💡 Summary
A collection of plugins for Claude Code enhancing AI consultation, content creation, and developer experience.
🎯 Target Audience
🤖 AI Roast: “Powerful, but the setup might scare off the impatient.”
Risk: Medium. Review: shell/CLI command execution; filesystem read/write scope and path traversal. Run with least privilege and audit before enabling in production.
Claude Plugins
My personal collection of Claude Code plugins.
Using this marketplace
Add this marketplace to Claude Code:
/plugin marketplace add nicknisi/claude-plugins
Then install plugins:
/plugin install consultant@nicknisi
Plugins
- consultant - Multi-model AI consultation and research with GPT-5/Codex, Gemini, Grok, Perplexity, and Claude (supports both single-agent consultation and parallel multi-agent research)
- content - Tools for bootstrapping content creation
- developer-experience - Tools for the experienced developer experience engineer
- essentials - Core productivity tools and workflows for Claude Code
- ideation - Transform brain dumps into structured contracts, phased PRDs, and implementation specs
- meta - Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
- sandbox - Experimental agents, skills, and output styles for unconventional interaction patterns
- spec-driven - Transform specifications into executable code with validation-driven development
- workos - Enterprise authentication and SSO integration toolkit
Development
This is a pnpm workspace with TypeScript project references.
# Install dependencies pnpm install # Type check everything pnpm run typecheck # Build all MCP servers pnpm run build # Build and sync marketplace metadata pnpm run build:all
Adding a new plugin
- Create
plugins/your-plugin/.claude-plugin/plugin.jsonwith metadata - Add components: agents, commands, skills, or MCP servers
- If adding an MCP server, update
pnpm-workspace.yamland roottsconfig.json - Run
pnpm run syncto auto-discover and add to marketplace
The sync script scans plugins/ and automatically discovers all plugins with valid plugin.json files. Add a plugin directory and it shows up. Remove one and it disappears.
License
MIT
Pros
- Diverse range of plugins for various needs
- Supports multi-agent research and consultation
- Easy installation and integration
- Active development and maintenance
Cons
- Documentation could be more detailed
- Limited examples of plugin usage
- Dependency on pnpm may deter some users
- Potential learning curve for new users
Related Skills
pytorch
S“It's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.”
agno
S“It promises to be the Kubernetes for agents, but let's see if developers have the patience to learn yet another orchestration layer.”
nuxt-skills
S“It's essentially a well-organized cheat sheet that turns your AI assistant into a Nuxt framework parrot.”
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author nicknisi.
