54 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
Zeige 54 Plugins, die diesen Filtern entsprechen.
claude-loresh008/claude-lore1
agent-ready-repoeugenelim/agent-ready-repo1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenManual-only skill for minimizing total codebase size. Only activate when explicitly requested. Measures success by final code amount.
Find similar implementations, usage examples, or existing patterns in the codebase. Provides concrete code examples based on what you're looking for.
CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and get synthesized answers to architectural questions. Includes a lightweight code exploration subagent, authentication hooks, and multiple search modes (fast lexical, semantic, and deep cross-cutting). Works standalone or alongside the CodeAlive MCP server for direct tool access via the Model Context Protocol.
Interactive AI teaching pipeline — /repo-to-course turns any codebase into a structured tutorial course (markdown, GitHub Pages site, or interactive HTML).
Persistent project knowledge base: STATE, ROADMAP, DECISIONS, LEARNINGS, JOURNAL under docs/lore/. A new session resumes from recorded state instead of re-reading the codebase.
productivityFind out what is actually true about your codebase before you change it. Index the repository once, then ask what calls this, what breaks if I change it, and which parts are load-bearing — answered from a resolved call graph that reports what it could not resolve, rather than a grep that quietly misses.
code-intelligenceAudits a repository through git history before reading source files
Security audit for codebases — threat modeling, vulnerability detection, compliance checking, and hardening recommendations
Plan features as PRPs (Product Requirements Prompts): implementation blueprints with requirements, codebase context and validation steps, then execute them
Explores a codebase for architectural friction through the lens of Ousterhout's deep-module principle (small interface, large implementation). Seven-step interactive workflow: an Explore sub-agent navigates the codebase organically — the friction it experiences IS the signal. Surfaces candidate clusters with coupling reasons, call patterns, shared types, dependency categories, and existing tests that a boundary test would replace. User picks what to explore, frames the problem, then 3–4 parallel sub-agents design competing deep-module interfaces. Chosen design becomes a structured RFC action file readable by GitHub MCP or ROVO (Jira) MCP. Use when the user says "arch review", "find shallow modules", "module depth", "deep module", "Ousterhout", "testability audit", "surface coupling", "design interfaces", "RFC issues", or "architectural friction".
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
Build deep architectural understanding through ultra-granular code analysis. Use when doing security audits, code reviews, or getting oriented in an unfamiliar codebase.
Transform project descriptions and feature requests into comprehensive specifications and actionable task lists. Use when the user wants to: (1) Create a specification from a project/feature description, (2) Generate a detailed plan with task breakdown, (3) Clarify requirements before implementation, (4) Convert ideas into structured development plans with progress tracking. Works with or without existing codebase files.
