Productivity AI agent skills

4,613 skills in the archive. Read a skill’s instructions or open its original repository.

• Shushu Internship Tool

  by @LiuMengxuan04

  Use when an AI assistant helps computer-industry internship candidates with 鼠鼠实习妙妙工具 quickly turn a target job description into a resume-ready and interview-ready project across backend, frontend, full-stack, mobile, testing,…

• Desktop Screenshot

  by @openakita

  Capture Windows desktop screenshot with automatic file saving. When you need to show desktop state, capture application windows, or record operation results. IMPORTANT - must actually call this tool, never say 'screenshot done'…

• Desktop Type

  by @openakita

  Type text at current cursor position in desktop applications. When you need to enter text in dialogs, fill input fields, or type in text editors. Supports Chinese input. For browser webpage forms, use browser_type instead.

• Enable Thinking

  by @openakita

  Control deep thinking mode. Default enabled. For very simple tasks (simple reminders, greetings, quick queries), can temporarily disable to speed up response. Auto-restores to enabled after completion.

• Get Image File

  by @openakita

  Get local file path of image sent by user. When user sends image, system auto-downloads it. When you need to process user's image or analyze image content.

• Create Todo

  by @openakita

  MUST CALL FIRST for multi-step tasks! If user request needs 2+ tool calls (like 'open + search + screenshot'), call create_todo BEFORE any other tool.

• Skill Creator

  by @omnimind-ai

  Guide for creating and updating effective Omnibot skills. Use when the user wants to add a new skill or improve an existing skill for the built-in {{OMNIBOT_TERMINAL_DISTRIBUTION}} workspace, tool workflows, or reusable domain…

• Obsidian Kb/Ofm Guide

  by @openakita

  Guide for creating and editing Obsidian notes using Obsidian Flavored Markdown (OFM). Covers wikilinks, embeds, callouts, YAML properties, and knowledge organization best practices.

• Openakita/Skills@Dingtalk Cli

  by @openakita

  DingTalk Workspace CLI (dws) - officially open-sourced cross-platform CLI tool from DingTalk. Provides 86 commands across 12 products: Contact, Chat, Bot, Calendar, Todo, Approval, Attendance, Ding, Report, AITable, Workbench,…

• Openakita/Skills@Obsidian Skills

  by @openakita

  Manage Obsidian vaults with full support for Obsidian Flavored Markdown — wikilinks, embeds, callouts, YAML properties, Dataview queries, Canvas, and Bases. Organize notes using MOCs (Maps of Content), atomic note principles,…

• Openakita/Skills@Google Calendar Automation

  by @openakita

  Automate Google Calendar events, scheduling, availability checks, and attendee management via Rube MCP (Composio). Create events, find free slots, manage attendees, and list calendars programmatically.

• Obra/Superpowers@Brainstorming

  by @openakita

  You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

• Oneskill

  by @xu-xiang

  发现技能（Skill），迭代查询，并在任何环境中自动安装技能。

• Market Research

  by @xu-xiang

  开展市场研究、竞争分析、投资者尽职调查和行业情报收集，提供来源引用和决策导向的总结。适用于用户需要市场规模测算、竞争对手比较、基金研究、技术扫描或为业务决策提供信息支持的研究场景。

• Verification Loop

  by @xu-xiang

  为 Claude Code 会话提供的全面验证系统。

• Investor Outreach

  by @xu-xiang

  草拟冷邮件、热情介绍简介、跟进邮件、更新邮件和投资者沟通以筹集资金。当用户需要向天使投资人、风险投资公司、战略投资者或加速器进行推广，并需要简洁、个性化的面向投资者的消息时使用。

