split-commits
智能拆分暂存区的代码变更为多个符合 Conventional Commits 规范的逻辑提交。当用户需要将大量变更按逻辑关系分组提交时使用,比如"拆分这些提交"、"把暂存区的变更分成多个 commit"、"按功能分别提交"、"split commits"等场景。特别适合处理包含多个模块、多种类型文件(配置、代码、测试、文档)的复杂变更集。
deepagents-filesystem
使用 FilesystemMiddleware 实现虚拟文件系统、后端（State、Store、Filesystem、Composite）和 Deep Agents 的上下文管理。
deepagents-cli
使用 Deep Agents CLI - 终端界面、持久化内存（AGENTS.md）、项目约定、技能目录和 CLI 命令。
Humanizer
|
deepagents-skills
在 Deep Agents 中创建和使用自定义技能，实现渐进式披露、SKILL.md 格式和 Agent Skills 协议。
subagent-creator
创建具有自定义系统提示和工具配置的专业化 Claude Code 子代理。当用户要求创建新的子代理、自定义代理、专业助手，或为 Claude Code 配置特定任务的 AI 工作流时使用。
agent-browser
AI 代理的浏览器自动化 CLI 工具。当用户需要与网站交互时使用，包括导航页面、填写表单、点击按钮、截图、提取数据、测试 Web 应用或自动化任何浏览器任务。触发场景包括"打开网站"、"填写表单"、"点击按钮"、"截图"、"从页面抓取数据"、"测试这个 Web 应用"、"登录网站"、"自动化浏览器操作"或任何需要编程式 Web 交互的任务。
changelog
基于 git commits 自动生成 CHANGELOG.md 变更日志。支持语义化版本、分类整理、多格式输出。触发场景包括"生成变更日志"、"更新 CHANGELOG"、"版本记录"。
cli-developer
构建CLI工具、实现参数解析或添加交互式提示时使用。用于CLI设计、参数解析、交互式提示、进度指示器、Shell自动补全。
code-fragment-extractor
仔细彻底阅读探索用户提供的代码目录/文件，分析拆解出对应的代码片段以供参考，颗粒度细到功能级别，只做片段提取不改变代码内容和页面布局结构，提取到./fragment-extractor目录下，按照指定模板格式生成代码片段模板文件，确保功能完整性和代码片段的实际性。
component-docs-batcher
批量生成和维护前端组件库文档的自动化工具。专为 Monorepo 组件库设计（如 atom-ui-mobile），通过对比组件文件和文档的修改时间，自动生成任务清单并批量生成符合规范的完整组件文档。支持以下场景：(1) 定期批量更新组件文档，(2) 单个组件文档维护，(3) 新组件文档初始化。自动识别主要组件文件，跳过 index.ts、store、hooks 等辅助文件，文档路径为组件目录下的 index.zh-CN.md。
doc-coauthoring
引导用户通过结构化的工作流协作编写文档。当用户想要编写文档、提案、技术规范、决策文档或类似的结构化内容时使用。此工作流帮助用户高效地传递上下文、通过迭代优化内容,并验证文档是否适合读者阅读。当用户提到编写文档、创建提案、起草规范或类似文档任务时触发。
deepagents-overview
理解 Deep Agents 框架 - 它们是什么、如何使用 createDeepAgent 创建，以及 agent harness 架构，包括内置的规划、文件系统和子代理中间件。
deepagents-memory
在 Deep Agents 中实现长期内存，使用 StoreBackend、CompositeBackend 和 InMemoryStore 进行跨会话的持久化数据存储。
deepagents-hitl
在 Deep Agents 中实现人工审批工作流，使用 interruptOn 参数对敏感工具操作进行人工干预。
apifox-mock-script-gen
|
AI Camera Director
生成专业视频运镜提示词，支持单镜头和分镜脚本。关键词：video prompt, camera movement, 运镜, storyboard, 分镜, Sora, Runway, Pika。
better-i18n
>-
ado-operation
Azure DevOps operations via Azure CLI. Use for Work Item management (create, update, query, link), Pull Request operations (create, review, vote, merge), Pipeline management (run, monitor, logs), and repository operations. Triggers on: Azure DevOps, work item, PR, pipeline, sprint, backlog, boards, repos, WIQL queries.
presentation-creator
Marpを使用した提案資料・比較検討資料の作成スキル。課題提示、複数案の比較検討、メリット・デメリット整理を含む資料を作成する。使用場面：(1) 技術選定や方式比較の検討資料、(2) 提案書・企画書、(3) 問題解決策の提示、(4) 意思決定を支援するドキュメント。作成完了後は必ずサブエージェントでレビューを実施する。
drawio-diagram
Create and open Draw.io diagrams from XML, CSV, or Mermaid syntax. Use when creating architecture diagrams, flowcharts, sequence diagrams, ER diagrams, org charts, or network diagrams.
