Claude Code Skills Marketplace

A comprehensive system prompt that enforces TypeScript strict mode patterns. Prevents common type errors, ensures proper null handling, and generates clean, type-safe code. Works with Claude, ChatGPT, and Gemini.

A Model Context Protocol server that connects Claude Code to a PostgreSQL database. Exposes schema introspection, safe read queries, explain plans, and index suggestions as MCP tools. Write operations require explicit confirmation.

System prompt for security auditing code against OWASP Top 10 (2025), plus auth/authz review, secrets detection, dependency vulnerability check, and input validation analysis. Outputs findings with severity, exploit scenario, and fix.

A Claude Code skill for designing REST APIs — resource modeling, URL structure, HTTP method semantics, pagination, filtering, error responses, versioning, and OpenAPI spec generation. Forces contract-first design before implementation.

A Claude Code skill that enforces systematic debugging — reproduce the bug, form a hypothesis, isolate the cause, fix with minimal change, and verify the fix doesn't break anything else. Triggers on error messages, stack traces, and 'it's broken' statements.

MCP server connecting Claude Code to Linear. Read issues, create tasks from TODOs in code, update issue status during implementation, search the backlog, and sync sprint context — all from your coding session.

A complete Cursor rules bundle for backend engineers — REST API design, PostgreSQL with Drizzle ORM, authentication with JWT, input validation with Zod, error handling, logging, testing, and Docker deployment. 9 rule files covering the full backend stack.

A three-agent research team — a Researcher that gathers sources, a Fact-Checker that verifies claims, and a Synthesizer that produces the final report. Prevents the single-source problem and flags contradictions automatically.

A Claude Code skill for performance optimization — profiling before optimizing, identifying real bottlenecks, database query optimization, frontend bundle analysis, caching strategies, and the common premature optimizations to avoid.

MCP server that gives Claude Code access to Redis — key inspection, pattern scanning, memory analysis, TTL auditing, and slow log review. Safe by default: read-only mode unless explicitly unlocked.

MCP server connecting Claude Code to Slack. Read channels, search messages, post updates, thread replies, and manage incidents — all from your coding session. Uses Slack Bot Token with granular scopes.

A Claude Code skill for safe, behavior-preserving refactoring — extract function, simplify conditionals, remove duplication, decompose god objects, and untangle spaghetti. Requires passing tests before and after every change.

A two-agent team for Claude Code — a Developer agent that implements features, and a QA agent that immediately tests them. The QA agent writes tests, checks edge cases, runs accessibility audits, and files bugs before you ship. Coordinated handoff between agents.

Enhanced MCP server for Notion — semantic search across pages, database queries with filters, page creation with rich blocks, and knowledge retrieval for context-aware coding. Goes beyond the official Notion MCP with better search and structured data access.

A three-agent content pipeline — a Writer that drafts, an Editor that rewrites for clarity and impact, and an SEO Optimizer that handles meta tags, keywords, and structure. For blog posts, documentation, and marketing pages.

A complete Cursor rules bundle for React developers — React 19 patterns, Next.js 16 App Router, TypeScript strict mode, Tailwind CSS v4, testing with Vitest, and accessibility. 8 rule files that work together as a coherent system.

A Claude Code skill for generating high-quality tests — behavior-driven test structure, edge case discovery, mock strategy, and the test patterns that actually catch bugs. Supports Vitest, Jest, pytest, and Go testing.

System prompt that analyzes a codebase's architecture — dependency graph health, separation of concerns, coupling hotspots, scalability constraints, and concrete recommendations. Not abstract advice — specific to the code it reads.

An AI agent blueprint for automated security auditing. Scans codebases for OWASP Top 10 vulnerabilities, generates reports with severity ratings, and suggests fixes. Designed for CI/CD integration.