도구
등록된 모든 Skill, MCP 서버, CLI, 플러그인입니다. 유형, 직업, 태그로 필터링하거나 키워드로 검색할 수 있습니다.
직업: ML / AI +3
여러 개를 선택할 수 있습니다. 그중 하나에라도 맞는 리소스가 표시됩니다.
- ML / AI162
- Product / Projects246
- Hardware engineering17
- Customer support66
- Full-stack / Indie524
- Frontend447
- Backend408
- Mobile & desktop96
- Game development29
- QA101
- DevOps / SRE209
- Data engineering81
- Data analysis152
- GIS / Surveying12
- Security71
- Design239
- Architecture / Civil19
- Operations233
- Marketing & sales306
- Admin / Office240
- Writing / Content229
- Video / Media187
- HR88
- Legal94
- Finance / Accounting142
- Investing / Analysis104
- Teachers / Students212
- Research / Academia255
- Healthcare19
- Translation / L10n84
- Founders282
태그
여러 개를 선택할 수 있습니다. 선택한 태그를 모두 가진 리소스만 표시됩니다.
- python55
- anthropic51
- task-management51
- knowledge-base46
- customer-support39
- product-specs39
- agent-development36
- llm35
- market-research28
- user-research26
- data-analysis25
- diagrams24
- email-calendar24
- openai24
- ui-design24
- meeting-notes23
- skill-management23
- crm22
- dev-workflow22
- codex21
더 있습니다. 입력해서 찾아보세요.
469개

MCP Server Dev
PluginDesigns and builds MCP servers: first picks a deployment model among remote HTTP, MCPB bundles and local stdio, then guides tool design, auth and in-chat interactive components. Maintained by Anthropic.
anthropics/claude-plugins-official47.5k
Playground
PluginHas the agent build single-file HTML interactive playgrounds: visual controls on one side, live preview on the other, and a prompt to copy back into Claude. Templates for design tuning, data exploration, concept maps, doc annotation, code review and architecture diagrams. By Anthropic.
anthropics/claude-plugins-official47.5k
Session Report
PluginOfficial Anthropic plugin that reads local session logs in ~/.claude/projects and generates an interactive HTML usage report covering tokens, cache hit rate, subagents, skills and the most expensive prompts, with optimization tips. Needs Node.js.
anthropics/claude-plugins-official47.5k
Skill Creator
PluginCreates or improves Agent Skills from scratch: writes eval cases to test them, runs benchmarks with variance analysis, and tunes descriptions for more accurate triggering. Maintained by Anthropic.
anthropics/claude-plugins-official47.4k
project-artifact
PluginOfficial Anthropic plugin that builds a shareable status page for big multi-track projects such as migrations, launches or research: goals, workstream order, next steps and risks; say 'refresh' to update the same link. Needs a claude.ai login; Artifacts are a beta for Team and Enterprise plans.
anthropics/claude-plugins-official47.4k
Pyright LSP
PluginConnects Claude Code to the Pyright language server for static type checking and code intelligence in Python. Install pyright first with npm, pip or pipx. Official Anthropic plugin.
anthropics/claude-plugins-official47.4k
Asana
PluginOfficial Asana plugin in Claude's plugin marketplace: connects Claude Code to the Asana V2 MCP server to create and manage tasks, search projects, change assignees and track progress. Create your own Asana OAuth app first, then run /asana-setup after installing.
anthropics/claude-plugins-official47.4k
Claude Plugins Official
PluginAnthropic's official plugin marketplace, built into Claude Code by default, with 300+ official and partner plugins for development, security, design and office collaboration. Browse and install with /plugin.
anthropics/claude-plugins-official47.4k
aria2
CLILightweight multi-protocol command-line downloader that fetches in parallel segments from multiple sources over HTTP(S), FTP, SFTP, BitTorrent and Metalink. Resumes downloads, reads URLs in bulk from text files and offers a JSON-RPC interface for scripts or agents.
aria2/aria243.5k
Conductor
PluginContext-driven development plugin: first captures product vision, tech stack and workflow docs, then generates a spec and phased plan for each feature, executes with TDD and supports per-task rollback. Ported from Google's Conductor for Gemini CLI.
