Claude Code 플러그인
공개 Claude Code 마켓플레이스의 플러그인 6,108개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
공개 Claude Code 마켓플레이스의 플러그인 6,108개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출Deep-reading assistant: five modes (quick / deep / knowledge-map / Feynman / book) to extract claims, arguments and evidence.
productivityreveal.js HTML 簡報製作、QA、講義 PPTX/PDF 與特效的兩個 skill
Microsoft 365, Intune, and Entra admin skills with Greybeard MCP server wiring.
2 AI engineering skills: LLM evals and LLM observability
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.
Create new agent skills from scratch, modify and improve existing skills, and measure skill performance through evaluation and benchmarking. Use when users want to create a skill, write a skill, build a new skill, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance, or optimize a skill's description for better triggering accuracy. Also triggers when users say "turn this into a skill", "make a skill for X", "skill for doing Y", or ask about skill structure, skill format, or SKILL.md files.
SolidJS 2.0 skills: write, migrate, and review solid-js 2.x code without React/1.x reflexes
An AI interviewer for YOUR project. Reads your repo and your Claude Code session logs, then grills you on every decision until you can defend it cold.
Catch AI-fabricated citations: verifyCitation cross-checks a claimed title against the real record at its identifier, detecting the dominant real-DOI + invented-title pattern (Topaz et al., Lancet 2026) that simple DOI resolution cannot catch. Also checks retraction and open-access status, and resolves eight identifier types (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.
Measure fast radio bursts with FLITS instead of writing dedispersion and measurement code by hand
Turn a brand name, industry, or reference image into a professional AI logo, brand mark, or app icon with multi-concept exploration, precise brand colors, and scalable composition.
Finish authorized, non-trivial AI agent work with direct, scope-matched evidence.
Rebuild scanned pages as searchable, newly typeset PDFs with vector diagrams, checked page by page against the scan.
productivityA skill that helps coding agents challenge assumptions and agree on scope before implementation.
Checks whether public GitHub projects already do what you are about to build, and gives a verdict: reuse, adapt, use as a base, or build.
Financial data and research MCP for US, China and Japan equities: filings with full-text and fact search, statements as reported, earnings, ownership, corporate events, executives, analyst data, company discovery and research signals. Every figure traced to its filing.
dataBackground Windows desktop for AI agents: native GUI automation, screenshots and app testing.
developmentAuthenticate with InFlow, inspect balances and deposit addresses, and perform agent-native payments via x402 and MPP.
financeFast council: three independent members down different reasoning paths, one synthesis check, chairman decision memo with preserved counter-position.
productivityOutbound skill plus an MCP connection to your OpenOutbound engine: find and research leads, watch signals, run email and LinkedIn campaigns, triage replies, get reports.
productivity