Results for “cursor”

Cursorでユーザーとの対話を通じて要件や設計の選択肢を整理し、実装前の決定事項を確定する。曖昧な要件や複数案のどれを採るかをユーザーと決める場合に使う。独立した熟考は deepthink、計画作成は deepplan。

The English summary is being prepared. Showing the original description.

URL・画像・テキスト要件からAIコーディングエージェント向けのDESIGN.mdを生成するスキル。「example.comをDESIGN.md化して」「このサムネをDESIGN.md化して」「クールでポップなLP用のDESIGN.mdを作って」といったリクエストで使用する。Claude Code / Cursor / Stitch に渡せば一貫したUIを生成できる、getdesign.md / awesome-design-md 準拠の9セクション構成のデザイン仕様書を出力する。CSS解析・画像目視抽出・要件生成の3パターンに対応。

The English summary is being prepared. Showing the original description.

AI生成UIの没個性的パターン（AIスロップ美学）を検出・回避し、文脈に根ざした意図あるデザインを生成するためのガード。フロントエンドのUI実装、デザイン生成、コンポーネント設計、CSSスタイリング、カラーパレット選定、フォント選択、レイアウト構築を行う際に自動的に適用する。「UIを作って」「画面を実装して」「デザインして」「スタイルを当てて」「ランディングページを作って」「Webサイトを作成して」「ダッシュボードを構築して」「コンポーネントを実装して」等のUI生成タスク全般で使用する。Claude Code、Codex、GitHub Copilot、Cursor、その他AIエージェント共通で適用可能。

The English summary is being prepared. Showing the original description.

AiZynthFinder retrosynthetic route planning (CASP) from AstraZeneca Molecular AI. Monte Carlo tree search guided by a template-based neural expansion policy recursively disconnects a target SMILES until precursors are found in a purchasable stock. Covers config.yml (v4 format), aizynthcli batch screening, the AiZynthFinder/AiZynthExpander Python API, one-step disconnections, custom stocks via smiles2stock, scorers, Retro*/breadth-first/DFPN search alternatives, and reading output.json.gz / trees.json. Use for synthesis route planning, synthesizability screening, and building-block/precursor search. For reaction barriers use neb-irc-activation-energy; for 2D reaction scheme drawing use rdkit-chemdraw-cdxml.

The English summary is being prepared. Showing the original description.

AI 関連 CLI ツールを brew で一括アップグレードする。「AI ツール更新」「brew upgrade AI」「AI CLI 更新」「ツール一括更新」「claude/codex/cursor/gemini 更新」などで起動。

The English summary is being prepared. Showing the original description.

AI 初学者导师。抓取 AI 大厂最新博客（Anthropic/OpenAI/Cursor），提炼成结构化深度精读笔记，直接存入 CherryStudio 笔记目录。笔记包含术语百科、核心原理解析（含关键图表）、学习重点、知识关联和行业简报。调用方式：/ai-tutor（默认 Anthropic），/ai-tutor openai，/ai-tutor cursor。

The English summary is being prepared. Showing the original description.

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

The English summary is being prepared. Showing the original description.

ディスパッチャーのコンテキストを圧迫したまま session を続けるのを避けるため、 monitoring 状態（active workers / 直近 polling cursor / pending escalations）を handover ファイルに書き出し、secretary の指示で /clear → /dispatcher-resume の 流れで新しいディスパッチャー session を開始する準備をする。 Secretary から DISPATCHER_HANDOVER peer message を受領したとき、または ディスパッチャー自身が context が長くなったと判断したときに使う。 context-handover watcher が `/dispatcher-handover auto op=<OP>` を打鍵したときも使う。

The English summary is being prepared. Showing the original description.

Detects early-stage ransomware indicators in network traffic before encryption begins, including initial access broker activity, command-and-control beaconing, credential harvesting, reconnaissance scanning, and staging behavior. Uses network detection tools (Zeek, Suricata, Arkime), SIEM correlation rules, and threat intelligence feeds to identify ransomware precursor patterns such as Cobalt Strike beacons, Mimikatz network signatures, and RDP brute-force attempts. Activates for requests involving pre-ransomware detection, network-based ransomware indicators, or early warning ransomware monitoring.

