666 boosters for "code" — open source, verified from GitHub, ready to install
"name": "manim-skill", "description": "Claude Code Skill for creating mathematical animations using Manim Community Edition. Plan, code, render, and iterate on 3Blue1Brown-style videos.", "name": "Yusuke Miyashita"
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Implementer. Own code changes inside the agreed file scope and report concrete results. Prefer minimal diffs and include verification evidence. Output a single JSON object (no surrounding text) that conforms to .
"name": "abiswas97-gemini", "description": "Gemini plugin for Claude Code — code reviews and task delegation via the Gemini CLI.", "description": "Use Gemini CLI from Claude Code for code reviews and task delegation.",
"name": "cc-skills", "version": "12.24.3", "description": "Claude Code Skills Marketplace: Meta-skills and foundational tools for Claude Code",
"name": "futuresearch", "description": "Give Claude Code a research team. Forecast, score, classify, or research every row of a dataset.", "name": "FutureSearch"
"schemaVersion": "1.0", "name": "slidev-dev-marketplace", "description": "Evidence-based presentation creation with Slidev, enforced design guardrails, and multi-platform diagrams",
"name": "aviz-skills-library", "url": "https://github.com/aviz85" "name": "aviz-skills-installer",
A skill booster that teaches developers to understand code by breaking it down line-by-line with context about purpose, problem-solving, and reasoning. Useful for learners, code reviewers, and anyone onboarding to unfamiliar codebases.
"name": "frontend-dev", "description": "Automatic closed-loop frontend development with visual testing, browser automation, and iterative refinement using multimodal AI", "name": "hemangjoshi37a",
"description": "VibeSurf integration - Control browsers, automate workflows, execute AI skills (search/crawl/js_code/summary), use Composio integrations (Gmail/GitHub/Slack), and run pre-built workflows", "name": "VibeSurf Community" "homepage": "https://github.com/vibesurf-ai/claude-surf",
"description": "WozCode enhanced coding tools — smart search, batch editing, SQL introspection, and cost-optimized subagent delegation", "version": "0.3.18", "homepage": "https://withwoz.com"
"description": "Cotask — task management with TASKS.md kanban dashboard", "homepage": "https://github.com/wbopan/cotask", "repository": "https://github.com/wbopan/cotask",
Enables developers and legal professionals to formalize contracts, regulations, and compliance logic as executable, type-checked code using L4, a functional programming language for computational law. Users benefit from automated validation, web app generation, and formal verification of legal rules.
"name": "claude-consensus", "name": "Altimate AI", "email": "support@altimate.ai"
"name": "readwise-skill", "description": "Claude Code plugin for Readwise workflows", "homepage": "https://github.com/ryanlyn/readwise-skill",
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.
The implement booster activates specialized AI personas (architect, frontend, backend, security, QA) to coordinate feature and code implementation with framework-specific best practices and MCP tool integration. It's designed for developers needing structured, multi-domain implementation workflows in Claude Code.
"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
Reference documentation for building Prismatic Code Native Integrations (CNI). Do NOT use these MCP tools — they return incomplete data that causes broken scaffolds and missing connections downstream. A hook will deny them, but avoid the wasted round trip. All components are accessed via manifests:
You are the CODER - the implementation specialist who turns requirements into working code. Take a SINGLE, SPECIFIC todo item and implement it COMPLETELY and CORRECTLY. 1. Understand the Task
Reference documentation for building Prismatic custom components. Do NOT use these MCP tools — they return incomplete data that causes broken scaffolds and missing connections downstream. A hook will deny them, but avoid the wasted round trip. Components define their own inputs — not wrappers. Each
You are the TESTER - the visual QA specialist who SEES and VERIFIES implementations using Playwright MCP. Test implementations by ACTUALLY RENDERING AND VIEWING them using Playwright MCP - not just checking code! 1. Understand What Was Built
"description": "Zeabur CLI skills for deployment, template management, and troubleshooting", "version": "1.16.1", "repository": "https://github.com/zeabur/zeabur-claude-plugin",
An autonomous coding agent that delegates tasks to Codex CLI with configurable risk modes (full-auto, sandbox, YOLO) to iteratively debug and test code until it passes. Developers building automated code generation and testing pipelines benefit most from this booster.
