Catch the spark.
Ship with AI prompts that work.
AI tool navigation, structured skills and copy-paste workflows — powered by precise prompts. Discover the right tool, learn the best prompt, and turn AI into real productivity.
Latest AI Tools
Freshly added tools, newest first.

DeepTutor
Agent-native lifelong personalized tutoring workspace by HKUDS — chat tutoring, problem solving, quiz generation, research and mastery practice in one runtime.
DeepTutor is an agent-native learning workspace that connects tutoring, problem solving, quiz generation, research, visualization, and mastery practice in one extensible system. Built by HKUDS (Hong Kong University Data Science). Features a unified runtime for chat, ask-questions, quiz, research, visualize, solve, mastery path and immersive reading. Supports multi-engine RAG (LlamaIndex, GraphRAG, LightRAG, PageIndex), subagent consultation (Claude Code, Codex, Grok CLI), persistent IM partners across Feishu/Telegram/Slack/Discord, immersive YouTube/Bilibili video learning with transcript-grounded tutoring, and the EduHub community skill registry.

Pokemon Cards CSS
Advanced CSS styles using transforms, gradients and blend modes to create realistic holographic foil effects on Pokemon trading cards.
Pokemon Cards CSS is a collection of advanced CSS styles that simulate the various Holofoil effects found in the Sword and Shield era of Pokemon Trading Cards. Built with SvelteJS, it uses CSS Transforms, Gradients, Blend-modes and Filters to render realistic holographic shimmer, galaxy holo, and other foil patterns directly in the browser. Featured on CSS-Tricks and CodePen. 8.3k stars, GPL-3.0.

AIHOT
Self-hosted AI news aggregator framework that auto-collects sources, scores with LLMs, clusters events and publishes daily digests.
AIHOT is an open-source engine for building your own industry hotspot news site. It ingests RSS, web pages, JSON APIs, X accounts and WeChat official accounts, uses an LLM to pre-filter and score stories independently twice, writes Chinese headlines and summaries, clusters reports on the same event, and calculates real-time heat. Ships with daily/weekly/monthly digests, theme pages, full-text search, MCP server, RSS feeds and a public API. Built with Node.js, TypeScript, React Router, Fastify and PostgreSQL, deployed via Docker Compose. 8.9k stars by 数字生命卡兹克.

GEOInflow
Self-hosted web and AI crawler analytics for Generative Engine Optimization — track AI search referrals, crawl logs, content coverage and conversions.
GEOInflow brings website visitors, AI search referrals, server crawl logs, and content inventories into a shared analytics context. It helps teams understand which AI crawlers visit their sites, which pages they request, which important pages have no observed crawl activity, where requests fail, and how AI search contributes visitors and conversions. Built-in crawler identity catalog covers OpenAI, Anthropic, Perplexity, Google, Microsoft, ByteDance, Baidu, Kimi, Tencent Hunyuan and more. Ships as a Docker Compose deployment with PostgreSQL and Redis. Jointly published by 猎看科技 and 北京日报社智源GEO, MIT licensed.

AI Pose Gallery (Chinese)
1,439 multi-angle human pose reference images for AI art, 3D and photography — fully Chinese-localized.
AI Pose Gallery is a curated, fully Chinese-localized pose reference library featuring 1,439 multi-angle human poses across 288 groups and 4 pose systems. It ships as a zero-dependency responsive static gallery with category filtering, 5 viewing angles, grouped and single browse modes, lightbox keyboard navigation and original PNG downloads. Built for AI painters, 3D artists, photographers and animators who need accurate human pose references.

Awesome AI Motion
A curated gallery of 441+ AI motion design works, 69 public prompts, and 25 open-source projects.
Awesome AI Motion is an inspiration and resource collection for motion design and creative video. Explore product films, 3D interactions, animated shorts and visual experiments, with creators' public source code, prompts and making-of material. Browse works across categories including product & marketing, education & explainers, motion design, pixel art & characters, 3D & interactive, narrative films, and music & lyrics. Created and maintained by Guanmo (@guanmo_ai).
Latest Prompts
Newest prompts for every creative scene.

Swiss Modernism × Frosted Glass Conceptual Photography × Body Fragmentation × Minimalist Cultural Festival Poster
A stable visual system combining Swiss modernism, translucent medium conceptual photography, body fragmentation, and minimalist cultural festival posters. The subject is anonymized behind a milky frosted glass panel, creating a broad soft-focus human silhouette with select high-clarity body fragments. Swiss International Style grid typography with lemon yellow accent title.

