[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-related-ru-pydantic-pydantic-ai-harness":3},{"items":4,"total":107,"page":108,"pageSize":109},[5,25,50,67,85],{"slug":6,"name":7,"title":7,"skillCategorySlug":8,"summary":9,"description":10,"skillCategoryName":11,"sourceUrl":12,"downloadUrl":13,"cliCommand":14,"authorName":-1,"version":-1,"license":15,"stars":16,"trendScore":17,"qualityScore":18,"recommendedTools":19,"recommendedToolNames":19,"supportedClients":20,"clients":21,"tags":22,"installHint":14,"useCases":23,"updatedAt":24},"shubhamsaboo-awesome-llm-apps","shubhamsaboo\u002Fawesome-llm-apps","devtools","100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.","Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文\n\n100+ AI Agent & RAG apps you can actually run — clone, customize, ship. AI Agents · Always-on Agents · Multi-agent Teams · MCP Agents · RAG · Voice Agents · Agent Skills · Fine-tuning\n\nFree step-by-step tutorials on Unwind AI Works with Claude · Gemini · OpenAI · xAI · Qwen · Llama\n\n  🚀 Quick Start     📂 Browse Templates     📚 Step-by-Step Tutorials  \n\nYou shouldn't have to rebuild the same RAG pipeline, agent loop, or MCP integration from scratch every time you start a new LLM project.\n\n- starter code you can fork, customize, and ship as a production LLM app. Every template here is self-contained with full source code, not collected from elsewhere.\n\n- 🛠️ - every template is original work, tested end-to-end before it ships. - 🧪 - no broken requirements.txt, no \"figure it out yourself\" scaffolding.","Developer tools","https:\u002F\u002Fgithub.com\u002Fshubhamsaboo\u002Fawesome-llm-apps","https:\u002F\u002Fgithub.com\u002Fshubhamsaboo\u002Fawesome-llm-apps\u002Farchive\u002FHEAD.zip","npx skillfish add shubhamsaboo\u002Fawesome-llm-apps","Apache-2.0",141821,100,76,[],[],[],[8,15],[],"2026-08-30T04:42:26.276972",{"slug":26,"name":27,"title":27,"skillCategorySlug":8,"summary":28,"description":29,"skillCategoryName":11,"sourceUrl":30,"downloadUrl":31,"cliCommand":32,"authorName":-1,"version":-1,"license":15,"stars":33,"trendScore":17,"qualityScore":34,"recommendedTools":35,"recommendedToolNames":35,"supportedClients":36,"clients":39,"tags":47,"installHint":32,"useCases":48,"updatedAt":49},"pbakaus-impeccable","pbakaus\u002Fimpeccable","The design language that makes your AI harness better at design.","Design guidance for AI coding agents. 1 skill, 23 commands, live browser iteration, and 45 deterministic detector rules for AI-generated frontend design.\n\nFrom your project root, run npx impeccable install, then run \u002Fimpeccable init inside your AI coding tool. Full docs: impeccable.style.\n\nAnthropic's frontend-design was the first widely-used design skill for Claude. Impeccable started from there.\n\nEvery model trained on the same SaaS templates. Skip the guidance and you get the same handful of tells on every project: Inter for everything, purple-to-blue gradients, cards nested in cards, gray text on colored backgrounds, the rounded-square icon tile above every heading.\n\nImpeccable adds: - \u002Fimpeccable init writes PRODUCT.md and offers DESIGN.md, so later commands know the audience, brand\u002Fproduct lane, voice, anti-references, colors, type, and components. - A shared design vocabulary with your AI: polish, audit, critique, distill, animate, bolder, quieter, and more.","https:\u002F\u002Fgithub.com\u002Fpbakaus\u002Fimpeccable","https:\u002F\u002Fgithub.com\u002Fpbakaus\u002Fimpeccable\u002Farchive\u002FHEAD.zip","npx skillfish add pbakaus\u002Fimpeccable",81231,84,[],[37,38],"cursor","vscode",[40,44],{"slug":37,"name":41,"summary":42,"count":43},"Cursor","AI-редактор кода, часто используемый с developer MCP.",0,{"slug":38,"name":45,"summary":46,"count":43},"VS Code","Экосистема редактора, где MCP помогает кодингу и локальной автоматизации.",[8,15],[],"2026-08-30T04:41:25.694275",{"slug":51,"name":52,"title":52,"skillCategorySlug":8,"summary":53,"description":54,"skillCategoryName":11,"sourceUrl":55,"downloadUrl":56,"cliCommand":57,"authorName":-1,"version":-1,"license":58,"stars":59,"trendScore":17,"qualityScore":60,"recommendedTools":61,"recommendedToolNames":61,"supportedClients":62,"clients":63,"tags":64,"installHint":57,"useCases":65,"updatedAt":66},"code-yeongyu-oh-my-openagent","code-yeongyu\u002Foh-my-openagent","omo\u002Flazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode","We loved Anthropic models enough to get blocked. Now we are backing Codex. If you are an OmO fan but the setup felt like too much, use LazyCodex. OmO for Codex has shipped: Learn more at lazycodex.ai.