Loading...
Loading...
Found 422 Skills
Think carefully no matter what question you answer. Before answering any question or performing any task, conduct in-depth analysis and reasoning first.
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.
Strengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.
Simulator mindset: Instead of asking "What do you think?", ask "Who knows this best in the world? What would they say?". Trigger words: super brain, top expert, world-class, best minds, who knows this best
Constructs technical Suno V5 style prompts, selects genres, and optimizes generation settings. Use when creating or refining Suno prompts for track generation.
Convert structured UX specs and product context into a sequenced prompts.md file for Claude Code. Use when a user has completed upstream design thinking (problem framing, PRD, UX spec) and needs to translate that into step-by-step prompts that coding agents can execute incrementally. This skill bridges design artifacts to code generation.
Generate and edit high-quality images with AI. Emphasize strong prompt design, structured JSON prompting, reference-image workflows, text rendering, and iterative refinement. Use any time the user needs an image generated.
Generate optimized prompts for YouThumb.ai YouTube thumbnails. Guided 4-step workflow: collect person name, map visual assets, describe the video, then generate 5 distinct ready-to-paste prompts. Use when the user says "thumbnail prompt", "YouThumb prompt", "generate thumbnail", "miniature YouTube", "prompt for my thumbnail", "help me with YouThumb", or when preparing YouTube thumbnail prompts.
图片提示词生成指南 — 角色、场景、宫格图三类提示词规范
Compress and simplify prompts to preserve meaning while reducing use of context
Ultra-compressed communication mode. Distills AI output to its core — ~65% fewer tokens while keeping full technical accuracy. Use when user says "caveman", "terse", "kurz", "kurz&knapp", "kurz bitte", "less tokens", "weniger text", or invokes /caveman-distillate.
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.