• Liquid Glass Design

  by @xu-xiang

  iOS 26 液态玻璃设计系统 — 适用于 SwiftUI、UIKit 和 WidgetKit 的动态玻璃材质，具有模糊、反射和交互式变形效果。

• Swift Concurrency 6 2

  by @xu-xiang

  Swift 6.2 可接近的并发性 — 默认单线程，@concurrent 用于显式后台卸载，隔离一致性用于主 actor 类型。

• Regex Vs Llm Structured Text

  by @xu-xiang

  选择在解析结构化文本时使用正则表达式还是大型语言模型的决策框架——从正则表达式开始，仅在低置信度的边缘情况下添加大型语言模型。

• Swift Actor Persistence

  by @xu-xiang

  在 Swift 中使用 actor 实现线程安全的数据持久化——基于内存缓存与文件支持的存储，通过设计消除数据竞争。

• Skill Stocktake

  by @xu-xiang

  用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估。

• Search First

  by @xu-xiang

  研究优先于编码的工作流程。在编写自定义代码之前，搜索现有的工具、库和模式。调用研究员代理。

• Dws

  by @Pinvou

  【何时用:仅当用户明确指向钉钉/DingTalk(钉钉文档、钉钉日程等)时使用;泛指做文档/表格/待办/审批默认走本地工具,不要误用钉钉】用 dws CLI…

• Lark Task

  by @Pinvou

  【何时用:仅当用户明确指向飞书/Lark(发到飞书、飞书文档等)时使用;泛指做个文档或PPT或表格或方案默认走本地工具,不要误用飞书】飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册任务智能体、更新任务智能体主页…

• Lark Calendar

  by @Pinvou

  【何时用:仅当用户明确指向飞书/Lark(发到飞书、飞书文档等)时使用;泛指做个文档或PPT或表格或方案默认走本地工具,不要误用飞书】飞书日历:管理日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。不负责:查询视频会议记录(本 skill 只覆盖日程;lark-vc 技能未随包收录,可 CLI 直连,见意图路由)、待办任务(走 lark-task)。

• Wecomcli Calendar

  by @Pinvou

  何时用:仅当用户明确指向企业微信日程/会议室预订/忙闲时使用;泛指记事、提醒、本地日程默认走本地工具,在线会议走 wecomcli-meeting。企微日程:预约/预订会议室/查看/更新/取消/查忙闲;仅说'开会/约个会'未明确日程还是在线会议时,先按本技能消歧流程追问,不可臆断直接创建。

• Wecomcli Meeting

  by @Pinvou

  何时用:仅当用户明确指向企业微信『在线会议』(含会议号/入会链接、可远程参会)时使用;泛指约会默认先按消歧流程确认,纯日程走 wecomcli-calendar。企微会议全生命周期:创建、查询、搜索、详情(含纪要/待办)、转写原文逐字记录、更新、取消;仅说'开会/约个会'未明确类型时先追问确认,不可臆断直接创建。

• Wecomcli Todo

  by @Pinvou

  何时用:仅当用户明确指向企业微信待办(建/查/改企微待办)时使用;泛指记个待办/提醒默认走本地工具,不要误用。企微待办:创建、删除或退出、完成、查询和筛选,以及修改标题、描述、参与人名单和截止时间。

• Create Mcp Servers

  by @glittercowboy

  Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol.…

• Setup Ralph

  by @glittercowboy

  Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in any directory with proper structure, prompts, and backpressure.

• Create Meta Prompts

  by @glittercowboy

  Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research…

• Create Slash Commands

  by @glittercowboy

  Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.

• Seedance Game Ui Livestream

  by @LearnPrompt

  The screen itself is the shot: a fake gameplay capture, livestream or desktop recording. It holds up when the overlay layer is pinned to fixed positions and its numbers and banners change in step with the action. Use when the…

• Seedance Retro Dv Home Video

  by @LearnPrompt

  The period feel comes from camera defects and one tiny everyday incident. Write the camcorder's autofocus hunting, exposure shifts and handheld shake as an explicit list, keep the story small, and the clip reads as a real old…

• Seedance Storyboard Grid To Video

  by @LearnPrompt

  Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. The sheet owns order, framing and timing, and the video prompt only has to connect the panels. Use…

• Seedance 3d Cartoon

  by @LearnPrompt

  One small anthropomorphic character carries the whole film. Spell out its looks part by part, write the style as render settings you can measure, and cut the timeline so each block holds a single action goal. Use when the user…

