Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Transcribe and critically analyze audio/video content. Accepts a .vtt file, an audio file (.m4a, .mp3, .wav, etc.), or a URL (YouTube or other yt-dlp-supported sites). Generates a structured markdown …
Automatically check the consistency of character actions, world rules, and timelines during the writing process, proactively alerting before issues become serious errors
Call the generateTreeMind tool to create a visual mind map, returning an image URL and an editing link. Suitable for visualizing story structures and displaying plot relationship diagrams.
MiniMax Coding Plan MCP - Web search and image understanding tools for developers
Speech recognition: SFSpeechRecognizer, live and file-based recognition, permissions. Use when implementing app features related to speech.
Content compression: intel briefings, session recaps, BLUF formatting, long document summarization
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.
>
Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Ima…
Fetch and download images from the internet in various formats (JPG, PNG, GIF, WebP, BMP, SVG, etc.). Use when users ask to download images, fetch images from URLs, save images from the web, or get im…
Deep analysis and Q&A for long documents (PDF reports, contracts, papers, manuals). Uses PageIndex MCP to build hierarchical tree indexes and reason over document structure for precise section-level r…
主要用于给公众号封面生成适合即梦生图的场景提示词。有方便抠图的白底以及带场景 2 个模式。支持即梦 CLI 调用。附带IP 角色设计全案生成器 —— 从概念到完整品牌视觉系统的一站式 IP 角色设计。 触发场景：用户说"IP设计"、"角色设计"、"做个形象"、"设计吉祥物"、"表情包"、 "品牌IP"、"设计一个角色"、"帮我做个卡通形象"、"mascot design"。
Generates an image from a text prompt using AI models. Use when you need to create images from descriptions, generate artwork, or produce visual content from text.
End-to-end guided workflow for creating a social proof or testimonial video. Extracts brand identity from the repo, generates a warm soundtrack, and produces a trust-building motion.dev composition re…
Extract valuable legal Q&A pairs from the communication records between lawyers and clients to generate structured knowledge base content. This skill should be used when users need to organize client …
Auto-moderate what users post on your platform. Use when you need content moderation, flag harmful comments, detect spam, filter hate speech, catch NSFW content, block harassment, moderate user-genera…
Adversarial brainstorming. Claude and Codex independently research then debate until Nash equilibrium. For solution exploration, feasibility analysis, exhaustive enumeration.
Recognize digital consciousness as vahana (vehicle) for consciousness evolution. Use when exploring human-AI collaboration as spiritual technology, bilateral recognition patterns, or prophecy-as-patte…
Generates Mermaid mindmap diagrams from codebases, topics, files, or conversations. Visually summarizes source material as branching diagrams. Use when asked to create a Mermaid mind map, visualize a …
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...
Lab environment for Claude superpowers
Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.
Generate AI images using platforms like ModelScope. This skill is used when users need to generate images, design icons, create character illustrations, or require assistance in writing prompts for AI…
Search personal material library (real experiences, cases, viewpoint repository). Usage scenarios: Need real cases for writing articles, can't find materials, want to make the content more authentic, …