wshobson/agents42.6k
Customer Sales Automation
PluginSupport and sales plugin with two subagents: one handles support replies, ticket triage and help docs; the other writes cold email sequences, follow-up cadences, quote templates and objection handling. Prompts only; no direct CRM connection.
wshobson/agents42.6k
Business Analytics
PluginBusiness analytics plugin from the wshobson/agents marketplace: KPI dashboard design and data storytelling skills plus a business analyst subagent to choose metrics, plan dashboard layouts and turn data into reports executives or investors understand. Methods and templates only; no data connections.
wshobson/agents42.6k
Quantitative Trading
PluginQuant trading plugin from the wshobson/agents marketplace: quant analyst and risk manager subagents plus backtesting and risk metrics skills for strategy backtests, portfolio optimization and risk measures like VaR, Sharpe ratio and max drawdown. Needs local Python; not investment advice.
wshobson/agents42.6k
LLM Application Dev
PluginPlugin for building LLM apps: LangGraph agents with memory and tool use, hybrid-search RAG, vector index tuning, prompt optimization and LLM evaluation. Includes 3 subagents and 8 skills.
wshobson/agents42.6k
Machine Learning Ops
PluginMLOps plugin from the wshobson/agents marketplace: data scientist, ML engineer and MLOps engineer subagents and a /ml-pipeline command that runs the pipeline in phases from data analysis and training to deployment and monitoring, plus ML pipeline and recommender system skills.
wshobson/agents42.6k
Startup Business Analyst
PluginStartup business analysis plugin with 5 skills, 3 commands and a subagent: TAM/SAM/SOM market sizing, 3-5 year financial models, team and compensation planning and competitive landscape analysis, producing investor-ready business case documents.
wshobson/agents42.6k
Lightpanda Browser
CLIHeadless browser written from scratch in Zig for AI agents and automation, using less memory and running faster than headless Chrome in official benchmarks. fetch turns pages into Markdown, and it can serve CDP or MCP. Telemetry is on by default (an env var disables it); Windows needs WSL.
lightpanda-io/browser42.1k
prd
SkillWrites product requirement docs for software and AI features: first asks about the problem, success metrics and constraints, then outputs an executive summary, user stories, technical specs and risk analysis with measurable requirements. From GitHub's awesome-copilot community library.
github/awesome-copilot41.3k
Meeting Minutes
SkillMeeting minutes skill from GitHub's awesome-copilot: turns notes, transcripts or speech-to-text output into structured minutes with attendees, agenda, decisions and action items with owners and due dates, asking when details are missing. Best for internal meetings under an hour.
github/awesome-copilot41.2k
Breakdown Epic PM
SkillTurns a new epic idea into a PRD: problem and goals, personas, user journeys, functional and non-functional requirements, success metrics and out-of-scope items, asking questions when information is missing, saved as Markdown. From GitHub's awesome-copilot collection.
github/awesome-copilot41.2k
Marker
CLIConverts PDFs, images, PPTX, DOCX, XLSX, EPUB and more into Markdown, JSON or HTML, preserving tables, formulas and layout, with optional LLM help for higher accuracy. Needs Python 3.10+ and PyTorch; large-scale commercial use of the model weights needs a paid license.
datalab-to/marker40.9k
PostHog MCP
MCPPostHog's official hosted MCP: lets agents query product analytics with HogQL, manage feature flags and A/B experiments, and investigate errors and session replays. Sign in to PostHog to authorize; tool calls are free, though a few LLM-powered tools count toward AI usage.
PostHog/posthog40.8k
Find Skills
SkillWhen a user asks whether a skill exists for some task, searches the skills.sh ecosystem with the skills CLI, then recommends and installs a fit. Maintained by Vercel Labs and shipped in the skills CLI repo.
vercel-labs/skills39.7k
@agent-infra/mcp-server-browser
MCPBrowser automation MCP server open-sourced by ByteDance in the UI-TARS-desktop repo: drives pages through Puppeteer accessibility data with an optional vision mode, running locally over stdio or remotely over SSE or Streamable HTTP.
bytedance/UI-TARS-desktop39.6k