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。
MCP Servers
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.
Local-first knowledge compiler for humans and agents. Inspired by Karpathy's vision. Plain markdown, CLI + MCP server.
Local macOS control server for MCP clients and Custom GPT Actions
Git-native API client with encrypted secrets.
Secrets management for AI agents via MCP • @janeesecure
Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
Four small MCP tools that let apfel (Apple's on-device LLM) reach the web and read local files: url-fetch (read a page), ddg-search (web search), search-and-fetch (search+read in one call), fs...
Add vision to text-only models in Opencode (, ) — , no manual file saving.
This project is . Please provide feedback via GitHub issues.
An MCP server that provides access to LLMs using the LlamaIndexTS library.
Agent Skills
A synthesized, spec-compliant pack of five agent skills that turns Claude Code, Codex CLI, and any other agentskills.io-compatible agent into a DSPy expert.
grill-for-unknowns combines docs/source-grounded plan interrogation with the “finding your unknowns” strategy: known knowns, known unknowns, unknown knowns, and unknown unknowns.
確定申告を自動化する AI コーディングエージェント向けプラグイン。個人事業主・会社員の所得税・消費税の確定申告を、帳簿の記帳から確定申告書等作成コーナーへの入力代行までエンドツーエンドで支援します。
Production design patterns for AI coding agents, distilled from 512,000 lines of Claude Code.
- 修复 AskUserQuestion 选项点击后只在界面显示已响应、却没有真正发送给模型的问题；答案现在按问题原文组装，并通过 Claude Code 控制协议回传。 - 修复 v1.0.7 过滤掉部分历史会话的问题；即使会话尚未写入助手回复，也会继续保留在历史列表中，避免旧对话莫名消失。
- ❌ ：GPTZero、Originality.ai 等工具检测出 AI 生成痕迹 - ❌ ：知网、维普等平台查重率过高 - ❌ ：语言风格不符合学术规范，逻辑不够严谨 - ❌ ：手动修改效率低，难以追踪优化进度
The coding-agent skills Zapier GTM teams use to turn scattered context into reviewable work products.
dsh-agent-teams turns the current DeepSeek Harness session into a captain that can assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate work through direct messages.
Documentation • 中文文档 • Live Examples • Tutorials
/bro is a tiny Agent Skills-format skill with one job: when the assistant's last reply was too dense, too jargon-heavy, or too formal, you type /bro and it re-explains like a smart friend over a beer.
Turn any codebase into a navigable , then use that handbook to help a code agent find every place a change needs to touch.
Turn AI output into game design decisions you can verify. Local-first · Evidence-linked · Human-gated