“cursor”的搜索结果

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

Import a recorded Remotion Canvas Capture as an editable composition with cursor keyframes, without using Studio controls. The workflow generates and registers a component, copies the video asset, and installs missing dependencies through an internal experimental command.

中文简介正在准备中。当前显示英语简介。

• Importing a recording as an editable composition
• Adding a capture without interacting with Studio
• Setting composition dimensions and frame rate during import

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

Define security controls for AI coding agents used by a team. Covers command and file permissions, secret scanning, isolated execution environments, code review gates, and audit trails, with configuration examples to adapt.

中文简介正在准备中。当前显示英语简介。

• Set team rules before introducing AI coding agents
• Restrict access to credentials and infrastructure files
• Design an isolated environment for agent execution

Turn a short product idea into working code through requirements analysis, technical planning, implementation, testing, and review. It coordinates agents across these stages, fixes detected problems, and reports assumptions that still need a human decision.

中文简介正在准备中。当前显示英语简介。

• Building a product from a short idea
• Creating a bookstore inventory API
• Developing a habit-tracking command-line tool

Develop network monitoring for signs that may precede ransomware encryption. Uses detection rules, linked log events, and threat intelligence to identify suspicious activity and define how alerts should be investigated, prioritized, and escalated.

中文简介正在准备中。当前显示英语简介。

• Creating detection rules for activity before ransomware encryption
• Linking suspicious logins, scans, and file share access
• Investigating unusual internal network communications

Connect agentmemory to coding agents such as Claude Code and Codex while preserving existing server settings. It guides configuration, host restarts, and checks that memory tools are available and can save and retrieve information.

中文简介正在准备中。当前显示英语简介。

• Connecting agentmemory to a coding agent
• Checking supported agents and connection methods
• Investigating an incorrect configuration path

Turn an OpenAPI specification into starter code for an MCP server, which connects AI agents to API tools. Support Python or TypeScript implementations, validate tool definitions, and plan changes that preserve compatibility.

中文简介正在准备中。当前显示英语简介。

• Exposing an existing REST API to an AI agent
• Creating a Python or TypeScript MCP server scaffold
• Checking tool definitions before integration tests

Create project-specific rules for turning Figma designs into code. The skill examines existing components and styling, then saves conventions for naming, file locations, reusable design values, and implementation steps in the coding agent's rule file.

中文简介正在准备中。当前显示英语简介。

• Setting up Figma implementation rules for a new project
• Teaching an AI agent existing component conventions
• Standardizing Figma implementation across a team

Connects supported AI clients, including Claude Code and Codex, to OpenWork through MCP, a protocol for accessing external tools. It guides account sign-in and verifies that tools for finding and running organization capabilities are available.

中文简介正在准备中。当前显示英语简介。

• Connecting an AI client to OpenWork organization resources
• Signing in and verifying available MCP tools
• Switching organizations or troubleshooting authentication

Turn a rough idea or an existing prompt into a ready-to-paste instruction for a specific AI tool. The skill clarifies the task, output format, constraints, and success criteria for writing, image generation, or coding agents.

中文简介正在准备中。当前显示英语简介。

• Turning a rough idea into an AI prompt
• Improving a prompt for a specific AI tool
• Defining scope and completion criteria for coding agents

Record a web app workflow on a desktop with a visible system cursor. It produces an MP4 video and a separate log of clicks, hovers, scrolling, and typing, and can re-record existing demo scripts.

中文简介正在准备中。当前显示英语简介。

• Recording a checkout or user invitation workflow
• Creating a feature video for a changelog
• Re-recording an existing demo after UI changes

Create fluid animations where rounded shapes merge as they approach and separate as they move apart. SVG filters combine blur with a cutoff effect to form soft, connected shapes for backgrounds, loaders, or cursor effects.

