一键导入
litepik-dev
comprehensive guide for developing, testing, and architecture within the Litepik AI Suite ecosystem
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
comprehensive guide for developing, testing, and architecture within the Litepik AI Suite ecosystem
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Guide for using the MCP Runner Node to execute external tools via the Model Context Protocol.
This skill should be used when the user asks to "pentest SSH services", "enumerate SSH configurations", "brute force SSH credentials", "exploit SSH vulnerabilities", "perform SSH tunneling", or "audit SSH security". It provides comprehensive SSH penetration testing methodologies and techniques.
Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image
Generate AI music and songs with Diffrythm, Tencent Song Generation via inference.sh CLI. Models: Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator
Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative
| name | litepik-dev |
| description | comprehensive guide for developing, testing, and architecture within the Litepik AI Suite ecosystem |
This skill provides the core standards, patterns, and workflows for working on the Litepik AI Suite.
@xyflow/react) handles the canvas, nodes, and connections.services/ai/core.ts aggregates model calls.gemini-3-pro-preview or gemini-3-flash-preview. DO NOT change this unless explicitly authorized.useNodesState, useEdgesState)./components
/nodes # Individual Node components (Research, Image, Agent, etc.)
/common # Shared UI (ErrorFallback, etc.)
/MagicPrompt # Floating AI assistant
/services
/ai # LLM integration (models.ts, core.ts)
/logicEngine.ts # "Brain" converting node inputs -> outputs
/tests
/unit # Logic tests
/components # UI tests
/integration # Flow tests
Rule: NEVER export a raw node component to App.tsx.
All nodes must be wrapped with withSafeNode to provide error isolation.
Incorrect:
// App.tsx
[NodeType.RESEARCH]: ResearchNode
Correct:
// App.tsx
import { withSafeNode } from './components/nodes/SafeNodeWrapper';
[NodeType.RESEARCH]: withSafeNode(ResearchNode)
gemini-3-pro-preview or gemini-3-flash-preview.services/ai/core.ts. Do not remove the try-catch block in detectIntent.npx vitest runNodeType enum in types.ts.components/nodes/MyNewNode/index.tsx.App.tsx and register in nodeTypes object wrapped with withSafeNode.bg-slate-900, border-slate-700, text-slate-200 for consistency.services/logicEngine.ts.npx vitest run tests/unit/LogicEngine.test.ts to ensure data transforms didn't break.bg-slate-950).text-cyan-400, stroke-indigo-500).backdrop-blur-md and bg-slate-900/80 for floating panels.