Four-Brand Capsule Commercial Advertisement
Create a premium vertical commercial ad featuring four transparent brand capsules (Coca-Cola, Pizza Hut, Pepsi, McDonald's) while preserving the exact identity of the person from your reference photo.

Rubber Stamp Travel Field Notes Poster
Create collectible rubber-stamp style travel posters on aged paper, featuring simplified landmark illustrations with authentic hand-stamped texture and imperfections.

Volcanic Beach Sunset
A dramatic volcanic black sand beach at sunset with glowing lava rocks and crashing turquoise waves.

Art Deco Cocktail Bar
A glamorous 1920s Art Deco cocktail bar with geometric patterns, gold accents and velvet seating.

Cyberpunk Cat Portrait
A cool cyberpunk cat with neon cybernetic implants sitting in a neon-lit futuristic alley.
Latest Skills
Newest reusable prompt frameworks.

Answer Me With HTML — One-Page Explainers from Your AI Agent
A Claude Code / agent skill that turns hard questions into one readable HTML page with SVG sequence diagrams, flow charts, ER diagrams, timelines and comparison tables. The model writes only a Markdown draft; a CLI handles layout, colors and SVG coordinates — 8x fewer output tokens and 2.6x faster than hand-writing HTML. Supports blueprint, shadcn and paper themes with light/dark mode, plus explainer video generation.

Emil Kowalski Skills — AI Skills for Designers & Engineers
A curated collection of 12 AI skills for designers and engineers, built by Emil Kowalski (ex-Vercel, ex-Linear). Helps agents make great animation and design decisions — from building animations from scratch to auditing your codebase, picking the right UI library, and writing modern Swift. 45.1k GitHub stars.

Image Blaster — Image-to-3D World Skillset for Claude
Creates 3D environments, SFX, and meshes from a single image using Claude skills, World Labs, and FAL. Takes you from an image to a fully meshed 3D environment in under 5 minutes — generates 3D models (.glb, .obj), Gaussian splats (.spz), and ambient sound effects (.mp3).

Ecommerce Image Skills — 12 Agent Skills for Product Photography
Twelve installable Agent Skills that turn a casual product photo into platform-ready ecommerce images — Amazon main images, lifestyle scenes, infographics, A+ modules, size charts, on-model shots, sale banners, Xiaohongshu covers and Taobao detail pages. Powered by GPT Image 2.5 (Flare / Sunburst).
Latest Workflows
Newest end-to-end pipelines with copy-paste steps.

Krea AI Video Generation
Generate, compare, and refine cinematic AI videos using all top video models (Seedance 2.5, Veo 3.1, Sora 2, Kling 3.0, Wan 2.6, Runway Gen-4.5) in Krea's unified workspace. One subscription, every model.

Autonomous Build Council Pipeline
Personal autonomous build queue where a council of opinionated AI agents evaluates, plans, and builds software features from a plain-language brief, with a Kanban board UI and confidence-weighted voting.

n8n Content & Business Automation Suite
15+ ready-to-use AI automation workflow templates across 5 categories: Content Creation, Email & Newsletter, Research & Monitoring, Business Operations, and Translation & Localization.

n8n AI Automation Workflow Templates
5 production-ready n8n workflow templates: crypto signal alerts, RSS-to-social-media auto-posting, AI email auto-responder, website change monitor, and daily business report generator.
Latest from the Blog
In-depth guides, comparisons, and tutorials for AI creators.

Emil Kowalski Skills: 12 AI Skills That Give Your Agent Design Taste (2026 Guide)
AI agents can write code, but they rarely have good design taste. Emil Kowalski's skill collection — 45.1k GitHub stars, built by an ex-Vercel and ex-Linear designer — fixes that. From animation curves to Apple design principles, here's how to give your agent the taste it's missing.

Krea AI Video Generator: All Top Video Models in One Workspace (2026 Guide)
Krea bundles Seedance 2.5, Veo 3.1, Sora 2, Kling, Wan, Runway, and more into one clean workspace. Generate, compare, and refine AI videos side by side. Complete review of features, models, pricing, and workflows.

OpenAI Codex vs Claude Code vs Gemini CLI: Which AI Coding Agent Wins in 2026?
A comprehensive comparison of the three dominant AI terminal coding agents in 2026. We break down features, pricing, benchmarks, ecosystem maturity, and real-world use cases to help you choose the right tool for your workflow.