• Seedance Epic Fantasy Scifi

  by @LearnPrompt

  Monsters, dragons, world reveals. Each entity gets its own definition block, the shots are cut by timecode, and scale is bought with reference objects and low angles rather than words like massive. Use when the user wants a…

• Seedance Food Asmr

  by @LearnPrompt

  Cooking close-ups, mukbang and eating vlogs. They work when every beat shows one visible change in the food and one matching sound, and the dish stays the same dish from first frame to last. Use when the user wants a Seedance…

• Seedance Sports Extreme

  by @LearnPrompt

  The clip lives or dies on the action loop. Write every link from run-up to landing in order, name the physics you want by part, and spend the negative list on flying, hovering and teleporting. Use when the user wants a Seedance…

• Seedance Horror Suspense

  by @LearnPrompt

  Every shot carries its own timecode and shows one visible change on a body. The dread comes from the chain — a look, veins, a bite, the next person — and the ending seals a door without settling anything. Use when the user wants…

• Seedance Meme Comedy

  by @LearnPrompt

  A short skit where every beat is laid down to serve one punchline. The joke has to land on something visible, and the absurdity only works when the camera and the physics stay dead serious. Use when the user wants a Seedance 2.5…

• Seedance Travel City Walk

  by @LearnPrompt

  One traveller moves through a place scene by scene, each scene carrying its own timecode, its own location and one short line. The polish is bought with film grain and golden-hour light. Use when the user wants a Seedance 2.5 /…

• Seedance Car Vehicle

  by @LearnPrompt

  The machine has to stay one machine while the camera does all the work. Lock the vehicle part by part, then fill the runtime with a numbered cut list that moves the camera every second. Use when the user wants a Seedance 2.5 /…

• Seedance Fashion Lookbook

  by @LearnPrompt

  One person, one look, a handful of places. A head-to-toe appearance lock carries the whole clip, and each scene gets one location, one gesture and one kind of light. Use when the user wants a Seedance 2.5 / 2.0 video prompt for…

• Seedance Pet Animal

  by @LearnPrompt

  The animal is the lead and a phone is the only camera. Lock the count to exactly one, keep the animal behaving like an animal, and let the payoff come from it closing in on the lens. Use when the user wants a Seedance 2.5 / 2.0…

• Continuous Learning V2

  by @xu-xiang

  一种基于本能（Instinct）的训练系统，通过钩子（Hooks）观察会话，创建带有置信度评分的原子化本能，并将其进化为技能（Skills）、命令（Commands）或智能体（Agents）。

• Continuous Learning V2

  by @xu-xiang

  基于本能的学习系统，通过钩子观察会话，创建具有置信度评分的原子本能，并将其进化为技能/命令/代理。

• Security Scan

  by @xu-xiang

  使用 AgentShield 扫描 Claude Code 配置（.claude/ 目录）中的安全漏洞、配置错误和注入风险。检查 CLAUDE.md、settings.json、MCP 服务端、钩子（Hooks）和智能体（Agents）定义。

• Database Migrations

  by @xu-xiang

  数据库迁移最佳实践，涵盖模式变更、数据迁移、回滚以及零停机部署，适用于PostgreSQL、MySQL及常用ORM（Prisma、Drizzle、Django、TypeORM、golang-migrate）。

• Springboot Tdd

  by @xu-xiang

  使用 JUnit 5, Mockito, MockMvc, Testcontainers 和 JaCoCo 进行 Spring Boot 的测试驱动开发（TDD）。适用于添加新功能、修复 bug 或重构场景。

• Content Engine

  by @xu-xiang

  为X、LinkedIn、TikTok、YouTube、新闻通讯和跨平台重新利用的多平台活动创建平台原生内容系统。适用于当用户需要社交媒体帖子、帖子串、脚本、内容日历，或一个源资产在多个平台上清晰适配时。

• Configure Ecc

  by @xu-xiang

  Everything Claude Code 的交互式安装程序 —— 引导用户将技能（Skills）和规则（Rules）安装到用户级或项目级目录，验证路径，并在需要时优化已安装的文件。

