Cursor インストールガイド

開発者向け MCP サーバーとよく使われる AI コードエディタ。

10713件

MCP Servers

5380 件

Agent Skills

5333 件
RG
rimagination/good-story
Developer tools

good-story 是一个给科研写作用的 agent skill。它帮你把手里的结果、图表和草稿,整理成一个证据站得住、读者听得懂、审稿人也挑不散的论文故事。

10570
RB
reliefeai/browser-relay
Developer tools

Let AI agents use the same Chrome browser you use every day.

12370
DD
dr-dumpling/paper-search-cli
Developer tools

Paper Search CLI is an agent-facing Skill + CLI package built on a standalone Node.js command line tool for academic literature work.

12770
ST
sablin39/tilelang-cuda-skills
Productivity workflow

Agent skills for GPU kernel development — writing, debugging, profiling, and optimizing CUDA and TileLang GPU kernels.

13370
RF
ricardoherediaj/football-analytics-tutorials
Developer tools

Professional post-match team reports from — a clean Python package + an agent skill, built on the Post-Match-Report-2.0 blueprint.

11570
TA
toseaai/awesome-html-slide-skills
Developer tools

The definitive list of agent skills and template libraries for generating beautiful, single-file HTML presentations — for Claude Code, Codex, Cursor, OpenClaw, and Hermes.

12670
ZO
zinklu/orca-orchestration
Developer tools

Split "planning by chatting with an agent" from "visualizing + executing" into two independent modules:

13270
SK
sherwinq/karpathy-wiki
Developer tools

基于 Andrej Karpathy 提出的 LLM Wiki 模式 构建的 Agent Skill,通过四阶段流水线将碎片化信息转化为结构化、可检索、持续增长的个人知识库。

10770
LP
lilmgenius/paperthin
Developer tools

On agent | Claude Code, Codex, OpenCode, Antigravity, Copilot, Cursor, Grok-Build, Pi, Hermes, OpenClaw, etc.

12170
GA
goldziher/ai-rulez
Deployment & DevOps

A complete development workflow for AI coding tools

13770
SA
sernote/audit-prompt-caching
Developer tools

audit-prompt-caching is a portable Codex/agent skill for finding why LLM cache reuse fails across the request path: prompt/prefix caches, provider cache telemetry, cache-aware routing, agent tool...

10970
XU
xuxh21/ui-regression-recorder-skill
Developer tools

Turn one human UI page flow into reusable automation capabilities, then assemble new testing flows from those capabilities instead of recording everything again.

11370