creative-claw

Complete PPT production workflow for PptProductManager, covering requirement normalization, story planning, visual direction, route selection, asset planning, PPTX delivery, and quality checks.

Use this private PPT product skill when a .pptx/.potx PowerPoint file is involved as input, output, or user-uploaded template. In Creative Claw, prefer this skill for uploaded PPTX/POTX template workflows while the native XML route is being built: analyze the template, choose layouts, unpack/edit/pack OOXML, and deliver an editable PPTX.

用于带文字的 poster、长图页面、视觉文章、社交媒体图文、小红书/公众号文章、营销单页等内容优先的 HTML 页面。这个 skill 要求 PageProductManager 先写文案草稿和图像期望，再通过搜索或图像生成补齐素材，最后生成一个独立 HTML 页面。用这个 skill 做 poster 是为了解决直接基于图像生成 poster 时文字模糊、不准的问题；它更侧重内容准确可控、排版精美，以及图文相对位置清晰。

Use when the user already has images or videos and wants a script, scene plan, or edit-ready narrative built around those existing assets instead of generating everything from scratch.

Use when the user gives a topic, campaign idea, product angle, or raw creative brief and needs it turned into a structured storyboard with hooks, scene beats, narration, and visual intent.

Use when the user wants to review or sanity-check a storyboard, prompt pack, script, or generated asset set for consistency, platform fit, and creative quality before final delivery or generation.

Use when a creative request could map to several different skills or experts and you need to choose the smallest correct workflow, required inputs, and next execution path.

Use when the user already has script, narration, or storyboard text and needs aligned image or video prompts that are generation-ready and mapped one-to-one to the source beats.

Use when the user describes a look, atmosphere, or aesthetic direction in natural language and needs it converted into a clean English prompt fragment or style prefix for image or video generation.

Generate Claude Design-style HTML design artifacts with visible sections, artboards, screen states, and visual variants for design review and AI iteration.

Use when the task depends on choosing the right Creative Claw expert, composing expert calls, or explaining the usage strategy for image, video, search, grounding, segmentation, prompt extraction, or knowledge experts.

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.

Use when the user explicitly asks to use MiniMax, minimax-cli, or mmx, or when the task needs MiniMax terminal capabilities that Creative Claw does not already expose well through experts, especially music generation, speech synthesis, or MiniMax file upload. Prefer existing Creative Claw experts for generic image, video, search, and vision tasks unless MiniMax is explicitly required.

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

Use OpenCV for Python image processing, contour analysis, thresholding, filtering, geometric transforms, and basic video I/O. Trigger when the user asks to process images or video with cv2/OpenCV, or when a task clearly fits classical computer vision instead of a remote VLM.

Summarize web pages, search results, or local text files into concise takeaways using the current built-in tools.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Get current weather and forecasts (no API key required).

Research a topic on the web using search and fetch tools, then return grounded findings.