• Investor Materials

  by @xu-xiang

  创建和更新宣传文稿、一页简介、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文件、预测、资金用途表、里程碑计划或必须在多个融资资产中保持内部一致性的材料时使用。

• Article Writing

  by @xu-xiang

  根据提供的示例或品牌指导，以独特的语气撰写文章、指南、博客帖子、教程、新闻简报等长篇内容。当用户需要超过一段的精致书面内容时使用，尤其是当语气一致性、结构和可信度至关重要时。

• Django Tdd

  by @xu-xiang

  Django 测试策略，包括 pytest-django、TDD 方法、factory_boy、模拟、覆盖率以及测试 Django REST Framework API。

• Nutrient Document Processing

  by @xu-xiang

  使用 Nutrient DWS API 进行文档处理、转换、OCR、提取、脱敏、签名以及表单填充。支持 PDF、DOCX、XLSX、PPTX、HTML 和图像格式。

• Tdd Workflow

  by @xu-xiang

  在创建新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发（TDD），要求包括单元测试、集成测试和 E2E 测试在内的测试覆盖率达到 80% 以上。

• Configure Ecc

  by @xu-xiang

  Everything Claude Code 的交互式安装程序 — 引导用户选择并安装技能和规则到用户级或项目级目录，验证路径，并可选择优化已安装文件。

• Foundation Models On Device

  by @xu-xiang

  苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用，以及在iOS 26+中的快照流。

• Springboot Patterns

  by @xu-xiang

  Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理与日志。适用于 Java Spring Boot 后端开发。

