243 skills · sorted by relevance
Use when the user provides a URL from AMD / ROCm official sources (github.com/AMD/*, github.com/ROCm/*, github.com/ROCmSoftwarePlatform/*, rocm.docs.amd.com, amd.com/…/rocm, gpuopen.com). Prefer this over generic GitHub for official ROCm URLs. Generates a hands-on tutorial-following project with no collaborator roles — only the user and the Instructor.
The English summary is being prepared. Showing the original description.
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
The English summary is being prepared. Showing the original description.
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and helper script for reproducible notebook structure and safer editing.
The English summary is being prepared. Showing the original description.
Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project. Also trigger when users mention 'turn this into a course,' 'explain this codebase interactively,' 'teach this code,' 'interactive tutorial from code,' 'codebase walkthrough,' 'learn from this codebase,' or 'make a course from this project.' This skill produces a stunning, self-contained HTML file with scroll-based navigation, animated visualizations, embedded quizzes, and code-with-plain-English side-by-side translations.
The English summary is being prepared. Showing the original description.
Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools (ask_user, sql, fetch_copilot_cli_documentation).
The English summary is being prepared. Showing the original description.
Transform this Python script into a polished, beginner-friendly project by refactoring the code, adding clear instructional comments, and generating a complete markdown tutorial.
The English summary is being prepared. Showing the original description.
Edit existing footage into vlogs, tutorials, demos, or short social clips. This skill guides segment selection, cutting, overlays, audio additions, and platform-specific framing, with final pacing and polish handled in a traditional video editor.
Draft articles, guides, and newsletters in a voice drawn from supplied examples or brand guidance. Turn notes and research into structured prose, or revise existing drafts for clearer pacing, stronger evidence, and consistent style.
Search the web, news, images, and videos through DuckDuckGo without an API key. Filter results by region or time and retrieve titles, links, and snippets, including when the usual search tool is unavailable.
Analyze an article, choose useful illustration positions, and generate images with consistent diagram types, visual styles, and colors. Save generation prompts for reuse and insert the finished illustrations into the article.
Turn source content into infographics that explain comparisons, timelines, processes, and other structures. Choose from 21 layouts and 21 visual styles, then generate an image with your preferred language and format.
Create terminal demos that look like screen recordings using Remotion's TerminalScene component. Script command typing, output, pauses, and badges, then adjust their timing to match narration in tutorials or setup walkthroughs.
Draft Appwrite blog posts around concrete developer problems and search intent. Structure the article, prepare titles, summaries, FAQs, and article metadata, check product claims against local documentation, and generate a cover image using Appwrite's cover API.
Compress screen recordings on Apple Silicon Macs using dedicated video hardware. Choose quality settings for sharing or archiving, inspect video properties, and check the resulting file size and storage savings.
Compress screen recordings on Apple Silicon Macs using dedicated HEVC video encoding hardware. Choose quality presets for sharing or archiving, inspect source files, and review file size savings through command output.
Find animation, short-video, and motion-effect references on 1human, including items saved in a shared human-agent library. Review sources and licenses to guide creative work, and publish creations only within the owner's explicit permission.
Generate realistic photo-style images with Google AI Studio for social posts and educational materials. Adjust aspect ratios, lighting, settings, and subtle imperfections to create a natural smartphone-photo look suited to each use.
Creates software documentation using Diátaxis, a framework that separates learning, task instructions, reference information, and explanation. Clarifies the audience, goal, and scope, then proposes an outline before writing Markdown content consistent with existing documentation.
Add a CUDA/C++ GPU operation to sgl-kernel using AOT, meaning compilation before use. Follow the implementation through PyTorch registration, Python API exposure, SGLang integration, correctness tests, and benchmarks that account for cache reuse.
Develop lightweight CUDA operations for SGLang using JIT, which compiles code on first use. A tensor-scaling example explains implementation conventions, input validation, memory access helpers, and when to choose this approach.
Use Perplexity to find web resources, recent information, or clear explanations drawn from the web. The skill chooses between search results and conversational answers, while directing specialized documentation and workspace questions to other tools.
Draft or revise technical documentation in a direct, friendly style based on Modal's documentation. Lead with the concept or benefit, place a runnable example near the top, and reduce jargon and vague promotional wording.
Coordinate game area design from story, world context, and visual direction through layout, enemies, rewards, accessibility, and test planning. Compile the results into a level design document, with specialist participation determined by the configured team size.
Turn written content into a series of one to ten illustrated image cards for social media. Choose from twelve visual styles, eight layouts, and three optional palettes, with content analysis and outline planning before image generation.