Explore the Skill Store

处理 PowerPoint / PPTX 生成、模板改稿与内容审查，输出可编辑的原生 .pptx，并覆盖逐页编排、结构设计与文本级 QA。

一個智能的翻譯助手，支持英文與繁體中文互譯，遵循香港政府術語規範

NotebookLM演示文稿提示词库，提供现代报纸、极简、漫画、时尚杂志、技术感、运动风等多种风格的幻灯片生成提示词。当用户需要生成演示PPT、幻灯片、Presentation deck时使用。

Test translation quality with built-in dictionaries and comparison tools. Use when evaluating translations.

Convert story synopses or single-scene descriptions into high-quality text-to-image prompts. Two modes: (1) multi-scene - a story outline is split into multiple coherent scenes, each with its own prompt; (2) single-scene - a single scene description gets a prompt directly. Outputs scored prompts with bilingual versions. Use when users say story to images, generate prompts for this scene, story split, storyboard prompts, text-to-image prompt, 文生图, 分镜, 故事拆分.

Transform existing songs with the Twin Remix method — produce Respectful and Viral versions with Suno v4.5 sliders and visual guides

Generate high-quality, customizable AI prompts for various use cases including creative writing, problem-solving, education, business, programming, Flutter development, and game development. Use when a user asks for help creating prompts, wants to improve their AI interactions, or needs structured prompt templates for specific tasks.

API文档助手。生成API文档、编写Swagger/OpenAPI、示例代码。使用场景：(1) 文档生成，(2) Swagger配置，(3) 示例代码，(4) 版本管理。

Create conversion-focused product marketing videos with Remotion + React using the AIDA framework (Attention, Interest, Desire, Action). Use when building launch videos, paid social ads, app promos, SaaS explainers, or product teasers that must follow this arc: (1) establish the problem, (2) introduce the solution, (3) show use cases instead of feature lists, and (4) end with a call-to-action that includes an incentive. Use Freepik only for ancillary assets (for example Nano Banana 2 stills, Kling inserts/transitions, and ElevenLabs voiceover/music), while core storytelling, timing, and final assembly stay in Remotion code.

This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

Intelligently analyzes user-provided multimodal assets and creative intent to generate optimal, structured video generation prompts for the Seedance 2.0 model.

Search Seedance 2.0 video generation prompts curated from the community. ByteDance AI video model — find cinematic, realistic, animated, and creative video prompts for Seedance 2.0 that actually work.

Create high-control English prompts for Seedance 2.0 and Seedance 2.0 Fast using multimodal references (image/video/audio/text).

Generate cinematic video prompts for Seedance 2.0 (ByteDance). Use when user asks for video prompts, Seedance prompts, AI video generation prompts, or anything related to Seedance 2.0 prompt crafting. Triggers on: seedance, video prompt, AI video, text to video prompt, seedance prompt.

Deep prompt engineering workflow—task spec, constraints, examples, evaluation sets, iteration protocol, regression testing, and safety alignment. Use when improving LLM outputs, shipping prompt changes, or building reusable prompt templates.

Write, test, and iterate prompts for AI models with voice preservation, model-specific adaptation, and systematic failure analysis.

Transform messages that begin with `@prt` or `@prompt` into structured, copy-ready prompts for coding, prototyping, planning, and other build-oriented tasks. Use when a user wants prompt-writing help, wants a natural-language request upgraded into a stronger prompt, wants a short summary of the prompt's key handling, or uses the `@prt` / `@prompt` prefix. Also use to bypass non-target prefixed inputs that are really ordinary chat, simple questions, or casual remarks.

Git for your prompts. Track every change, diff versions, rollback mistakes, never lose a good prompt again. All local, zero dependencies, works offline.

Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.

Designs and optimizes system prompts for advisory AI and autonomous agent systems using a three-layer architecture (Foundation → Structure → Execution). Integrates evidence-graded techniques with production-proven patterns from Claude Code, Vercel v0, and Manus. Use when designing agentic systems with tool use, building advisory AI with confidence grading, optimizing existing prompts, diagnosing prompt failures, or building a spec to hand off to a prompt engineer. Includes a spec builder knowledge base and modular extensions for RAG grounding, domain calibration, and multi-agent orchestration. Trigger on: "system prompt", "agent", "agentic", "prompt engineering", "write a prompt", "improve my prompt", "AI advisor", "tool use prompt", "multi-agent", "build me a spec", "write a spec", "spec for", "tool specification", "system prompt build request".

SHA-256 prompt deduplication for LLM and TTS calls — hash normalize prompts, check cache before calling APIs, store results for instant replay. Use when making repeated or similar API calls to avoid redundant spending. Works with any database backend (SQLite, Turso, Postgres).

Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (CoT, Few-Shot, Persona, etc.).

A comprehensive AI agent skill for writing prompts that get consistently excellent results from AI models. Teaches the principles behind effective prompting, helps you write prompts for any task, builds a personal library of prompts that work, diagnoses why a prompt is not producing what you want, and keeps your prompting practice current as models evolve.