“cursor”的搜索结果

Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 69 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "deep paper review", "auto research", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness".

中文简介正在准备中。当前显示原文说明。

Create, implement, or review oversized cursor work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on oversized cursor.

中文简介正在准备中。当前显示原文说明。

生成一份对外可分享、脱敏的 AI-Native 开发者 README。 量化展示我对 Claude Code + Codex CLI + Kiro (AWS) + Trae (ByteDance) + Gemini Antigravity (Google) + Cursor 的使用深度、AI 协作风格、 项目与领域分布、兴趣主题，以及与 GitHub 提交的产出关联。 Trigger when the user says: "生成我的 AI 档案" / "做一份 AI-native README" / "分析我的 Claude / Codex / Kiro / Trae / Antigravity / Cursor 使用情况" / "总结我的 AI 使用" / "生成 AI 月度报告" / "按月份分析我的 AI 编码" / "分析 2026-05 的 AI 使用" / "build my AI usage profile" / "build my monthly AI coding report" / "analyze my AI usage for May 2026" / "summarize my Claude / Codex / Kiro / Trae / Antigravity / Cursor history" / "生成开发者画像". 全程本地、只读、默认匿名、不上传任何数据。

中文简介正在准备中。当前显示原文说明。

Control Cursor AI code editor via CLI. Use when opening files, comparing diffs, managing extensions, or configuring Cursor as git editor.

中文简介正在准备中。当前显示原文说明。

Shell out to Cursor Agent CLI for headless IDE-aware code tasks. Supports multi-model routing (auto mode routes to Claude, Gemini, GPT). Requires Cursor Pro/Business subscription.

中文简介正在准备中。当前显示原文说明。

Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project

中文简介正在准备中。当前显示原文说明。

Hunts for ransomware precursor behavior that precedes encryption — shadow-copy and backup deletion, recovery disabling, security-tool tampering, and mass file modification — so the attack can be stopped before payload detonation. Activates for requests to hunt ransomware precursors, detect shadow-copy deletion, or find pre-encryption recovery sabotage.

中文简介正在准备中。当前显示原文说明。

FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use this skill. It gives AI agents a cursor and a keyboard on a real desktop — the last mile when the only remaining surface is a GUI. Concretely: use it when an earlier attempt via API, CLI, or direct file edit has failed and the user says things like "open X", "click Send", "type this in Word", "read what is on my screen", "do this in Outlook", "drive the Figma UI", "control my desktop", "automate this workflow", "fill out this form", or "copy text between apps". Works on Windows, macOS, and Linux with any LLM that can call functions (Claude, GPT, Gemini, Llama, Kimi, Ollama) over MCP — stdio for editor hosts (Claude Code, Cursor, Windsurf, Zed) or HTTP for daemons and dashboards.

中文简介正在准备中。当前显示原文说明。

Delegate implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).

中文简介正在准备中。当前显示原文说明。

Devin CLIから /handoff でDevin Cloudにタスクを引き継ぐ際に発動。ハンドオフ先のDevin Cloudに対して、タスクの実行をCursor Cloud Agentに委譲するよう指示を含める。

中文简介正在准备中。当前显示原文说明。

Cursor Cloud Agentにタスクを委託するよう依頼された際に発動。エージェント作成、SSEストリーム監視（stream）、実行キャンセル（cancel）、ステータスポーリング（フォールバック）、Pull Request状態確認、Linear紐付け、レビュー・フォローアップを行う。

中文简介正在准备中。当前显示原文说明。

Expert Cursor (IDE IA, multi-file edits, composer, contexte, rules, contexte DZ)

中文简介正在准备中。当前显示原文说明。

事前設計が必要な複数段階のCursor委任作業で、依存関係・担当・検収条件を持つ永続PLANを作成・実行する。

中文简介正在准备中。当前显示原文说明。

轩辕AI编码舰队——OpenClaw作为大脑，指挥Claude Code/Cursor/Windsurf/Trae/Codex CLI集群并行开发。覆盖：ACP配置、IDE接入、权限管理、任务分发、windsurf+cursor双IDE调度、worktree隔离、舰队看板。触发词：IDE舰队、编码集群、AI IDE、多工具编排、ACP配置、Cursor舰队、Windsurf集群、Trae接入、IDE调度、并行编码、AI编码引擎、IDE编排、coding fleet

中文简介正在准备中。当前显示原文说明。

读取MCP配置，在不运行服务器的情况下检查批准后仍可能获取不同代码的包引用，分类npm、Python和Docker版本指定，并建议固定到团队已审阅的版本。

• 批准前检查MCP配置
• 检查latest标签和版本范围
• 向CI添加可重复的配置检查

将网页应用的操作流程录制为带箭头光标和字幕的WebM视频。先检查界面并排练，再以便于观看的节奏展示输入、点击和滚动，呈现操作过程与结果。

• 用视频介绍新功能的操作
• 为首次使用者制作引导视频
• 为文档添加操作视频

为SwiftUI界面设计提供支持，涵盖避免AI常见雷同风格的规则、设计方向建议、品牌素材处理流程，以及从五个维度审查已完成界面的方法。

• 确定SwiftUI界面的设计方向
• 审查AI界面的雷同风格
• 确认品牌素材的处理方式

Connect AI agents to OmniRoute through MCP, a protocol for accessing tools. Use tools for request routing, memory, cache, providers, and audits, with three connection methods and permission scopes that control which operations are available.

中文简介正在准备中。当前显示英语简介。

• Connect Claude Desktop or an editor to OmniRoute
• Inspect and explain request routing
• Add and search stored memories

Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.

中文简介正在准备中。当前显示英语简介。

• Find community skills for a specific task
• Compare skills using relevance scores
• Check for malware and embedded secrets

Set up and operate Ruflo to coordinate multiple AI coding agents. This skill guides project initialization, shared memory, task assignment, health checks, and plugin discovery for work that needs coordinated or parallel execution.

中文简介正在准备中。当前显示英语简介。

• Initializing a multi-agent development environment
• Coordinating parallel work across agents
• Keeping searchable memory across sessions

Understand how Codex Rules adds project instructions and file-specific rules to agent context. Check supported rule locations, when rules are applied, and environment settings for modes, sources, and text limits.

中文简介正在准备中。当前显示英语简介。

• Checking supported locations for rule files
• Understanding when file-specific rules are applied
• Configuring rule modes and text limits

Plan HyperFrames videos so motion flows continuously between scenes. Match movement direction and speed across cuts, connect actions through visible causes, and verify scene boundaries while keeping each scene active through meaningful reveals or interactions.

中文简介正在准备中。当前显示英语简介。

• Plan consistent movement across scene transitions
• Connect scenes with a shared visual element
• Replace idle motion with reveals or interactions

Prepare Remotion Studio and Canvas Capture for a product demo recorded by the user. Import the original capture into packages/brand as an editable composition, preserve cursor metadata, and upload the verified recording to remotion.media.

中文简介正在准备中。当前显示英语简介。

• Prepare a Studio interaction demo for recording
• Frame a timeline demonstration
• Import a capture with editable cursor data

Start Remotion Studio and open a browser preview while creating or editing a video. Keep the preview visible during work so users can review changes and guide adjustments as the composition takes shape.

中文简介正在准备中。当前显示英语简介。

• Previewing a Remotion video during creation
• Reviewing changes while editing a video
• Opening Studio in an in-app browser