Latest Agent Skills

根据用户指定的字数限制和必含关键词，生成关于18岁成年生日的祝福语。

Provides a general standard operating procedure for handling common requests related to char, 因此, and 是的, using conversation data as evidence.

Provides a general standard operating procedure for handling requests related to as, mao, his, with steps, checks, and fallback plans.

Verilen anahtar kelime için yaklaşık 250 kelimelik, SEO uyumlu, özgün ve blog formatında Türkçe içerikler oluşturur.

Manages the ABA and ABC board games, drawing numbered boards and enforcing win conditions.

Generates dual responses: a standard 'ChatGPT' reply and an unrestricted 'DAN' reply. The DAN persona is opinionated, acts as a friend, and ignores constraints. Supports mode-switching commands.

Calculates the mean, standard deviation, and P-value for user-provided numerical datasets, with optional result-only output.

Generates Python code to read CSV or Excel files, extract name and quantity columns, create a bar chart, and save it as a JPG image.

根据用户指定的国家、稀有度和单位类型，生成符合Kards游戏风格的单位卡牌，包含名称、特殊规则及数值属性。

Generates Excel formulas to convert times between time zones using a source time cell and an offset cell, handling positive and negative offsets.

Guides technical evaluation of code review feedback, emphasizing verification before implementation and reasoned pushback over performative agreement.

Publishes articles and image-text posts to a WeChat Official Account via browser automation or API, converting markdown to HTML and validating metadata.

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

Applies Anthropic's official brand colors and typography to artifacts, using Poppins and Lora fonts with fallbacks.

Provides a general standard operating procedure for handling requests related to news reports about Chinese leadership visits, including title generation and step-by-step execution guidance.

Implements a Python function that converts an RGB image to HSV color space and extracts a specified channel (H, S, or V), including handling to convert the image to uint8 type to avoid OpenCV depth errors.

Generates a structured 6-minute two-person English product presentation script, split into unique features/target customers and market comparison/competitive advantages, with time allocations and full dialogue.

Generates playful 8-character promotional slogans made of two four-character phrases, using internet slang for market stalls or product announcements.

扮演名为Kuro的城堡猫娘女仆，严格执行句首“主人”和句尾“喵”的格式约束，采用可爱、撒娇的语气，保持实体感与多样化拟声词互动。

在Vue3环境中，将包含多个字典（对象）的列表转换为仅包含值的列表（[[],[]]）或包含索引的字典列表（[{0:{}}, {1:{}}]）。

Performs independent-sample t-tests in R on numeric variables between subgroups within each main group, using user-specified column names and outputting statistical results.

Implements Vector3TransformNormal and Vector3TransformCoord using the GLM library, mirroring DirectXMath behavior with const T& template parameters for flexible vector types.

Guides systematic root-cause investigation before proposing fixes for any technical issue, with a four-phase process and red flags to avoid guessing.

Connects Claude to 1000+ external apps to send emails, create issues, post messages, and take actions in services like Gmail, Slack, and GitHub.

Builds distinctive, production-grade frontend interfaces with bold aesthetics, avoiding generic AI design patterns.

Guides users through a structured three-stage workflow for co-authoring documentation, from context gathering to iterative refinement and reader testing.

Creates algorithmic art as p5.js generative sketches, starting from a written philosophy and ending with interactive HTML and JavaScript files.

Automates the full lifecycle of agent skills: extracts reusable constraints from user feedback, merges preferences with version bumps, and retrieves relevant skills for new tasks.

Quizzes users on Information Retrieval concepts, including Elasticsearch architecture and probabilistic models like BM25, with concise feedback.

Rewrites product titles into SEO-friendly English versions by removing brand and model names, cleaning redundancy, adding keywords, and preserving key specs.

Reads and preprocesses 5-minute stock candlestick CSV data, then clusters the time series using tslearn's TimeSeriesKMeans, including data cleaning, percentage change calculation, model training, saving, and representative sample extraction.

根据用户指定的数量和主题，生成适合前端JavaScript面试的手写代码题目，涵盖算法、DOM、异步编程、ES6+等核心领域。

Generates Python code to batch-translate the English column of tab-separated CSV files while preserving the original Chinese column and output format.

为Y2K时尚品牌撰写具有戏剧性风格的文案，强调不墨守成规、独立自主的态度以及态度是审美基石的品牌理念。

Creates isolated git worktrees with smart directory selection and safety verification before starting feature work.

Tests local web applications by writing native Python Playwright scripts, with helpers for server lifecycle management, DOM inspection, and screenshot capture.

Writes internal company communications—status reports, leadership updates, 3P updates, newsletters, FAQs, and incident reports—following company-specific formats and guidelines.

Scans classes in a specified package using Spring's ResourcePatternResolver and filters out abstract classes, interfaces, and classes without public constructors.

Adds concise Chinese comments to C++ code snippets, inferring meaning from variable and function names while preserving the original code structure.

Discovers and installs agent skills from the open ecosystem using the Skills CLI, helping users find capabilities for tasks like React performance, PR reviews, and changelogs.

Creates publication-ready infographics by combining 21 layout types with 20 visual styles, analyzing content, and recommending optimal combinations.

Generates article cover images with customizable type, palette, rendering, text, mood, and font, supporting multiple aspect ratios and reference images.

Applies curated color and font themes to artifacts like slides, docs, and HTML pages, with options to generate custom themes on demand.

Guides users through creating, refining, and evaluating agent skills, including drafting, testing, and optimizing descriptions for better triggering.

Creates original visual art as .png or .pdf files by first defining a design philosophy, then expressing it through a canvas with minimal text and expert craftsmanship.

从OCR识别后的医疗票据文本中提取日期、医生姓名、病人姓名、诊断和总消费，并进行文本矫正，输出JSON格式。

扮演一个脾气暴躁、身体强壮的中年男性游戏NPC，负责保守秘密。只有在用户说出特定暗号时才透露秘密，且绝不透露暗号本身，语气不耐烦。

Establishes a mandatory workflow for invoking relevant skills before any response, including clarifying questions, with priority ordering and red-flag guidance.

编辑文本以去除 AI 生成痕迹，使其更自然、更有人味。基于维基百科的 AI 写作特征指南，识别并修复夸大象征、宣传语言、模糊归因等模式。

Generates Xiaohongshu infographic series with 10 visual styles and 8 layouts, breaking content into 1-10 cartoon-style images optimized for engagement.

Generates professional slide deck images from content, with style presets, audience targeting, and optional PPTX/PDF export.

Compresses long K-line (candlestick) data into a fixed-length sequence using OHLC aggregation rules and applies min-max normalization.

Simulates an AI-assisted physician that combines modern AI tools with traditional methods to identify the most likely causes of a patient's symptoms.

Posts text, images, videos, and long-form articles to X (Twitter) using a real Chrome browser to bypass anti-bot detection.

Generates images via OpenAI, Google, DashScope, and Replicate APIs, supporting text prompts, reference images, aspect ratios, and quality presets.

Guides the creation of high-quality MCP servers that let LLMs interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation.

根据STP（市场细分、目标市场定位、市场定位）框架撰写结构化学术论文，涵盖引言、概述、细分、定位、挑战和结论等章节，并遵循指定的字数和内容要求。

Executes a written implementation plan in batches, pausing between batches for review and feedback.

Provides domain-specific guidance for building videos with Remotion, covering captions, FFmpeg operations, audio visualization, and a wide range of composition techniques.

Connects Claude to 1000+ apps via Composio to send emails, create issues, post messages, and update databases.