Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 374,720 indexed, measured the same four ways as everything else here.
MCP server Claude CodeCodexCursor +2
Comprehensive Windows AutoCAD MCP server with 300+ specialized tools for handle-first drawing, editing, understanding, validation, visual grounding, plotting, and guarded CAD automation. Runs locally from the best-cad-mcp Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Control Ableton Live 11/12 with 154 typed MCP tools for MIDI, devices, arrangement, mixing, automation, and offline .als analysis. Runs locally from the mcp-server-ableton-live Python package.
Skill Claude CodeCodex
Drive the WeftCut video editor over its MCP tools. Use BEFORE calling any weftcut MCP tool — when the user wants to edit video in WeftCut (cut, trim, arrange a timeline, add captions or voiceover) or author/update a Motif (animated overlay).
MCP server Claude CodeCodexCursor +2
A local MCP server for creating and managing OpenSpec projects without using command-line commands. OpenSpec is the project-management system supported by this server.
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "specmatic" as configured in jmanhype/speckit. Runs locally from the @specmatic/mcp npm package. Needs 1 environment variable to run.
jpiece3/lead-magnet-quiz-workflow
Skill Claude CodeCodex
Create distinctive visual specifications for the lead magnet funnel that match the brand's visual personality. Output design tokens, component variants, and implementation guidance that produces visually unique quiz experiences.
dyeoman2/tanstack-start-template
Command Claude CodeCursor
This guide demonstrates proper ShadCN form implementation using @tanstack/react-form with the October 2025 component suite (Field, InputGroup, etc.).
ostikwhy-blip/claude-code-handoff-skill
Skill Claude CodeCodex
Use when ending or pausing a Claude Code session whose work must continue in a fresh session — user says "create a handoff", "write a handoff", "I'm ending this session", "prepare for a fresh session", "hand this off", or "/handoff" — or when starting a session in a project that already contains a HANDOFF.md at the…
Skill Claude CodeCodex
Run diagnostic scripts in sandbox with human approval (MCP tool).
robertbstillwell/marketing-skills
Skill Claude Code
Send messages and interactive cards to Feishu (飞书) and Lark channels via webhooks or Bot API. Create rich-text announcements, marketing updates, and team notifications. Trigger phrases: "post to feishu", "feishu message", "lark message", "feishu webhook", "lark webhook", "send to feishu", "send to lark", "feishu bot"…
Cursor rule Claude CodeCursor
Mandatory agent delegation, skill loading, and sub-agent usage directives for ALL tasks in ALL contexts.
Agent Claude Code
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Skill Claude CodeCodex
The framework's single design engine: craft-first selection of an intentional visual direction, a stable token system, and UI continuity across screens. A blank designskill resolves to it; only a project-forged skill (site-forge or hybrid output) that designskill names explicitly replaces it. Never combined with…
MonumentalSystems/Atlas-Agent-Teams
Plugin Claude Code
Bundles 4 skills, 1 command · 0 tokens together
Specialized team for building generative UI applications with Vercel, Next.js, AI SDK, and AI Elements.
Skill Claude CodeCodex
Robinhood Chain research desk — buy-the-dip, high-PnL wallet buys, honeypot filter. RH only, research only.
Plugin Claude Code
Bundles 1 skill, 3 hooks, 1 MCP server · 36 tokens together
Compile provenance-backed context and enforce verified Change Bundles for each behavior-bearing logic unit.
Skill Claude CodeCodex
Use when a task spans multiple steps, files, or unknowns — before planning the order of work, whenever about to report completion or success in any wording, and when picking the next action after a result, failure, or surprise. Also under deadline pressure, or when resuming work built on questionable foundations.
MCP server Claude CodeCodexCursor +2
MCP server "Teamwork", hosted remotely at mcp.ai.teamwork.com, as configured in Teamwork/mcp.
Skill Claude CodeCodex
How to work inside an ai-pod container — running commands on the host and adjusting the container environment.
Skill Claude CodeCodex
Reviews pull requests with upfront, severity-ranked findings and guides a human reviewer through context, code, and manual test cases. Use for PR reviews, merge assessments, or reviewer test preparation.
Intersect-Collaborations-LLC/research-workflow-assistant
MCP server Claude CodeCodexCursor +2
One of 12 in mcp.json
MCP server "prisma-tracker" as configured in Intersect-Collaborations-LLC/research-workflow-assistant. Runs prisma_tracker with ${workspaceFolder}/.venv/Scripts/python. Needs 2 environment variables to run.
Skill Claude CodeCodex
Backstage patterns: Software Catalog (catalog-info.yaml, kinds, relations, lifecycle), TechDocs (MkDocs, techdocs-cli), Scaffolder templates (CSF3, steps, fetch:template, publish:github), custom plugins (frontend React, backend Express), GitHub App integration, and Chromatic CI.
Plugin Claude Code
Bundles 5 skills, 2 MCP servers · 166 tokens together
Prospect, enrich leads, load outreach sequences, and query sales analytics with Apollo.io — one-click MCP server integration for Claude Code and Cowork.
Skill Claude CodeCodex
Borrow from Aave V3 via credit delegation. Agent draws against delegator collateral. Supports borrow, repay, health checks.
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: