352 个 · 按相关度排序
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Analyze an article, choose where illustrations would help, and generate images with consistent types, styles, and colors. Save the illustration plan and prompts, then insert image references into the article's Markdown.
中文简介正在准备中。当前显示英语简介。
Develop applications with the Claude API using examples from Anthropic's official cookbooks. Explore document summarization, image analysis, document retrieval, external tool calls, and prompt caching through practical Python code and implementation guidance.
中文简介正在准备中。当前显示英语简介。
Create image generation prompts for portrait Xiaohongshu covers using supplied photos and post content. Choose from eight visual styles, then define large Chinese headlines, colors, poses, and supporting graphics in a detailed composition.
中文简介正在准备中。当前显示英语简介。
Write, review, and edit developer documentation for SDKs, libraries, and frameworks. Organize guides, API references, and code examples around readers’ tasks, checking technical claims against source code and official documentation while following the destination site’s conventions.
中文简介正在准备中。当前显示英语简介。
Diagnose why an AI agent skips tools, passes incorrect arguments, or repeats calls. Get guidance on tool descriptions, schemas that define accepted inputs, execution flow, and mock tests before connecting to a real model.
中文简介正在准备中。当前显示英语简介。
Create, edit, or validate Jupyter notebooks for SQL and Python analysis. Organize data sources, assumptions, calculations, and findings into a readable document that others can review and rerun, with execution gaps clearly identified.
中文简介正在准备中。当前显示英语简介。
Guide an AI agent through research, implementation, and verification with fewer interruptions. The skill emphasizes evidence, concise reporting, and saved progress notes, with three working modes that adjust how closely the user follows the work.
中文简介正在准备中。当前显示英语简介。
Helps users get started with Onchain OS, find OKX.AI role registration guidance, or reach support resources. It identifies the purpose of a question and routes it to the appropriate guide.
中文简介正在准备中。当前显示英语简介。
Search YouTube by keyword and upload date, then collect video metrics and channel details through BrowserAct. Results include views, likes, comments, duration, and subscriber counts for comparing videos and researching activity around a topic.
中文简介正在准备中。当前显示英语简介。
Search Chinese social platforms for videos, questions, and answers, with script results returned as JSON, a structured text format. For 小红书 and 微博, use public web pages and record the source and search limitations.
中文简介正在准备中。当前显示英语简介。
Write and edit gh-aw documentation using Diátaxis, a framework that separates learning, task instructions, reference, and explanations. Apply Astro Starlight Markdown conventions while keeping examples focused and removing repeated or unnecessary content.
中文简介正在准备中。当前显示英语简介。
Create Excalidraw diagram files that explain workflows, architectures, and concepts through visual relationships. Technical diagrams include concrete code or data examples, while a rendering and review process checks readability, connections, spacing, and overall composition.
中文简介正在准备中。当前显示英语简介。
Automate video editing in JianYing Pro with Python, from importing media and adding narration or subtitles to creating drafts, recording screens, applying zoom effects, and exporting projects, with export options varying by operating system.
中文简介正在准备中。当前显示英语简介。
Write and revise commits, pull requests, issues, documentation, reports, and blog posts using Marin's editorial style. Lead with results, support claims with evidence, explain limitations, and adapt the structure to the publication format.
中文简介正在准备中。当前显示英语简介。
Find the right tool for equations, calculus, numerical calculations, proof checks, or math practice. The guide connects tasks to commands for computing results, verifying steps, requesting hints, and plotting functions.
中文简介正在准备中。当前显示英语简介。
Create timestamped chapter lists for medium-length and long videos. Transcribe speech with timing information, identify topic changes, and name each chapter, producing a text table of contents for YouTube or B站 descriptions plus structured JSON.
中文简介正在准备中。当前显示英语简介。
Create scripts for videos from 7 seconds to 30 minutes, with timed narration, subtitles, and visual cues. Compare opening ideas for short videos and plan chapters, pacing changes, and viewer retention for longer videos.
中文简介正在准备中。当前显示英语简介。
Turn Markdown, Word, PDF, or plain text articles into HTML for the WeChat official account editor. The skill selects a visual theme, formats headings and highlights, and produces a preview page with a copy button.
中文简介正在准备中。当前显示英语简介。
Prowler documentation style guide and writing standards. Trigger: When writing documentation for Prowler features, tutorials, or guides.
中文简介正在准备中。当前显示原文说明。
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
中文简介正在准备中。当前显示原文说明。
Use this skill to locate authoritative NVIDIA DOCA information without the source tree: the docs.nvidia.com page for a library/service/tool, which DOCA libraries are installed and at what version, a sample on disk or GitHub, a path under /opt/mellanox/doca, or a 404'd/renamed doc URL. Activate on implicit phrasing only when the conversation already names DOCA, BlueField, ConnectX, or /opt/mellanox. Do not activate for generic 'which version is installed' or 'where is the sample' questions with none of that context. Refuse and route elsewhere for hands-on programming, env prep, API tutorials, or hardware/firmware mutation — those belong to doca-programming-guide, doca-setup, the per-library skills, and doca-hardware-safety.
中文简介正在准备中。当前显示原文说明。