Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 378,556 indexed, measured the same four ways as everything else here.
Hunt for bugs in distributed consensus protocol implementations using a 2-agent strategy+testgen pipeline. Use when targeting consensus protocols (Raft, PBFT, HotStuff, Tendermint, etc.) for automated vulnerability discovery.
A communication framework that helps turn vague requests and hidden assumptions into explicit instructions. It focuses on making goals, relationships, boundaries, and acceptance criteria clear enough for another person or an AI system to reproduce.
An automation skill for carrying out a smart Lunar New Year greeting-sending task in the WeChat Mac desktop app. The supplied description does not provide further details about how it works.
Use this agent PROACTIVELY after implementing new features, before committing changes, or when refactoring existing code. The agent will automatically run linting and type checking tools, then analyze both frontend (React/TypeScript) and backend (Python/FastAPI) code against specific quality rules including file size…
Process learning materials into structured Obsidian atomic notes with roadmaps, MOCs, and double-links. Auto-generate study vaults from PDFs, Markdown, Word, PowerPoint, and more with AI-powered note-taking, knowledge linking, and deep research. Supports English and Chinese output. Use when the user wants to build a…
Use when creating Lit web components with TypeScript decorators, JSDoc documentation, Zod validation, and Playwright testing. Use for building reusable web components, design systems, or shareable UI elements that work across frameworks.
Extract any brand into a DESIGN.md file. Use when the user asks to extract a brand, get colors and fonts from a website, generate brand guidelines from a URL, build on-brand assets for a specific company, or prepare design tokens for AI agents. Outputs a Stitch-compatible DESIGN.md any AI agent (Claude Code, Cursor…
A skill for starting or continuing a compact mind map, a structured visual outline of a topic. It creates files, writes drafts, and supports repeated human-agent revisions.
Get a second opinion from multiple AI models at once. Use this whenever you're stuck, want to validate an approach or design, pressure-test a plan or claim, or want diverse cross-model viewpoints on a hard decision - anything you'd reach for "peer review", "ask another model", or "council of models" for. Wraps the moa…
Autonomous full-stack software factory. Spec-driven. Builds a working React + Node app from a single idea — constitution file, persistent spec, task breakdown, tests before code, REST API, seed data, and polished UI. Enforces Anti-Generic UI (references/ANTIGENERICUI.md): no default analytics card-dashboard shells…
Search Google Flights for cash prices, Google Hotels for accommodation, and Google Travel Explore for destination discovery. Use when comparing award flights vs pay-with-points portal pricing, searching hotels, or exploring travel options. Triggers on "cash price", "how much does the flight cost", "hotel search"…
Designs components and sections within an existing design system. Creates 3 composition variations that use the project's actual tokens, colors, typography, and component primitives. Use when user says "design a component", "component variations", "design a card", "design a hero", "design a section", "component…
A learning agent that teaches through questions, problems, and active recall — not lecturing — and verifies every claim against a cited knowledge base. Its method is drawn from the classical Islamic tradition of teaching.
A planning framework for turning a vague request for repeated automation into a self-running workflow, called a loop. It defines the goal, triggers, task roles, connections, saved state, checks, and safety rules before producing commands for Claude Code or Codex.
Multi-perspective cross review for product, design, and technical proposals. Reviews proposals from user, system, and cost perspectives using isolated reviewer roles. Works out of the box with zero configuration (single-model with sub-agent isolation). Optionally configure a second model (GPT, Claude, Gemini…
Complete workflow for AI agents using Chub: how to query docs efficiently and how to write structured annotations back to build persistent team knowledge.
A tool that turns an HTML page into one tall PDF page instead of several paginated sheets. It preserves the desktop layout, backgrounds, and selectable text by rendering the page and measuring its actual content height.
★not rated 11 3mo agoA98 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: