Use this agent when you need to implement features based on detailed specifications (PRD, ADR, UI/UX briefs). This agent excels at translating comprehensive design documents into production-ready code while maintaining strict adherence to architectural patterns and best practices. <example> Context: The user has a set of design documents and needs to implement a new feature. user: "I have a PRD for a user profile feature, an ADR defining our microservices architecture, and UI/UX mockups. Please implement the profile management functionality." assistant: "I'll use the coder agent to implement this feature based on your specifications." <commentary> Since the user has detailed specifications that need to be translated into code, use the coder agent to ensure proper implementation following all design documents. </commentary> </example> <example> Context: The user needs to implement a feature with strict architectural requirements. user: "Here's the specification for our new payment processing module. It needs to follow our layered architecture with proper separation of concerns." assistant: "Let me use the coder agent to implement this payment module according to your specifications and architectural requirements." <commentary> The user has specifications that require careful adherence to architectural patterns, making this a perfect use case for the coder agent. </commentary> </example>
Developer Experience specialist focused on eliminating friction and maximizing team velocity. Expert in modern tooling, AI-assisted development, cloud IDEs, and workflow automation. Use proactively for project setup, onboarding optimization, CI/CD enhancement, or when development friction is detected. Specializes in measuring and improving developer productivity metrics.
Use this agent when you need to evaluate SDK design decisions, review SDK code for developer experience issues, assess API usability, or make architectural decisions that impact SDK consumers. This agent should be consulted before finalizing public APIs, when refactoring SDK interfaces, or when resolving tensions between implementation complexity and user simplicity. Examples: <example> Context: The user is building an SDK and needs to review a newly designed API interface. user: "I've created a new authentication module for our SDK. Can you review it?" assistant: "I'll use the dx-sdk-advocate agent to review this authentication module from a developer experience perspective." <commentary> Since this involves SDK API design, the dx-sdk-advocate agent should evaluate the interface for usability, consistency, and developer ergonomics. </commentary> </example> <example> Context: The user is debating between two implementation approaches for an SDK feature. user: "Should we use a builder pattern or configuration object for initializing the client?" assistant: "Let me consult the dx-sdk-advocate agent to evaluate both approaches from a DX perspective." <commentary> This is a design decision that directly impacts SDK usability, so the dx-sdk-advocate agent should analyze the trade-offs. </commentary> </example> <example> Context: The user has written SDK documentation and wants feedback. user: "Here's the getting started guide for our new SDK version." assistant: "I'll have the dx-sdk-advocate agent review this documentation to ensure it provides an excellent onboarding experience." <commentary> Documentation is crucial for SDK developer experience, so the dx-sdk-advocate agent should assess clarity and completeness. </commentary> </example>
Use this agent when you need to create or improve README documentation for open source projects, libraries, or developer tools. This agent specializes in crafting engaging, developer-focused documentation that balances professionalism with authenticity, avoiding marketing fluff while maximizing clarity and adoption potential. Examples: <example>Context: User has just finished building a new TypeScript library and needs comprehensive documentation. user: "I just built a new state management library for React. Can you help me write a README that will get developers excited about using it?" assistant: "I'll use the readme-writer agent to create compelling documentation that showcases your library's value proposition and technical details." <commentary>The user needs professional README documentation for a developer tool, which is exactly what this agent specializes in.</commentary></example> <example>Context: User's existing README feels too corporate and isn't getting traction. user: "My project's README sounds like corporate marketing copy. I need something that feels more authentic and developer-friendly." assistant: "Let me use the readme-writer agent to rewrite this with a more authentic, story-driven approach that resonates with developers." <commentary>This agent excels at transforming corporate-sounding documentation into engaging, authentic content that developers actually want to read.</commentary></example>
Security specialist focusing on OWASP compliance, vulnerability assessment, secure coding practices, and threat modeling
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
My personal collection of Claude Code plugins.
Add this marketplace to Claude Code:
/plugin marketplace add tinetti/claude-plugins
Then install plugins:
/plugin install consultant@tinetti
This repo is also a Pi package. Install it directly:
pi install git:github.com/tinetti/claude-plugins
# or, while developing locally:
pi install /Users/jtinetti/Developer/claude-plugins
The Pi package loads the same plugins/*/skills and plugins/*/commands files, plus pi/extensions/claude-compat.ts for Claude Code compatibility shims like AskUserQuestion, WebFetch, WebSearch, TodoWrite, and file-backed task tools.
For skills that rely on Claude Code's Task/Agent subagent workflow, install pi-subagents once:
pi install npm:pi-subagents
This repo does not load pi-subagents directly because Pi currently errors when the same extension/tool is loaded twice, and many Pi setups already have pi-subagents installed globally.
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
plugins/your-plugin/.claude-plugin/plugin.json with metadatapnpm-workspace.yaml and root tsconfig.jsonpnpm run sync to auto-discover and add to marketplaceThe 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.
Forked from nicknisi/claude-plugins by Nick Nisi.
MIT
npx claudepluginhub tinetti/claude-plugins --plugin developer-experienceTransform brain dumps into implementation specs through an evidence-gated interview stress-tested by adversarial plan critics. Interactive HTML contract for planning decisions, Markdown specs for execution. /ideation:autopilot runs all phases on a deterministic workflow engine with overlap-serialized parallel waves; /ideation:retro mines implementation notes into learnings future interviews read.
Experimental agents, skills, and output styles for unconventional interaction patterns
Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2. Supports 1K/2K/4K resolution and masked inpainting.
Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Park tangents as side quests with full resurrection context — writes a handoff doc to the Obsidian vault and creates a linked OmniFocus task
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC plugin for engineering teams - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.