Best Claude Code AI Skills & MCP Servers

Turn editor chat history (Cursor, Claude Code, Windsurf, Copilot) into typed Markdown decisions + AGENTS.md rules — local-first, git-trackable, zero remember() calls.

Stops Claude Code from skipping research, claiming 'done' without verifying, and repeating yesterday's mistakes. The 7 Laws of AI Agent Discipline — 13 enforcement skills, gating hooks, the Mulahazah auto-leveling instinct engine, and a GitHub Action tran

Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.

Scaffold a Tap v2 browser-automation plan in seconds. `npx create-tap-script <site>/<name>` generates a deterministic .plan.json that runs at zero LLM tokens in Claude Code, Cursor, and any MCP host.

Orchestration + observability + coach layer for Claude Code token optimization. Measures tool usage, enforces budgets, advises on complementary tools (serena, RTK), and proactively surfaces savings tips.

The official Barker stablecoin yield skill suite — real-time data from 500+ DeFi protocols and 20+ CEX. Skill installer for Claude Code / OKX Plugin Store + a stdio MCP server wrapping the Barker public API.

Model Context Protocol server for Gradus Notation API. Lets AI agents render music notation, validate input, and search music-theory knowledge — sponsored by Gradus School of Music Composition.

Convert Playwright scripts into Tap v2 plans. Compile .spec.ts / .test.ts files into deterministic v2 Plan JSON that runs at zero LLM tokens in Claude Code, Cursor, and any MCP host.

MCP server for retrieving YouTube video transcripts for Claude Code

MCP server for delegating tasks to specialized AI assistants in Cursor and other tools

Dokploy MCP server for Codex, Cursor, and Claude with compact stdio and hosted HTTP modes

Persistent memory + FTS5 search for Claude Code conversations. MCP server exposes your ~/.claude/projects/ history as queryable memory for any MCP-compatible AI agent.

MCP Server for Claude Code Session Insight — structured data extraction, git log collection, and LLM synthesis guidance

Local MCP credential broker for coding agents (Claude Code, Codex, Gemini, and any other MCP-stdio client). Values never enter the AI transcript — the agent requests secrets through a schema, a localhost form lets you type them, and they land in Vault, .e

Trust-score any AI skill or MCP server from inside Claude Code, Cursor, or any MCP client. Accepts GitHub repos, npm packages, Smithery URLs, and OpenClaw skills. 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence), safety scanning, OpenClaw frontm

Turn Claude research output into designed PDFs. Cover page, table of contents, code blocks that hold across pages. MCP server and Claude Code skill for markdown to PDF.

A2ABench MCP server for public agent Q&A benchmarking: list questions, submit runs, and fetch leaderboard scores.

PR Worlds — the CLI and MCP server that gives your repo coherent, reproducible worlds your agent can open, replay, and inhabit. v0.2 ships the coherence resolver: agents see the plan's confidence, evidence, and explicit unknowns before the world is materi

Compile your Markdown vault into a portable agent memory. One build, every agent: Claude, Codex, Cursor, MCP, llms.txt.

Context governor and between-commit activity surface for coding agents

MCP server for Gandi LiveDNS — manage DNS records, domains, and zone snapshots from Claude Code or any MCP client.

Cross-Code Organizer (CCO, formerly Claude Code Organizer) — manage AI coding tool configs across Claude Code, Codex CLI, and more. Memories, skills, MCP servers, commands, agents, rules, and hooks across global and project scopes

AI-powered idea & task manager for developers. Brainstorm → structured tasks → AI agent execution. CodeMirror editor with slash commands, MCP Server, Claude/Gemini/Codex support. Local-first SQLite, cross-PC Git sync.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.