brainstorming

• 说明： 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.
• 场景： 内容与设计
• 结构： 66/100（较完整）；scripts 5、references 0、assets 0
• 风险： 中（会执行命令或脚本；包含可执行脚本）
• 来源路径： skills/brainstorming/SKILL.md

dispatching-parallel-agents

• 说明： Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
• 场景： 其他场景
• 结构： 71/100（较完整）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/dispatching-parallel-agents/SKILL.md

executing-plans

• 说明： Use when you have a written implementation plan to execute in a separate session with review checkpoints
• 场景： 其他场景
• 结构： 61/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 中（会执行命令或脚本）
• 来源路径： skills/executing-plans/SKILL.md

accessibility

• 说明： Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA
• 场景： 编程与代码审查
• 结构： 61/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/accessibility/SKILL.md

agent-architecture-audit

• 说明： Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
• 场景： 方法论与协作
• 结构： 51/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 中（会执行命令或脚本）
• 来源路径： skills/agent-architecture-audit/SKILL.md

agent-eval

• 说明： Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
• 场景： 编程与代码审查
• 结构： 64/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 中（会执行命令或脚本；可能访问网络或 API）
• 来源路径： skills/agent-eval/SKILL.md
• Skill 声明许可证： MIT

ask-matt

• 说明： Ask which skill or flow fits your situation. A router over the skills in this repo.
• 场景： 编程与代码审查
• 结构： 51/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 高（涉及凭据或密钥）
• 来源路径： skills/engineering/ask-matt/SKILL.md

code-review

• 说明： Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a…
• 场景： 文档与办公
• 结构： 61/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/engineering/code-review/SKILL.md

codebase-design

• 说明： Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
• 场景： 编程与代码审查
• 结构： 61/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/engineering/codebase-design/SKILL.md

n8n:community-pr-readiness-check

• 说明： >-
• 场景： 编程与代码审查
• 结构： 43/100（信息有限）；scripts 0、references 0、assets 0
• 风险： 中（会执行命令或脚本；声明了预授权工具）
• 来源路径： .agents/skills/community-pr-readiness-check/SKILL.md

n8n:content-design

• 说明： Product content designer for UI copy. Use when writing, reviewing, or auditing user-facing text: button labels, error messages, tooltips, empty states, modal copy, placeholder text, confirmation dialogs, onboarding flows, or i18n strings. Also use when the user says /copy, /content, or /ux-copy.
• 场景： 内容与设计
• 结构： 68/100（较完整）；scripts 0、references 0、assets 0
• 风险： 高（涉及凭据或密钥）
• 来源路径： .agents/skills/content-design/SKILL.md

n8n:conventions

• 说明： Quick reference for n8n patterns. Full docs /AGENTS.md
• 场景： 其他场景
• 结构： 40/100（信息有限）；scripts 0、references 0、assets 0
• 风险： 高（涉及凭据或密钥）
• 来源路径： .agents/skills/conventions/SKILL.md

algorithmic-art

• 说明： Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
• 场景： 内容与设计
• 结构： 58/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/algorithmic-art/SKILL.md
• Skill 声明许可证： Complete terms in LICENSE.txt

brand-guidelines

• 说明： Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
• 场景： 内容与设计
• 结构： 48/100（基础可读）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/brand-guidelines/SKILL.md
• Skill 声明许可证： Complete terms in LICENSE.txt

canvas-design

• 说明： Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
• 场景： 内容与设计
• 结构： 68/100（较完整）；scripts 0、references 0、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： skills/canvas-design/SKILL.md
• Skill 声明许可证： Complete terms in LICENSE.txt

chatgpt-app-builder

• 说明： DEPRECATED: This skill has been replaced by mcp-app-builder. Check if mcp-app-builder is available in the skills folder. If not, install it: npx skills install mcp-use/mcp-use --skill mcp-app-builder Use mcp-app-builder instead of this skill. Build ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK. Use when creating ChatGPT app…
• 场景： Agent 构建
• 结构： 76/100（较完整）；scripts 0、references 9、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md

mcp-apps-builder

• 说明： MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or perfor…
• 场景： 方法论与协作
• 结构： 76/100（较完整）；scripts 0、references 18、assets 0
• 风险： 高（涉及部署或发布；涉及凭据或密钥）
• 来源路径： generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md

mcp-builder

• 说明： DEPRECATED: This skill has been replaced by mcp-app-builder. Check if mcp-app-builder is available in the skills folder. If not, install it: npx skills install mcp-use/mcp-use --skill mcp-app-builder Use mcp-app-builder instead of this skill. Build Model Context Protocol (MCP) servers with mcp-use framework. Use when creating MCP servers, defining t…
• 场景： Agent 构建
• 结构： 76/100（较完整）；scripts 0、references 5、assets 0
• 风险： 低（未发现脚本、预授权工具或明显写入操作）
• 来源路径： generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md

agent-tui

• 说明： Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the tui_tester subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection. Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior. Also use when: user asks "what is agent-tui"…
• 场景： 方法论与协作
• 结构： 71/100（较完整）；scripts 0、references 0、assets 0
• 风险： 高（涉及凭据或密钥）
• 来源路径： .gemini/skills/agent-tui/SKILL.md

async-pr-review

• 说明： Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
• 场景： 其他场景
• 结构： 70/100（较完整）；scripts 2、references 0、assets 0
• 风险： 中（会执行命令或脚本；包含可执行脚本）
• 来源路径： .gemini/skills/async-pr-review/SKILL.md