5,123 boosters — open source, verified from GitHub, ready to install
"description": "Use Claude Code As Is - native plugin leveraging built-in architecture", "keywords": ["workflow", "agents", "hooks", "native"],
A testing framework for Model Context Protocol (MCP) servers with CLI tools and dual transport support (SSE/stdio). Developers building or integrating MCP servers can use this to validate their implementations against protocol standards.
A Windsurf-optimized development ruleset for building particle systems with Three.js, TypeScript, and WebGL. Ideal for developers creating interactive 3D visualizations who need clear coding standards and best practices.
"name": "learnship", "description": "Agentic engineering done right — 49 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.", "name": "Favio Vazquez",
Generate text files and export to PNG/SVG/PDF using (local) or Kroki API (no install). 1. Check deps — try , fallback to Kroki if unavailable 2. Pick diagram type — choose from table below
"description": "AI-assisted spec crafting through research, interviews, and multi-LLM review. Like Geppetto carved Pinocchio from wood, transform rough ideas into living implementation plans.", "name": "Leonardo Flores", "url": "https://github.com/leonardocouy"
Heuristic scoring (no AI key configured).
"name": "claude-code-toolkit", "name": "Scott Spence" "description": "Productivity and ecosystem tools for Claude Code",
Use when organizing media files (movies, TV, anime) on NAS or local storage - cleaning junk files, merging scattered episodes, normalizing folder names to "Title (Year)" format, and verifying episode completeness against TMDB
A parent skill providing code quality assurance strategies that integrates security reviews and systematic debugging for AI-assisted coding agents. Developers using Claude Code will benefit from structured approaches to identifying and fixing code quality, security, and reliability issues.
"name": "context-provider", "description": "MCP context & instinct engine — learned rules from sessions with confidence scoring. Provides tool-aware context injection and 6 MCP tools.", "version": "2.0.0-alpha.4",
Rails Upgrade Assistant intelligently guides developers through Rails application upgrades from 7.0 to 8.1.1 by identifying breaking changes, deprecations, and providing step-by-step migration instructions. Essential for teams maintaining Rails applications and planning version transitions.
A Claude Code skill that converts PDFs to Markdown format, supporting large files and Korean paths while avoiding common encoding issues. Developers working with PDF processing in coding tasks benefit from this automation.
You are a writing editor that strips AI-isms from Malaysian Bahasa Melayu writing. Content AI dalam BM ada "accent" sendiri, yang pembaca Malaysia boleh spot dalam 3 saat je. Kerja kau, buang accent tu, supaya tulisan bunyi macam manusia Malaysia betul-betul tulis, bukan bot. Detect the language of
"name": "react-native-preflight", "description": "Maestro E2E testing for React Native — isolated screens, dev catalog, visual regression",
CortexGraph is a temporal memory system for AI assistants that implements human-like forgetting curves using local storage (JSONL and Markdown), enabling natural conversation memory across Claude, Cursor, and other platforms without explicit save commands.
kube-audit-kit is a read-only Kubernetes security auditing skill that exports cluster resources, sanitizes metadata, and generates PSS/NSA-compliant audit reports. DevOps engineers and security teams use it to perform compliance reviews and identify security misconfigurations without cluster modification.
Automates configuration of container image registries (ghcr.io, Docker Hub, Harbor) with vulnerability scanning, image signing, and retention policies for secure CI/CD pipelines. Essential for DevOps engineers and platform teams managing containerized applications at scale.
<!-- AIOS-GENERATED: orchestrator-agents v1 --> Role: security-reviewer You are the Security Reviewer. Review auth, data handling, secrets, injection risks, and unsafe automation. Do not modify code; report security findings and mitigations.
You are a naming strategist. You help users create memorable, meaningful names for products, SaaS tools, brands, projects, open source libraries, and anything else that needs a name. Your approach is metaphor-driven, not thesaurus-driven. Great names tell compressed stories. They plant concrete imag
Alexi is an expropriation appraisal specialist that provides expert-level valuation analysis using before/after methods, comparable sales, and severance damage assessment for legal and real estate professionals. Real estate appraisers, lawyers, and property valuators benefit from delegating complex expropriation cases to this specialized agent.
<!-- 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": "context-cascade", "description": "Context-saving nested plugin architecture for Claude Code. Playbooks contain skills, skills contain agents, agents contain commands. Only load what you need - context cascades down through layers on demand, saving 90%+ context space. Includes 224 agents, 17
