Building with LLMs
Skill Đã xác minhHelp users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI output quality.
This skill provides curated advice and techniques for building AI applications, covering prompt engineering, RAG, agent creation, and evaluation. It distills expert insights into actionable steps for product builders.
Maintenance
- warning:Commit recencyThere are no commits in the last 90 days (pushedAt is n/a), suggesting the project might be unmaintained.
Versioning
- warning:Release ManagementThere is no explicit version field in the SKILL.md frontmatter, package.json, or any other manifest, and no CHANGELOG or GitHub releases are present.
Practical Utility
- info:Usage examplesWhile the skill provides a lot of detailed insights and advice, it lacks concrete, end-to-end examples demonstrating specific prompts and their observable outcomes.
- info:Edge casesThe skill mentions common mistakes and provides questions to help users, but it does not explicitly document specific failure modes with symptoms and recovery paths.
Cài đặt
npx skills add refoundai/lenny-skillsChạy Vercel skills CLI (skills.sh) qua npx — yêu cầu Node.js trên máy và ít nhất một agent tương thích skills đã được cài (Claude Code, Cursor, Codex, …). Giả định repo tuân theo định dạng agentskills.io.
Tiện ích tương tự
AI Product Strategy
98Help users define AI product strategy. Use when someone is building an AI product, deciding where to apply AI in their product, planning an AI roadmap, evaluating build vs buy for AI capabilities, or figuring out how to integrate AI into existing products.
LangChain RAG
85INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
Academic Paper Review Skill
98Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".
Optimize for AI
98Optimize content for AI search engines — ChatGPT, Perplexity, Claude, Gemini, Google AI Overviews. Use when the user asks about AI SEO, AISO, getting cited by AI, appearing in AI answers, answer engine optimization, AEO, GEO, LLMO, AI Overviews, zero-click search, or how to appear in ChatGPT/Perplexity results. For traditional SEO, see diagnose-seo.
AI Slides
98Generate complete presentations with AI - from outline to polished slides
happy-video-gen
98Universal AI video generation supporting OpenAI Sora, Google Veo 2/3, Runway Gen-3/Gen-4, Pika 2.2, Luma Dream Machine (Ray 2), FAL (Kling / Wan / Veo / Sora wrappers), Ark Seedance 1.5 Pro/Lite, Bailian Wanx (i2v), MiniMax Hailuo-02, and Vidu Q3. Use this skill whenever the user asks to generate, create, make, or synthesize a video from a text prompt or from a first-frame image. Covers text-to-video and image-to-video, with optional last-frame control on providers that support it. Typical phrases include "generate a video of ...", "make a 5-second clip of ...", "animate this image", "生成一段视频", "做个短片", or any mention of video-generation model families like Sora, Veo, Runway Gen, Kling, Wan, Seedance, Hailuo, Pika, Dream Machine, Vidu. Always use this skill even if the user does not name a specific model — pick a provider from their EXTEND.md defaults or available API keys. Do NOT use this skill when the user explicitly mentions 即梦 / Dreamina / Jimeng — those go to happy-dreamina instead.