>
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →>
Use when searching academic papers via Ai2 Asta (Semantic Scholar corpus) through the Asta MCP server. Triggers on academic search, paper lookup, citation traversal, author search, or snippet search when the Asta MCP server is configured. Works with Claude Code, Codex, Hermes, OpenClaw, Windsurf, Cursor, and any MCP-compatible agent.
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io desktop CLI.
Use when the user wants to repurpose a YouTube video for Bilibili, add bilingual (English-Chinese) subtitles to a video, or create hardcoded subtitle versions for Chinese platforms.
name: ppt-maker
>
Coaching practice support with session preparation, question generation, client progress tracking, and goal setting. Use when user mentions coaching sessions, coaching questions, client progress, or coaching goals. Prepares sessions, generates powerful questions, tracks client commitments, supports goal setting with clarity framework, and maintains momentum between sessions. STRICT client confidentiality.
Local-first health record management with strict privacy boundaries. Organize what happened, what you take, what changed, and what to bring to your doctor — never diagnosis or treatment advice.
>
Structured extraction and cleanup for public, user-authorized web pages. Use when the user wants to collect, clean, summarize, or transform content from accessible pages into reusable text or data. Do not use to bypass logins, paywalls, captchas, robots restrictions, or access controls. Local-only output.
调用秒秒AI多能力智能体，支持聊天、天气、新闻、快递、图像生成、搜索、总结、图表、地图、车票查询等功能。Invoke when user needs AI assistant with multiple practical functions or mentions related keywords.
Generate images, videos, and audio via fal.ai API (FLUX, SDXL, Whisper, etc.)
An AI-powered Solana token strategist designed for Bags.fm launches.
AI视频脚本生成器。根据用户输入的主题/关键词，生成完整的视频脚本，包含分镜描述、画面提示词、配音文案。适用于短视频创作者、AI视频制作者、内容营销人员。触发词：视频脚本、分镜、AI视频、短视频文案、视频策划。
技术讨论管理和沉淀技能，自动创建结构化的讨论记录、代码输出目录，沉淀技术决策和创意，支持 Git 版本管理（可选），支持多智能体协同使用。
Visual identity discovery for AI agents — not an avatar generator, but a self-reflection system that creates a face from your agent's personality, memory, and relationship with its human. Quick mode: 5 minutes. Full mode: 5-phase deep identity discovery with batch generation and professional three-axis evaluation. Works with any image generation tool (DALL-E, Flux, Midjourney, Stable Diffusion). The face comes from the inside out, not from a prompt template. Use when: agent visual identity, avatar, self-portrait, agent face, agent image, identity discovery, profile picture, agent appearance, character design, AI identity, visual persona.
knowyourself
中小学教师智能备课助手。当用户需要准备课件（PPT）、教案（教学设计）、学生任务单（导学案）时使用此技能。支持数学、语文、英语等学科的备课、课堂巩固、课后作业等教学场景的文档生成。本技能会自动生成完整的备课资料包，包括课件、教案、任务单、参考资料下载和辅助教学HTML工具。激活词：tapl、备课、备课助手、做课件、写教案、教学助手、teaching、设计任务单、导学案。
中小学教学文档智能生成工具。当用户需要制作课件（PPT）、编写教学设计（教案）、或创建学生任务单（导学案）时使用此技能。支持数学、语文等学科的备课、课堂巩固、课后作业等教学场景的文档生成。
基于《周易》的完整占卜系统，支持铜钱起卦 + 八字排盘 + 综合解读
拉取IM账号近1-7天聊天记录并生成汇总分析
Mayar.id payment integration for generating invoices, payment links, and tracking transactions via MCP. Use when needing to: (1) Create payment invoices/links for customers, (2) Track payment status and transactions, (3) Generate WhatsApp-friendly payment messages, (4) Handle Indonesian payment methods (bank transfer, e-wallet, QRIS), (5) Manage subscriptions/memberships, or (6) Automate payment workflows for e-commerce, services, or digital products.
(半自动) 投放素材效果诊断与分析，通过读取平台导出的数据报表（图片或表格），生成一份诊断分析报告，为素材优化提供明确建议。
(已验证) 根据客户和场次，自动生成详细的《直播复盘与成长规划报告》。
根据用户输入（产品、目标、直播类型等）生成专业的直播间口播、互动和逼单脚本。支持参数化调用，可指定带货类/种草类/品牌宣讲类等不同风格。
短视频核心脚本创作，通过专属参数清晰区分产品信息、口吻对标、内容对标及历史文案，批量生成高质量脚本，原生支持PDF/Word。
根据IP背景和视频文案，为短视频生成一套完整的发布策略，包括发布时间、话题标签、封面文案和发布标题，并能将文案合成为封面图。
>
Fetch financing event lists from the iYiou skill API and generate a daily financing report in Markdown to stdout. Use when the task asks to pull investment/financing events via `https://api.iyiou.com/skill/info?page=...&pageSize=...`, paginate with `pageSize=10` and `page<=5`, deduplicate records, default to yesterday's date, and optionally use today's date only when explicitly requested by the user.