copilot-delegate
Copilot CLIに処理を委譲するスキル。ユーザーが「Copilotに聞いて」「Copilotで確認して」「Copilotに任せて」などと明示的に依頼したときに使用する。GitHub Copilot CLIの機能を活用して、コマンドの提案やGit操作の説明などを取得する。
skill-generator
Create, validate, and package Claude skills with structured workflows. Use when creating a new skill, updating an existing skill, or packaging a skill for distribution.
save-report
コードレビュー・調査・バグ解析などの結果をHTMLドキュメントとして保存するスキル。「レポートを保存して」「結果をまとめて」「HTMLに出力して」「ドキュメントに残して」「保存しておいて」「調査結果をファイルにして」などと言われたときに必ず使用する。会話の内容から種別を自動判定し、output-config.toml に設定された保存先へ番号付きHTMLファイルを生成する。コードレビュー、バグ調査、コード調査、リサーチ結果のどれにでも対応。
claude-code-guide
|
claude-agent-ruby
Implement or modify Ruby code that uses the claude-agent-sdk gem, including query() one-shot calls, Client-based interactive sessions, streaming input, option configuration, tools/permissions, hooks, SDK MCP servers, structured output, budgets, sandboxing, session resumption, Rails integration, and error handling.
gemini-api
Delegate tasks to Google Gemini 3 series models via REST API. Use when tasks benefit from Gemini's multimodal capabilities - image generation (Nano Banana Pro), image editing (Nano Banana Pro), image understanding/vision (Gemini 3.1 Pro), or text tasks (Gemini 3.1 Pro). Always prioritize Pro models.
openjung-api
|
vue-composables
Patterns for Vue 3 composables with localStorage persistence in Nuxt 4. Activate when creating composables, working with useProgress, useQuiz, useCertificate, or localStorage.
quiz-system
Knowledge for implementing the LMS quiz system with Nuxt UI. Activate when working with quiz components, question types, scoring, or quiz-related composables.
nuxt-ui
Expert knowledge for Nuxt UI v4 components and patterns. Activate when creating UI components, working with buttons, cards, forms, or any Nuxt UI component.
ui-ux-design
UI/UX design patterns and best practices for the LMS. Activate when designing pages, creating layouts, working on user experience, or building navigation.
svg-illustrations
Expert knowledge for creating hand-drawn style SVG illustrations. Activate when creating custom diagrams, working with illustration components, or needing consistent visual design for lessons.
nuxt-content
Expert knowledge for @nuxt/content module in Nuxt 4. Activate when working with content directory, markdown files, frontmatter, or ContentRenderer.
cheat-sheets
Expert knowledge for creating effective cheat sheets with PDF export. Activate when creating/editing cheat sheet content, designing quick reference sheets, or working with PDF export functionality. (project)
monetization
Integrate PayMCP into an MCP server to monetize tools (pay-per-request pricing or subscriptions), configure payment providers (traditional and/or X402), choose an appropriate coordination mode, and validate the integration.
screenshot-ui-analyzer
Takes a screenshot, analyzes it using AI (Gemini Vision) to detect UI elements with bounding boxes, names, and descriptions, saves to JSON, and generates an annotated image. Use when you need to identify and label screen elements with advanced AI. Key commands: screenshot, analyze, annotate.
whatsapp-agent
Enviar mensajes de WhatsApp (contactos y grupos) reutilizando las secuencias existentes de macro-agent. Los mensajes se procesan para estar en minúsculas y sin acentos. Comandos: list, send <contacto> <mensaje>.
web-fetch
HTTP requests (GET/POST/PUT/DELETE) to URLs. Use for API calls, endpoint testing, or basic scraping.
process-monitor
Shows system processes sorted by CPU or memory, load average, RAM usage and uptime. Use for performance monitoring.
macro-agent
Desktop macro control with image recognition. Commands: find, search, click-on, click, move-to, write, press, hotkey, scroll, drag, screenshot, region-capture, seq-create/add/run/list/delete. ALWAYS uses template matching (image search), NEVER fixed coordinates. Use 'region-capture' to capture new elements.
datetime-info
Shows current date and time in multiple formats. Use when you need timestamps, day of week, or formatted dates.
Code Review
Guidelines for reviewing and improving code quality in YT Lite v3.
skill-finder
Search for and install new skills from the open-source community (GitHub/SkillsMP) to extend capabilities.
Implement Feature
A workflow for implementing new features in YT Lite v3, covering backend (FastAPI), frontend (templates/static), and design aesthetics.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
gpt-prompting
Prompt patterns, reusable system-prompt blocks, and a migration checklist for GPT-5.2 (GPT-5-class) models. Use when you need to (1) write/refine prompts for GPT-5.2 production agents, (2) clamp verbosity/output shape, (3) prevent scope drift (esp. frontend/UX and over-building), (4) handle ambiguity and reduce hallucinations, (5) improve tool grounding + structured extraction, or (6) migrate prompts from GPT-5/5.1/4.1/4o to GPT-5.2 with stable reasoning_effort.
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Page 1350 of 1570 · 78471 results