• Continuous Learning

  by @xu-xiang

  自动从 Claude Code 会话（Session）中提取可重用的模式（Pattern），并将其作为已学习的技能（Skill）保存以备将来使用。

• Cpp Coding Standards

  by @xu-xiang

  基于C++核心指南（isocpp.github.io）的C++编码标准。在编写、审查或重构C++代码时使用，以强制实施现代、安全和惯用的实践。

• Java Coding Standards

  by @xu-xiang

  适用于 Spring Boot 服务的 Java 编码规范：命名、不可变性、Optional 使用、流（Stream）、异常、泛型及项目布局。

• Springboot Security

  by @xu-xiang

  Spring Boot 服务的 Spring Security 身份验证/授权、验证、CSRF、密钥、响应头、速率限制和依赖项安全最佳实践。

• Strategic Compact

  by @xu-xiang

  建议在逻辑间隔处进行手动压缩（Manual Compaction），以在整个任务阶段保持上下文（Context），而非随意的自动压缩。

• Python Testing

  by @xu-xiang

  使用 pytest、TDD 方法论、固件（Fixtures）、模拟（Mocking）、参数化及覆盖率要求的 Python 测试策略。

• Cpp Testing

  by @xu-xiang

  仅在创建/更新/修复 C++ 测试、配置 GoogleTest/CTest、诊断失败或不稳定的测试、以及添加覆盖率或消毒器时使用。

• Jpa Patterns

  by @xu-xiang

  Spring Boot 中用于实体设计、关联关系、查询优化、事务、审计、索引、分页和连接池的 JPA/Hibernate 模式。

• Backend Patterns

  by @xu-xiang

  后端架构模式、API 设计、数据库优化以及 Node.js、Express 和 Next.js API 路由的服务端最佳实践。

• Backend Patterns

  by @xu-xiang

  后端架构模式、API设计、数据库优化以及适用于Node.js、Express和Next.js API路由的服务器端最佳实践。

• Cpp Testing

  by @xu-xiang

  仅用于编写/更新/修复C++测试、配置GoogleTest/CTest、诊断失败或不稳定的测试，或添加覆盖率/消毒器时使用。

• Coding Standards

  by @xu-xiang

  适用于TypeScript、JavaScript、React和Node.js开发的通用编码标准、最佳实践和模式。

• Python Patterns

  by @xu-xiang

  Pythonic 惯用法、PEP 8 标准、类型提示，以及构建稳健、高效且可维护 Python 应用的最佳实践。

• Deployment Patterns

  by @xu-xiang

  部署工作流、CI/CD流水线模式、Docker容器化、健康检查、回滚策略以及Web应用程序的生产就绪检查清单。

• Coding Standards

  by @xu-xiang

  TypeScript、JavaScript、React、Node.js 开发的通用编码标准、最佳实践和模式。

• Golang Testing

  by @xu-xiang

  Go测试模式包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循TDD方法论，采用地道的Go实践。

• E2e Testing

  by @xu-xiang

  Playwright E2E 测试模式、页面对象模型、配置、CI/CD 集成、工件管理和不稳定测试策略。

• Postgres Patterns

  by @xu-xiang

  PostgreSQL 数据库模式，涵盖查询优化、架构设计、索引和安全。基于 Supabase 最佳实践。

• Api Design

  by @xu-xiang

  REST API设计模式，包括资源命名、状态码、分页、过滤、错误响应、版本控制和生产API的速率限制。

• Django Security

  by @xu-xiang

  Django 安全最佳实践、认证、授权、CSRF 防护、SQL 注入预防、XSS 预防和安全部署配置。

• Docker Patterns

  by @xu-xiang

  用于本地开发的Docker和Docker Compose模式，包括容器安全、网络、卷策略和多服务编排。

• Cost Aware Llm Pipeline

  by @xu-xiang

  LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。

• Continuous Learning

  by @xu-xiang

  自动从Claude Code会话中提取可重复使用的模式，并将其保存为学习到的技能以供将来使用。

• Golang Patterns

  by @xu-xiang

  构建健壮、高效且可维护 Go 应用程序的惯用法（Idiomatic Go）、最佳实践与规范。

• Clickhouse Io

  by @xu-xiang

  ClickHouse 数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。

• Clickhouse Io

  by @xu-xiang

  ClickHouse数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。

• Frontend Patterns

  by @xu-xiang

  适用于 React、Next.js、状态管理、性能优化和 UI 最佳实践的前端开发模式。

• Content Hash Cache Pattern

  by @xu-xiang

  使用SHA-256内容哈希缓存昂贵的文件处理结果——路径无关、自动失效、服务层分离。

• Eval Harness

  by @xu-xiang

  Claude Code 会话的正式评测框架，实现了评测驱动开发（EDD）原则

• Frontend Patterns

  by @xu-xiang

  React、Next.js、状态管理、性能优化和UI最佳实践的前端开发模式。

• Iterative Retrieval

  by @xu-xiang

  为了解决子智能体（Sub-agent）的上下文问题，逐步优化上下文获取的模式

• Golang Patterns

  by @xu-xiang

  用于构建健壮、高效且可维护的Go应用程序的惯用Go模式、最佳实践和约定。

• Eval Harness

  by @xu-xiang

  克劳德代码会话的正式评估框架，实施评估驱动开发（EDD）原则

• Golang Testing

  by @xu-xiang

  保证测试驱动开发与 Go 代码高质量的全面测试策略。

• Node

  by @mcollina

  Provides domain-specific best practices for Node.js development with TypeScript, covering type stripping, async patterns, error handling, streams, modules, testing, performance, caching, logging, and more. Use when setting up…

• Skill Optimizer

  by @mcollina

  Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking…

• Methods Reverse Engineer

  by @aipoch

  Reverse-engineers the methods section of a biomedical paper into a structured, reproducible workflow. Use this skill when a user wants to understand how a study was actually executed, extract data sources, inclusion/exclusion…

• Clinical Question Clarifier

  by @aipoch

  Clarifies a vague clinical or biomedical research idea into a structured, bounded, searchable, researchable, and testable question. Always use this skill whenever a user has an early-stage clinical or research thought, an…

• Replica Architect

  by @Jakeschincariol

  Plans the stack, database schema and API for an app clone, from the recon map replica-recon wrote. Picks boring, managed tech, turns the inferred data model into real SQL with indexes and access rules, lists every route by flow,…

• Replica Backend

  by @Jakeschincariol

  Builds the backend of an app clone: auth, database migrations and access rules, payments with Stripe, email, background jobs and third-party integrations through official APIs only, plus a security checklist. Use when the user…