Loading...
Loading...
Found 258 Skills
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
Activate when user provides a prompt, SKILL.md, or agent instruction and requests optimization. Transforms weak instructions into reliable, enforceable agent protocols.
Expert in using v0.dev for AI-powered UI generation. Covers prompting strategies, component iteration, shadcn/ui integration, export workflows, and customization. Knows how to get the best results from v0 and integrate generated components into production codebases. Use when "v0, v0.dev, generate ui, shadcn component, ai component, generate component, v0, v0-dev, ui-generation, shadcn, component-generation, ai-ui, vercel" mentioned.
Create and configure custom OpenCode agents (primary and subagents) with specialized prompts, tools, permissions, and models. Use when the user wants to create, modify, or configure OpenCode agents, or mentions agent modes, tool permissions, or task delegation.
Transforms vague UI/feature requests into structured, optimized prompts with design system awareness. Use when generating prompts for UI implementation, feature specification, or design-to-code translation. Triggers on tasks requiring prompt refinement, UI specification, or design system integration.
Triggered when users provide dream text materials, diary fragments, or oral dream descriptions and wish to generate videos. Trigger phrases include: "dreamt of", "had a dream", "dream material", "help me generate a video", "convert to video", "dream to video". It also applies to scenarios where users directly paste a dream description and expect to receive a video file. This skill converts text into video prompts, automatically submits them to the Jiemeng Platform for generation, and downloads the video files.
Analyze requirements during the functional design and problem diagnosis stages to develop executable solutions, and output user-facing and AI-facing action documents separately.
Uncle Huang's Private Advisory Board — a business decision think tank composed of 12 top thinkers. With a structured private advisory board process, different cognitive frameworks collide to produce optimal decisions. Trigger scenarios: - Users say "start a private advisory board", "invite the think tank", "help me make decisions" - Users say "Private Advisory Board: [topic]", "Let the experts discuss this matter" - Users use the /私董会 or /advisory-board command - Users face major business decisions requiring multi-perspective analysis Non-trigger scenarios: - Simple operational issues (how to publish, how to typeset) - Pure technical issues (code debugging) - Daily content creation (use article-writer / topic-partner) - Personal emotional counseling (use life-coach)
Ultra-compressed communication mode. Talk like a caveman to reduce token usage by about 75%. Full technical accuracy is maintained. Intensity levels: 3 tiers - Polite, Normal (default), Extreme. Activate by saying "Caveman Mode", "Shorten", "Be Concise", "Save Tokens", or using /genshijin.
Generate anime-style video prompts for Seedance 2.0 (Higgsfield). Use this when users want anime, Japanese animation style, shonen manga action, seinen manga drama, magical girl, mecha, isekai, slice-of-life anime, or any Japanese animation aesthetics. Trigger conditions: anime, Japanese animation, shonen manga, seinen manga, manga-style video, anime fight, anime opening, anime ending, cherry blossoms, chibi, cute style, mecha, isekai, or any anime-style request. Even phrases like "make it look like anime" or "Japanese cartoon style".
Skill for image generation. Uses Google Nano Banana Pro (Gemini 3 Pro Image) API to generate high-quality images. Supports logos, infographics, illustrations, photorealistic images, and more.
Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".