remotion-prompt-generator
Remotion Prompt Generator — Skill Router
Generate comprehensive, structured prompts that the Remotion Dev skill can use to produce professional programmatic videos.
MANDATORY: Always-Load References
Before generating ANY prompt, you MUST read these two files first:
references/remotion-capabilities.md— Core Remotion knowledge (architecture, features, limitations, packages)references/intelligent-inference.md— How to analyze vague requests and auto-fill smart defaults
MANDATORY: Web Search Requirement
Before generating a prompt, you MUST perform web search to gather context about what the user is building:
- Search for the user's product/company/industry if mentioned
- Search for current design trends relevant to their video type
- Search for competitor examples or reference videos in their space
- This context makes prompts dramatically better — never skip it
Reference Files
| Reference | File | Read When |
|---|---|---|
| Remotion Capabilities | references/remotion-capabilities.md |
ALWAYS READ FIRST — core Remotion knowledge needed for every prompt |
| Intelligent Inference | references/intelligent-inference.md |
ALWAYS READ — how to handle vague prompts, auto-fill defaults, infer from signals |
| Video Types (Router) | references/video-types.md |
Identifying video category: marketing, social, data-viz, education, e-commerce, etc. |
| Prompt Engineering | references/prompt-engineering.md |
How to structure the final prompt output, 12-section format, scene descriptions |
| Discovery Workflow | references/discovery-workflow.md |
Follow-up questions to ask users, requirement gathering, clarification strategies |
| Asset & Styling Guide | references/asset-styling-guide.md |
Colors, fonts, logos, images, audio, branding, dimensions, platform specs |
| Animation & Effects | references/animation-effects.md |
Spring physics, transitions, easing, text animations, 3D, particles, motion patterns |
| Domain Examples (Router) | references/prompt-engineering/domain-examples.md |
Real prompt examples for specific industries: SaaS, real estate, finance, education |
How This Skill Works
- ALWAYS read
remotion-capabilities.mdandintelligent-inference.mdfirst - ALWAYS do a web search about what the user wants to build (their product, industry, competitors)
- Analyze the user's request — extract every signal, infer what you can, auto-fill smart defaults
- Ask only 2-3 critical questions that cannot be inferred (use AskUserQuestion tool)
- Read the relevant video-type sub-reference and domain example
- Generate a complete, detailed, 12-section structured prompt for the Remotion Dev skill
- The Remotion Dev skill uses that prompt to write React/Remotion code
Quick Reference
- Remotion docs: https://remotion.dev/docs
- GitHub: https://github.com/remotion-dev/remotion
- Templates: https://remotion.dev/templates
More from abhisheksharma-17/skills-graph
agno
Build AI agents, multi-agent teams, and agentic workflows using the Agno framework. MANDATORY TRIGGERS: Agno, agno-agi, AgentOS, any mention of the Agno framework. Also trigger when the user wants to build AI agents with tools/memory/knowledge, create multi-agent systems, RAG pipelines, reasoning agents, agentic workflows, or deploy agents to production. Trigger even if the user just says 'build me an agent', 'create an AI assistant', or 'make a chatbot' — if Agno is anywhere in their stack or project dependencies. When in doubt about whether to use this skill for agent-building tasks, use it.
10design-engineering
Comprehensive frontend design engineering system covering the full design lifecycle — planning, building, styling, reviewing, refining, hardening, and upgrading interfaces. MANDATORY TRIGGERS: design, UI, UX, frontend, interface, component, layout, typography, color, animation, responsive, accessibility, critique, audit, polish, redesign, design system, onboarding, micro-interactions, visual design. Also trigger when user asks to build a page, create a component, review a design, improve typography, add animation, fix layout, audit accessibility, redesign an existing project, add delight, make it look professional, or any frontend visual/interaction task. When in doubt about whether to use this skill for any design or frontend task, use it.
2litellm
Unified LLM gateway and SDK for calling 100+ LLM providers (OpenAI, Anthropic, Bedrock, Vertex, Azure, Ollama, etc.) with a single OpenAI-compatible interface. MANDATORY TRIGGERS: litellm, litellm proxy, litellm router, litellm.completion, llm gateway, multi-provider llm, openai-compatible proxy, model fallback, llm cost tracking, llm load balancing. Also trigger when user wants to switch LLM providers without rewriting code, route requests across multiple models, add fallbacks/retries to LLM calls, track token costs, run a self-hosted OpenAI-compatible proxy, or unify observability across providers. When in doubt about whether to use this skill for any multi-provider LLM task, use it.
1livekit
Build realtime voice, video, and AI agent applications with LiveKit. MANDATORY TRIGGERS: livekit, live kit, voice agent, voice AI, realtime audio, realtime video, WebRTC agent, speech-to-speech, voice pipeline, voice assistant framework. Also trigger when user wants to build voice AI agents, realtime communication apps, telephony integrations, video conferencing, or multimodal AI agents with audio/video. When in doubt about whether to use this skill for realtime media or voice AI tasks, use it.
1claude-agent-sdk
Build AI agents programmatically with the Claude Agent SDK (Python and TypeScript). Provides the same tools, agent loop, and context management that power Claude Code, but as a library. MANDATORY TRIGGERS: claude-agent-sdk, claude agent sdk, claude_agent_sdk, @anthropic-ai/claude-agent-sdk, ClaudeAgentOptions, ClaudeSDKClient. Also trigger when user wants to build AI agents with Claude programmatically, create agent loops with tools, use Claude Code SDK, orchestrate subagents, or deploy autonomous coding agents. When in doubt about whether to use this skill for agent SDK tasks, use it.
1