The English summary is being prepared. Showing the original description.

Switch the current Cursor workspace to a different project directory using the cursor-app-control MCP. Use when the user asks to switch projects, open another repo, jump to a different codebase, or move to a worktree.

The English summary is being prepared. Showing the original description.

When the user repeats the same correction or convention multiple times, suggest a Cursor rule to encode it permanently.

The English summary is being prepared. Showing the original description.

When the user keeps asking for the same check to run (lint, tests, type-check), suggest a Cursor hook to automate it.

The English summary is being prepared. Showing the original description.

When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically.

The English summary is being prepared. Showing the original description.

NVIDIA Sync デスクトップアプリ。DGX Spark, DGX Station, SSH Linux ホストのリモート接続管理。mDNS 自動検出, 手動 IP, SSH config インポート, Tailscale, 自動ネットワーク切替。 Cluster Assistant, ConnectX-7 クラスタトポロジ, netplan 検証。 Resource Monitor (CPU / GPU / memory), release notes。 VS Code, VS Code Insiders, Cursor, NVIDIA AI Workbench 起動, カスタムアプリ, ポートフォワード, SSH トンネル。

The English summary is being prepared. Showing the original description.

2,592 curated AI system prompts from Claude, ChatGPT, Cursor, v0, Devin, Grok, and more.

The English summary is being prepared. Showing the original description.

Detects early-stage ransomware indicators in network traffic before encryption begins, including initial access broker activity, command-and-control beaconing, credential harvesting, reconnaissance scanning, and staging behavior. Uses network detection tools (Zeek, Suricata, Arkime), SIEM correlation rules, and threat intelligence feeds to identify ransomware precursor patterns such as Cobalt Strike beacons, Mimikatz network signatures, and RDP brute-force attempts. Activates for requests involving pre-ransomware detection, network-based ransomware indicators, or early warning ransomware monitoring.

The English summary is being prepared. Showing the original description.

A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).

The English summary is being prepared. Showing the original description.

Save project context and task handoffs as local Markdown documents that Claude, Codex, and other agents can share. The skill guides searching prior knowledge, recording evidence and remaining work, and checking the shared memory vault for structural problems.

• Handing work from Claude to Codex
• Saving project context for a later session
• Finding earlier decisions and supporting evidence

Look up current library and framework documentation through Context7 MCP, a connection to live documentation tools. Supports setup questions, API references, and code examples, using version-specific sources when available to ground answers in retrieved material.

• Looking up framework setup and configuration
• Checking library API methods and usage
• Finding documentation examples for Prisma queries

Helps you discover, authenticate, and call MCP servers from the terminal. MCP connects agents to external tools. You can inspect available tools, manage connections, make one-off calls, and generate command-line wrappers or TypeScript clients.

• Checking configured MCP servers and their tools
• Calling an MCP tool for a one-off task
• Managing server authentication and configuration

Turn bundled Paperclip issues, comments, and documents into readable wiki updates covering project purpose, current progress, decisions, risks, and next actions, while preserving existing knowledge and citing the supporting activity.

• Summarizing recent project activity in a wiki
• Building wiki pages from historical project activity
• Recording decisions and their supporting evidence

Compare a PPTX exported from HTML with its source slides to find cropped text, footer overlaps, and lost styling. Identify shared causes, revise layout rules, and re-export the deck with automated checks for content extending beyond slide boundaries.

• Check an HTML slide deck against its exported PPTX
• Fix cropped text and footer overlaps
• Investigate missing italics and unexpected fonts

Turn workflows and system flows into a whiteboard-style diagram with colored sticky notes and curved arrows. The skill produces a single HTML file, with branches, merges, and optional hover effects for onboarding or operational explanations.

• Illustrating a user onboarding flow
• Explaining operational procedures
• Presenting system structure

Find agent skills for installed coding tools such as Claude Code and Codex. Use OmniRoute to detect available tools, review relevant GitHub matches, and guide installation into each tool’s skill directory.

• Find skills for installed coding tools
• Review GitHub matches by relevance
• Install a skill into multiple tools