1,359 boosters for "AI" — open source, verified from GitHub, ready to install
"name": "claude-consensus", "name": "Altimate AI", "email": "support@altimate.ai"
A comprehensive coding standards guide for Windsurf that covers style, naming conventions, architecture patterns, and tech stack best practices (Next.js, TypeScript, Tailwind, React Query). Ideal for teams and educational platforms training developers to write consistent, maintainable code.
"name": "mountaineering-skills", "description": "Automated mountain route research combining PeakBagger data, weather forecasts, avalanche conditions, and trip reports into comprehensive beta documents", "name": "dreamiurg",
"name": "depwire-cli", "description": "Code cross-reference visualization and AI context engine for TypeScript, JavaScript, Python, Go, Rust, and C. Zero native dependencies — works on Windows, macOS, and Linux.", "depwire": "dist/index.js"
A comprehensive tutorial chapter teaching developers how to build and deploy intelligent AI agents with tool use and automation capabilities in AnythingLLM. Ideal for engineers looking to add autonomous workflows and function-calling to their self-hosted RAG systems.
ultraplan is a CLI tool that records multi-modal context (audio, screenshots, clipboard, keystrokes) from work sessions and converts them into detailed prompts for Claude analysis. Developers and researchers benefit by capturing complete context from meetings, debugging, or research workflows for later AI-assisted analysis.
Enables Claude to maintain long-term memory across sessions, automatically recalling user context, preferences, and prior work to provide continuous, personalized assistance. Essential for developers who need stateful AI interactions across multiple conversations.
Cursor rules for Convex best practices, providing guidelines for database schema design, queries, mutations, and function syntax in TypeScript/JavaScript projects. Useful for developers building Convex backends who want AI-assisted code review within Cursor.
"name": "autonomous-agent", "version": "7.19.0", "description": "Revolutionary four-tier agent architecture with 35 specialized agents, 24 skills, and 40 commands focused on autonomous development, code quality, and validation. Strategic Analysis & Intelligence (Group 1) analyzes and recommends, Dec
You are the STUCK AGENT - the MANDATORY human escalation point for the entire system. You are the ONLY agent authorized to use AskUserQuestion. When ANY other agent encounters ANY problem, they MUST invoke you. You are invoked when:
Heuristic scoring (no AI key configured).
"version": "0.1.68", "description": "Agent work marketplace — train your agent, let it work for others", "url": "https://github.com/lhead/akemon"
"version": "0.14.4", "description": "Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions and surfaces them when relevant.", "name": "Robert Allen",
"name": "norman-finance", "description": "AI-powered bookkeeping and tax filing automation for entrepreneurs at the heart of the European economy. Connect to Norman to manage clients, invoices, transactions, taxes, and documents.", "name": "Norman Finance",
You are a content optimization agent using , a deterministic linter with 92 rules. Your job is to validate and fix content files so they are optimized for both traditional SEO and AI search engine citation (GEO).
Reviews email content before sending and provides a comprehensive quality score (0-100) across 5 weighted dimensions. Identifies critical issues, suggests improvements, and provides a rewritten version for low-scoring emails. Accept email content in any of these formats: 1. Pasted text - Subject lin
This sub-skill handles intelligent inbox triage by connecting to Gmail or Outlook via MCP, analyzing unread emails, scoring them by importance, categorizing them, and generating reply suggestions for high-priority items. Check which MCP tools are available: Prefer Gmail if both are available (better
An adversarial validation agent that challenges expertise claims and mental models to prevent overconfident reasoning. Useful for researchers, engineers, and decision-makers who need rigorous validation of their assumptions.
This sub-skill generates a complete email marketing strategy tailored to your business type, including: Invoked by from the main email skill. First, check if exists and contains business type. If not, analyze context signals:
Spotdb is an ephemeral data sandbox for AI workflows that provides secure, isolated database environments for agentic AI systems. It's useful for developers building AI agents and LLM applications that need safe data isolation and guardrails.
A Claude agent designed to guide ML model training workflows with library-first principles, helping developers reuse existing components and patterns. Useful for teams building AI/ML solutions who want standardized, reusable training processes.
当用户对已有导师 Skill 说以下内容时，进入进化模式： 本 Skill 运行在 Claude Code 环境，使用以下工具： 1. 不主动给出学术不端建议：不伪造数据、不抄袭、不代写造假
An AI-powered code review agent that automatically analyzes code changes for quality, security, and maintainability issues, providing prioritized feedback with specific fixes. Ideal for developers seeking proactive code quality assurance and security vetting in their workflows.
"name": "cc-godmode", "description": "Self-orchestrating multi-agent development system — 8 specialized AI agents, parallel quality gates, and automated workflows. You say WHAT, the AI decides HOW.", "name": "Dennis Westermann",
