3,583 skills. One install layer.

MCP server for Kai — semantic code intelligence for AI coding assistants

Hud MCP

Connect Claude Code sessions across projects via shared context bundles

A terminal coding agent powered by Kimi K2.6, routed through your own Cloudflare AI Gateway — per-request logs, response caching, authoritative cost. Web search, GitHub, headless browser, LSP, MCP, local memory, 262k context.

Model Context Protocol server for wcagcheckr. Lets LLM-IDEs (Claude Code, Cursor, Continue, etc.) drive accessibility audits, verify forensic receipts, and look up tier features programmatically. Same audit engine as the Chrome extension and CI runner.

MCP server that exposes terminal pilot automation as tools.

Knip MCP Server

MCP server for Calcis: LLM cost estimation for AI agents

MCP server for atrib. The producer-side cognitive primitive: lets agents sign explicit observations, annotations, and revisions beyond what middleware auto-signs.

Knowledge graph builder — construct a graph of code entities (files, functions, types) and their relationships.

TiDB MCP Server - 统一权限控制

Structured planning — create plans with steps, dependencies, and time estimates.

MCP server for AG-Grid to help developers integrate AG Grid into their applications

Structured multi-perspective debate — define positions, score arguments, find consensus, summarize.

Production-parity MCP server for the findtime.io Time API

Diagram generation — produce Mermaid, DOT/Graphviz, and ASCII diagrams from data.

MCP Server for Regle

Knowledge graph query — find nodes, traverse neighbors, find paths, filter by type.

Multi-language tree-sitter parser — supports ~50 languages including TypeScript, Python, PHP, Go, Rust, HTML, YAML, JSON, Markdown, Twig, SCSS, etc.

Versioned context store with hybrid search for AI agents. Stdio + HTTP MCP server and CLI.

Conformance test runner for FocusMCP bricks — validates manifests, tool schemas, and runtime behavior.

A testing utility for Model Context Protocol (MCP) servers

Structured reasoning chains — think step by step, branch alternatives, revise conclusions, summarize.

Shared state for multi-agent — share context, files, results between agents, broadcast messages.