\n\nWe are restructuring the codebase to support multiple agent harnesses (OpenCode, Codex, Pi, and others). If you are interested in contributing, please read the ROADMAP first. PRs related to roadmap work should use the ROADMAP label.\n\nThe maintainer builds and maintains oh-my-openagent in real-time with Jobdori, an AI assistant running on a heavily customized fork of OpenClaw. Every feature, every fix, every issue triage — live in our Discord.\n\nThis is oh-my-openagent, running Team Mode. With Kimi K2.6 and GPT-5.5.\n\nAnthropic They want you locked in. Claude Code is a nice prison, but it's still a prison. You don't need to pay $200 for 2 hours of work. The future isn't picking one winner; it's orchestrating them all. Models get cheaper every month. Smarter every month.","https:\u002F\u002Fgithub.com\u002Fcode-yeongyu\u002Foh-my-openagent","https:\u002F\u002Fgithub.com\u002Fcode-yeongyu\u002Foh-my-openagent\u002Farchive\u002FHEAD.zip","npx skillfish add code-yeongyu\u002Foh-my-openagent","NOASSERTION",70033,68,[],[],[],[8,58],[],"2026-08-30T08:28:10.975478",{"slug":68,"name":69,"title":69,"skillCategorySlug":8,"summary":70,"description":71,"skillCategoryName":11,"sourceUrl":72,"downloadUrl":73,"cliCommand":74,"authorName":-1,"version":-1,"license":75,"stars":76,"trendScore":17,"qualityScore":77,"recommendedTools":78,"recommendedToolNames":78,"supportedClients":79,"clients":80,"tags":82,"installHint":74,"useCases":83,"updatedAt":84},"asgeirtj-system-prompts-leaks","asgeirtj\u002Fsystem_prompts_leaks","Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity.","The full verbatim system prompts behind the most popular chatbots in the world. Carefully curated and complete. Feel free to open up a PR or get in contact if you got a different result.\n\nbuilt its interactive story on prompts from this repo: See the hidden rules behind AI. Then use them to rewrite this article. (May 11, 2026)\n\nbuilt an interactive breakdown of what is inside system prompts, topic by topic, from this repo's files: System prompts and what they tell us about the chat before the chat (July 10, 2026)\n\ncalls it \"the most thorough leaked system prompt collection I know of\": ChatGPT search now uses the site: operator at scale (August 20, 2026)","https:\u002F\u002Fgithub.com\u002Fasgeirtj\u002Fsystem_prompts_leaks","https:\u002F\u002Fgithub.com\u002Fasgeirtj\u002Fsystem_prompts_leaks\u002Farchive\u002FHEAD.zip","npx skillfish add asgeirtj\u002Fsystem_prompts_leaks","CC0-1.0",69620,66,[],[38],[81],{"slug":38,"name":45,"summary":46,"count":43},[8,75],[],"2026-10-13T01:54:07.525239",{"slug":86,"name":87,"title":87,"skillCategorySlug":8,"summary":88,"description":89,"skillCategoryName":11,"sourceUrl":90,"downloadUrl":91,"cliCommand":92,"authorName":-1,"version":-1,"license":93,"stars":94,"trendScore":17,"qualityScore":95,"recommendedTools":96,"recommendedToolNames":96,"supportedClients":97,"clients":99,"tags":104,"installHint":92,"useCases":105,"updatedAt":106},"cathrynlavery-diagram-design","cathrynlavery\u002Fdiagram-design","38 editorial diagram types for Claude Code, Codex, and Pi. Self-contained HTML + SVG. No shadows. No Mermaid slop.","14 types. One Claude Code skill. Your brand in 60 seconds — the skill reads your website and maps colors + fonts to every diagram.\n\nNo Figma. No generic rounded boxes. No 30-minute color-picking sessions.\n\nI write at littlemight.com (and run BestSelf.co on the side). Every time I needed a diagram — an architecture sketch, a flowchart, a pyramid of what matters most — I'd ask Claude and get back a generic rounded-box thing that looked nothing like the rest of the site. I'd either fight with Figma for 30 minutes or just skip the diagram.\n\nSo I built a Claude Code skill for it. Fourteen types, editorial quality, matches your brand in 60 seconds by reading your website.\n\nThe highest-quality move is usually deletion. Every node earns its place. The accent color is reserved for the 1–2 things the reader should look at first. Target density: 4\u002F10.\n\nAll 14 diagrams ship in three variants: minimal light, minimal dark, and full-editorial.","https:\u002F\u002Fgithub.com\u002Fcathrynlavery\u002Fdiagram-design","https:\u002F\u002Fgithub.com\u002Fcathrynlavery\u002Fdiagram-design\u002Farchive\u002FHEAD.zip","npx skillfish add cathrynlavery\u002Fdiagram-design","MIT",55478,80,[],[37,98],"cline",[100,101],{"slug":37,"name":41,"summary":42,"count":43},{"slug":98,"name":102,"summary":103,"count":43},"Cline","Клиент для агентного кодинга с практичными MCP-интеграциями.",[8,93],[],"2026-08-30T08:29:12.588839",5373,1,5]