analyze bottlenecks - Automated issue categorization: Automatically tag issue labels and set milestones based on content - Priority sorting: Let AI analyze issue cont

Minimal bash statusline showing model, git branch, and directory. Zero dependencies — a single shell script you drop into your Claude Code settings.

Outlook Assistant MCP server for Outlook email, calendar, and contacts — let your AI assistant manage your inbox directly from the conversation. Outlook Assistant connects AI assistants to your Microsoft Outlook account through the Model Context Protocol. Ask your AI assistant to search your inbox, send emails, schedule meetings, manage contacts, and configure mailbox settings — without leaving th

Node-based Claude Code statusline. Shows model, session cost, token usage, and git branch. Configurable segments via a JSON config.

openings-mcp One MCP server to search job boards and company career sites. openings-mcp searches job listings across job boards and company career sites from any MCP client: Claude Code, Codex, Gemini CLI, and others. - Job boards: 104, Cake, Jobindex (Denmark), マイナビ転職 (Japan), Flowxtra (board-wide across every company on the Flowxtra ATS), LinkedIn, and Indeed (public search). - Company career si

A local vector memory explorer with a modern UI inspired by Supabase and Pinecone. Browse, search, visualize and manage the SQLite-vec database created by MCP Memory Service . I'm a sysadmin by trade, not a developer. My coding background is some C++ from many years ago. I built memviz entirely through vibe coding with Claude Code as a way to test AI-assisted development workflows. The whole thing

59 skills that actually work. Built by a physician-researcher, tested on real publications. MedSci Skills is an end-to-end research tool for physician and medical-engineering researchers — design → scaffold → validate → publish — for the clinical manuscript and the medical-AI model behind it. Its moat is the compliance layer — 49 reporting guidelines and risk-of-bias tools, referenc

Push architecture docs to oh-my-mermaid cloud. Handles login, link, and push workflow with error guidance. Use when the user says "omm push", "push to cloud", "deploy architecture", or "share architecture".

Drives strict red-green-refactor: writes a failing test, runs it, implements just enough to pass, refactors. Use when you want to enforce TDD on a new feature.

Instead of manually checking the Rybbit dashboard, let your AI assistant query analytics data directly: - "How many users visited the site today?" - "Show me the top pages by bounce rate this week" - "What errors occurred in the last hour?" - "Show user journey from homepage to checkout" - "Compare browser usage between mobile and desktop" Or clone and build: Add to your ~/.claude/settings.json or

An MCP (Model Context Protocol) server that makes critical best practices automatically available to Claude AI in every conversation. Based on exhaustive analysis of 96+ real documented failures over 6+ months of intensive production usage. The system provides 21 numbered rules organized into 5 categories, with automatic verification checklists, rule summaries, and auto-update capabilities. - 21 C

An MCP server that lets AI assistants like Claude read LinkedIn data through your own logged-in browser session. Access profiles and companies, search for jobs, or get job details. This MCP server is free and open source, supported by Unipile. It runs locally with your own browser session. Unipile is the fully managed cloud alternative: a hosted LinkedIn API for Classic, Sales Navigator, and Recru

General principles for structured content modeling that apply across CMSs, with Sanity-specific guidance. Use when designing content schemas, planning content architecture, or evaluating content reuse strategies.

- Fixed reply threading — auto-resolves In-Reply-To and References headers so email replies land in the correct thread instead of creating orphaned messages (upstream PR 91, still pending) - Send-as alias support — optional from parameter for multi-identity email management (send from any configured Gmail alias) - Reply-all tool — replyall automatically fetches the original email, builds To/CC rec

Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminals, logs, traces, or Claude's context. Trigger phrases include "environment variables", "secrets", ".env", "API key", "credentials", "sensitive", "Varlock".