图片提示词生成

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

Local speech-to-text with the Whisper CLI (no API key).

Extract frames or short clips from videos using ffmpeg.

UI/UX design intelligence and implementation guidance for building polished interfaces. Use when the user asks for UI design, UX flows, information architecture, visual style direction, design systems/tokens, component specs, copy/microcopy, accessibility, or to generate/critique/refine frontend UI (HTML/CSS/JS, React, Next.js, Vue, Svelte, Tailwind). Includes workflows for (1) generating new UI layouts and styling, (2) improving existing UI/UX, (3) producing design-system tokens and component guidelines, and (4) turning UX recommendations into concrete code changes.

Expert frontend design guidelines for creating beautiful, modern UIs. Use when building landing pages, dashboards, or any user interface.

Generate and edit diagrams with the mcp-diagram-generator MCP server. Use this skill for new diagrams, existing .drawio/.mmd/.excalidraw edits, network topol...

Complete toolkit for programmatic video creation with Remotion + React. Covers animations, timing, rendering (CLI/Node.js/Lambda/Cloud Run), captions, 3D, charts, text effects, transitions, and media handling. Use when writing Remotion code, building video generation pipelines, or creating data-driven video templates.

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

飞书端读取USER.md任务清单。当用户说"查看任务"、"我的任务"时触发，实时解析并返回格式化的分类任务列表，让用户快速了解当前所有可用任务和技能。

Agent 上下文管理方法论：通过分层文件体系实现跨 session 记忆延续、职责分离和高效上下文恢复。Use when: (1) 搭建新 agent 工作区, (2) 优化 agent 记忆和上下文管理, (3) 长期运行 agent 的记忆维护。

七阶段（含阶段0任务澄清）多角色工作坊；角色种类与人数均由任务决定。触发词："多角色研讨"、"需求工作坊"、"需求评审"、"圆桌"、"定方案再执行"。