A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
中文简介正在准备中。当前显示原文说明。
Add a Codex plugin from a GitHub repo to a repo or personal marketplace using the current Codex plugin layout and marketplace metadata.
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Use when the user gives a GitHub repo for a Codex plugin and wants it available in Codex.
Follow the current Codex plugin docs. Do not invent alternate install flows.
owner/reporepo or personal.codex-plugin/plugin.json..codex-plugin/plugin.json and validate the canonical structure:
name, version, and description should exist.skills, apps, and mcpServers should be relative to the plugin root and start with ./.plugin.json should live inside .codex-plugin/.@plugin-creator skill when the task is to scaffold a new local plugin or add an existing local plugin to a marketplace. Use the manual path below when you are wiring up a repo the user already provided.SKILL.md, into a marketplace-visible location. Default to the documented standard locations unless the repo already uses a different valid marketplace-relative path:
repo: $CWD/plugins/<plugin-name> and $CWD/.agents/plugins/marketplace.jsonpersonal: ~/.codex/plugins/<plugin-name> and ~/.agents/plugins/marketplace.jsonskills/, .app.json, .mcp.json, assets/, and any other plugin files. Do not move those files under .codex-plugin/.nameinterface.displayNamenamesource.source = "local"source.path relative to the marketplace root:
repo: ./plugins/<plugin-name>personal: ./.codex/plugins/<plugin-name>policy.installationpolicy.authenticationcategorypolicy.installation = "AVAILABLE"policy.authentication = "ON_INSTALL"category from interface.category when present, otherwise Productivity/plugins.~/.codex/plugins/cache/<marketplace>/<plugin>/<version>/.local.~/.codex/config.toml.repo marketplace and personal marketplace over workspace and global.plugins/ as the complete install. The marketplace entry is what makes the plugin discoverable in Codex.name stable and consistent across folder, manifest, and marketplace entry../-prefixed where the docs require it.source.path remains valid and stays inside the marketplace root.Use repo when the plugin should live with one repo or be shared through that repo's marketplace. Use personal when the plugin should be available from the user's own Codex setup across projects.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
中文简介正在准备中。当前显示原文说明。
Create or update Codex hooks for global or project scope by asking for scope and hook type when ambiguous, then writing the hook config, scripts, and any required feature flag config.
中文简介正在准备中。当前显示原文说明。
Build responsive, mobile-first layouts using fluid containers, flexible units, media queries, and touch-friendly design that works across all screen sizes. Use this skill when creating or modifying UI layouts, responsive grids, breakpoint styles, mobile navigation, or any interface that needs to adapt to different screen sizes. Apply when working with responsive CSS, media queries, viewport settings, flexbox/grid layouts, mobile-first styling, breakpoint definitions (mobile, tablet, desktop), touch target sizing, relative units (rem, em, %), image optimization for different screens, or testing layouts across multiple devices. Use for any task involving multi-device support, responsive design patterns, or adaptive layouts.
中文简介正在准备中。当前显示原文说明。
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
中文简介正在准备中。当前显示原文说明。
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
中文简介正在准备中。当前显示原文说明。
Build, transform, audit, and migrate prompts for GPT-5.6 Sol using outcome-first contracts, explicit success criteria, evidence and tool rules, approval boundaries, output requirements, and stop conditions. Use when someone asks for a GPT-5.6 prompt, wants an existing prompt optimized for GPT-5.6, or needs a prompt stack adapted from an older model.
中文简介正在准备中。当前显示原文说明。