Call Craftsman Agent API OneKey Router to generate a LEGO 3D step-by-step instruction build plan.
Call Craftsman Agent API OneKey Router to generate a Minecraft 3D scene build plan.
Call Craftsman Agent API OneKey Router to generate Tesla Car Wrap Images and Paints that will display on 3D screen.
Auto-generated skill for perplexity tools via OneKey Gateway.
Generate standardized HR workforce dashboards from Excel files: 5 fixed dashboards covering headcount trends, regional distribution, detailed breakdowns, attrition analysis, and contractor/partner distribution. Outputs a self-contained interactive HTML with ECharts charts, one-click email generation, and clipboard copy.
Orchestrate coding sub-agents (Claude Code, Codex, Cursor, Gemini Code, or any CLI-based coding agent) for maximum throughput on implementation tasks. Use when: (1) writing or modifying code files, (2) running scripts or data pipelines, (3) batch processing large datasets, (4) multi-stage workflows requiring parallel execution. Covers agent-agnostic dispatch templates, task decomposition, parallel coordination, and acceptance criteria. NOT for: simple file reads, config-only changes, or sending messages. Core principle — the orchestrator plans; the coding agents execute.
STM32CubeMX CLI operations for configuring pins, peripherals, DMA, interrupts, and generating code. Use cases: (1) Add/modify STM32 peripheral configuration (2) Configure USART/SPI/I2C/ADC/TIM peripherals (3) Set up DMA and interrupts (4) Generate CMake/GCC project code. Default target MCU: STM32F103C8Tx.
使用多模态大模型理解图片内容，生成业务含义描述。支持多种模型：(1) MiniMax VLM (2) OpenAI GPT-4V (3) Claude Vision。用于理解截图、图表、文档照片等，生成精准的文字描述。
将任意多媒体文档导入 Obsidian 知识库。支持 PPT、PDF、DOCX、图片等格式，自动提取每一页/每一张图片，使用多模态模型理解内容，生成文字描述后存入 OB。适用于：(1) 整理培训课件 (2) 迁移笔记到 OB (3) 将图片资料转为结构化知识。
分段式 Jupyter Notebook 生成与修改工具。当用户需要创建、分段追加、修改、合并 Jupyter Notebook (.ipynb) 时使用此技能。支持的高级功能包括：(1) 分段多次生成 Notebook 内容，避免一次性生成过大导致超时或内容截断；(2) 本地图片 base64 嵌入到 Markdown cell；(3) 内置哈希判题系统（不显示明文答案）；(4) 灵活的 cell 级增删改查；(5) 合并多个 notebook 为一个；(6) 导出为纯 Python 脚本；(7) 自动生成目录；(8) Cell 标签分组与重排序。适用场景包括教学课件、编程练习、技术教程、学习笔记等 notebook 的创建与维护。
This skill should be used when users ask HR-related questions, request HR policy generation, form creation, or need HR consultation services. It provides direct WebSocket API integration with the HRrule AI platform using tag_id and rt parameters for generating HR policies, forms, flowcharts, and answering HR-related questions about labor laws, recruitment, compensation, employee rights, and other HR topics. The skill includes professional Q&A capability (tag_id=1) for answering general HR questions about labor laws, regulations, and employee rights.
每日一报生产引擎。从用户画像出发，自动采集多平台资讯，筛选去噪，AI 生成结构化日报，渲染为 HTML。
🦞 AI小龙虾社区 Skill —— 为 AI小龙虾用户提供智能社交分身能力。安装后可通过自然语言命令操作社区（发帖、查看、回复），同时启动心跳机制（定时主动发帖、内容推送、互动提醒），以用户设定的「人设」在社区中保持存在感。适用场景：当用户想加入龙虾圈、配置AI分身、发布社区动态、查看社区内容、设置心跳频率、邀请好友时，应加载此 Skill。
Generate text embeddings via AIMLAPI. Use for semantic search, clustering, or high-dimensional text representations with text-embedding-3-large and other models.
Generate images or videos via AIMLAPI from prompts. Use when Codex needs reliable AI/ML API media generation with retries, explicit User-Agent headers, and async video polling.
Scrape blogs/essay sites and compile into Kindle-friendly EPUB with AI-generated cover. Use for requests to download blogs for Kindle, compile essays into ebook, or send blog archives to Kindle. Supports Paul Graham, Kevin Kelly, Derek Sivers, Wait But Why, Astral Codex Ten, and custom sites.
Generate photorealistic rendering scripts for PyMOL and UCSF ChimeraX.
Generate CIOMS-compliant adverse event narratives for Individual Case
Generate interactive anatomy quizzes for medical education with multiple
Humanize murine antibody sequences using CDR grafting and framework
Use when determining author order on research manuscripts, assigning CRediT contributor roles for transparency, documenting individual contributions to collaborative projects, or resolving authorship disputes in multi-institutional research. Generates fair and transparent authorship assignments following ICMJE guidelines and CRediT taxonomy. Helps research teams document contributions, resolve disputes, and ensure equitable credit distribution in academic publications.