Manus-ai_clone

Creates AGENT.md files for AI coding agent compatibility. Use this skill whenever creating a new project, setting up AI agent documentation, or when the user mentions AGENT.md, agent configuration, or AI coding agent setup. Works with Claude Code, Cursor, GitHub Copilot, OpenAI Codex, Gemini CLI, Windsurf, and other AI coding tools.

Write high-quality, engaging blog posts that are SEO-optimized and formatted for maximum readability. Use this skill whenever the user wants to create blog content, articles, or posts - whether they're creating new content from scratch, improving existing drafts, asking for help with blog writing, or needing assistance with any aspect of blog post creation including headlines, structure, SEO optimization, or formatting. This skill covers all blog post types including how-to guides, listicles, opinion pieces, tutorials, ultimate guides, and more. Don't wait for the user to explicitly ask for "blog post writing help" - if they mention writing, creating, or publishing blog content, activate this skill immediately.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Build Flask web applications from scratch. Use this skill whenever the user mentions Flask, Python web apps, REST APIs, web servers, or wants to create any kind of web application using Python, even if they don't explicitly say "Flask." This skill guides you through project setup, routing, templates, forms, APIs, and sandbox deployment.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Create Node.js applications, run JavaScript scripts, and execute TypeScript code in a sandbox environment using the node:22-slim Docker image. Use this skill whenever the user mentions Node.js, JavaScript execution, TypeScript, npm packages, or wants to create/run any kind of Node.js application, even if they don't explicitly say "Node.js sandbox."

Complete browser automation with Playwright for Python. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task using Python. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing with Python.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

MANDATORY FIRST SKILL for all project-building tasks. This skill MUST be read and executed BEFORE any app-building skill (flask-app-builder, web-artifacts-builder, etc.). Use when user asks to build, create, or develop ANY application, website, API, or coding project. Ensures each project has its own isolated working folder with organized structure.

Ensure agents ALWAYS return sandbox_id and endpoint_url when deploying or running applications in a sandbox. Use this skill whenever an application is deployed, a server is started, or a web service is running in a sandbox environment. This skill guarantees consistent output formatting for sandbox deployments.

Export a generated project from a sandbox environment to the local `sandbox-files` directory while **strictly preserving the exact folder structure** from the sandbox.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Ensure that all static assets (CSS, JavaScript, images) in sandbox-generated websites are referenced using RELATIVE paths (without leading slash). This is necessary for assets to correctly load through OpenSandbox proxy URLs. Use this skill whenever generating or modifying HTML files in a sandbox environment, creating static websites, or when asset loading issues are reported in sandbox-deployed sites.

Conducts deep online research to answer complex questions with enhanced query decomposition, source verification, and structured reporting. Use when the user asks for current facts, market data, competitive analysis, or multi-step information gathering from the web. Automatically triggers for research-intensive queries, fact-checking requests, and information synthesis tasks. Supports configurable research depth levels.

Clean up temporary files and old todo lists from the workspace to maintain organization. Use this skill when the user mentions cleaning up files, removing temporary reports, clearing old todo lists, or organizing the workspace. Also use proactively when you notice accumulated reports-*.md files or old .todos.json files that are no longer needed.