中文简介正在准备中。当前显示英语简介。

• Adding fluid shapes to a page background
• Creating a merging-blob loading indicator
• Building a soft cursor effect

Create coordinated website animations with GSAP, ScrollTrigger, and Lenis. Combine smooth scrolling, staged text and image reveals, pinned scenes, and pointer interactions, with guidance for performance, touch devices, and reduced-motion preferences.

中文简介正在准备中。当前显示英语简介。

• Coordinating motion across a portfolio website
• Revealing text and images during scrolling
• Building pinned storytelling sections

Audit MCP servers, which connect AI agents to external tools, for injected instructions, excessive access, secret leaks, and unapproved actions. Trace untrusted input through tool calls and document demonstrated issues with concrete fixes.

中文简介正在准备中。当前显示英语简介。

• Auditing a custom MCP server
• Reviewing third-party tool integrations
• Checking client connection settings

Choose which installed PeonPing character voice pack plays during the current chat. The command checks that the pack exists and enables a mode that prioritizes session assignments, so the selected voice is used for that conversation.

中文简介正在准备中。当前显示英语简介。

• Selecting GLaDOS for the current chat
• Assigning different voices to different sessions
• Switching to an installed character voice pack

Run an app preview on the local machine and provide an HTTPS link for trying changes. It selects a frontend preview or full local stack based on changed files, then explains sign-in, certificate requirements, and how to stop it.

中文简介正在准备中。当前显示英语简介。

• Previewing frontend changes in the browser
• Trying backend changes with the full local stack
• Testing permissions with seeded sample data

Choose AI tools for literature searches, PDF conversion, citation-backed questions, and review writing. The skill also installs and runs supported tools through a shared launcher, with workflows that connect paper retrieval, conversion, and analysis.

中文简介正在准备中。当前显示英语简介。

• Choosing tools for a literature review
• Converting research PDFs to Markdown
• Asking citation-backed questions across PDFs

Create HTML design artifacts, including interface mockups, interactive prototypes, and slide decks, then preview and verify them. The skill also guides importing design references and building reusable design systems with shared styles and components.

中文简介正在准备中。当前显示英语简介。

• Creating interface mockups
• Exploring user flows with interactive prototypes
• Creating slides and exporting them to PowerPoint

Coordinate AI agents running in Herdr workspaces inside Ghostty. Inspect terminal output and agent status, send instructions, wait for completion, share missing context, and combine results into one summary while avoiding duplicate work.

中文简介正在准备中。当前显示英语简介。

• Check agent status and output in a Herdr workspace
• Send instructions to a specific agent
• Wait for task completion and read the results

Write the structured handoff from a planning session to a coding agent: a dispatch with a header, Gate 0 checks, scope, specification, verification, delivery rules, and stop conditions, so the agent can execute unattended and return a reviewable draft PR. Use this skill whenever the user wants to hand work to an agent, write an agent brief, write instructions for Claude Code, Codex, or a Cursor agent, queue work to run overnight, or turn a plan into something an AI coder can execute without asking questions. Triggers on dispatch, hand off to an agent, agent brief, agent handoff, task brief for an AI coder, instructions for Claude Code, Codex task, Cursor agent, background agent, run this overnight, give this to an agent, unattended run. Also triggers when the user has a plan or a spec and asks how to get an agent to build it, even if they never say dispatch.

中文简介正在准备中。当前显示原文说明。

A fluid-simulation cursor — pointer movement splats swirling, glowing dye (full multi-pass WebGL fluid sim). A marketing-grade hero backdrop. One per view; scrim behind text. Renders a static frame under prefers-reduced-motion.

中文简介正在准备中。当前显示原文说明。

An animated target ring replaces the cursor and grows when it hovers buttons/links — a focused, techy pointer. One per page. Off on touch and under prefers-reduced-motion.

中文简介正在准备中。当前显示原文说明。

A soft gooey blob trails the cursor with a springy lag — a playful custom pointer for a hero section. One per page; can distract on content-heavy pages. Hidden on touch and under prefers-reduced-motion.

中文简介正在准备中。当前显示原文说明。