Generate AI images from text prompts — one API key for GPT Image, Gemini, Seedream, and 10+ models. No juggling subscriptions. Images saved to your YouMind knowledge board. Use when user wants to "generate image", "create image", "AI image", "text to image", "生成图片", "AI 生图", "画像生成", "GPT image", "Gemini image", "Seedream", "DALL-E", "Midjourney".

Write and publish Hashnode articles through YouMind OpenAPI. Supports draft-first publishing, published post listing, draft listing, tag lookup, and clear connector / pricing guidance when the user's Hashnode account is not ready inside YouMind.

Write and publish Ghost articles with AI — topic research via YouMind knowledge base, Ghost-oriented writing, Markdown-to-HTML conversion, feature image upload, and one-click publishing. Use when user wants to "write Ghost article", "publish to Ghost", "Ghost 文章", "发布到 Ghost".

Write and publish Dev.to articles with AI — topic research via YouMind knowledge base, developer-audience adapted writing, Markdown with front matter formatting, and one-click publishing. Use when user wants to "write Dev.to article", "publish to Dev.to", "post on Dev.to".

Conduct deep research on any topic — get comprehensive reports with citations, key findings, and actionable insights in minutes. Use when user wants to "deep research", "research this", "investigate", "analysis report", "深度研究", "调研", "リサーチ", "심층 연구".

Generate blog cover images optimized for 16:9 headers — clean composition with text-friendly layouts, powered by multi-model AI. Use when user wants to "blog cover", "featured image", "article image", "cover image", "thumbnail", "文章配图", "封面图", "博客配图", "ブログカバー", "블로그 커버".

Write and publish Beehiiv posts with AI — topic research via YouMind knowledge base, newsletter-publication writing, Markdown-to-HTML conversion, and publishing through the Beehiiv account already connected in YouMind. Use when user wants to "write Beehiiv article", "publish to Beehiiv", "Beehiiv post", "Beehiiv newsletter", "写 Beehiiv 文章", "发布到 Beehiiv".

Dispatch content to multiple platforms from a single topic — Dev.to, Hashnode, WordPress, Tumblr, Ghost, Beehiiv, Kit, X/Twitter, WeChat, Qiita. Each platform skill adapts content independently for its audience and format. Pure orchestration, no publishing logic. Integrates YouMind knowledge base for topic research and content material mining. Use when user wants to "publish everywhere", "cross-post", "multi-platform publish", "dispatch article", "post to all platforms", "distribute content". Do NOT trigger for: single-platform requests (route to specific skill), non-content tasks.

Guidelines and examples for UI motion and animation. Use when designing, implementing, or reviewing motion, easing, timing, reduced-motion behaviour, CSS transitions, keyframes, framer-motion, or spring animations.

SEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Use when user wants to improve search visibility, search optimization, search ranking, AI visibility, ChatGPT ranking, Google AI Overview, indexing, JSON-LD, meta tags, or keyword research.

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Use when designing ablation studies to compare model components, loss functions, or architectural choices. Covers synthetic data experiments, variant loops, production metrics, and W&B grouping. Triggers: "ablation", "ablation study", "variant comparison", "controlled experiment", "synthetic data experiment"

Use when optimizing PyTorch training speed or memory on CUDA GPUs — global flags, torch.compile, fused optimizers, mixed precision, gradient checkpointing, kernel fusion, memory layout, or latent-space training. Applies to any PyTorch training workload. Triggers: "torch.compile", "TF32", "fused optimizer", "mixed precision", "bf16", "fp16", "gradient checkpointing", "Triton kernel", "CUDA flags", "GPU slow", "GPU memory"

Use when evaluating generative models — choosing metrics (FID, IS, KID, sFID, FDD, FVD, PRDC, LPIPS, SSIM, AuthPct, Vendi), setting up online or offline evaluation, feature extractor selection, distributed computation, memory management during sampling. Triggers: "FID", "IS", "KID", "inception score", "frechet", "LPIPS", "SSIM", "evaluation metrics", "generative evaluation", "FVD"

Use when reading a YouTube video (especially an AI/ML interview, podcast, or technical talk) and producing a faithful, timestamped wiki entry the user can return to weeks later. Fetches the transcript via yt-dlp, sections by chapters or LLM-detected topics, summarizes per-section with parallel subagents, preserves verbatim quotes with speaker attribution, and runs a coverage test against the raw transcript. Triggers: "youtube wiki", "video wiki", "summarize this youtube", "watch this interview", "read this talk", "digest this video", "https://youtu.be/", "https://www.youtube.com/watch"

Use when reading PDF papers, reports, or long documents where text, figures, and tables must all be captured and chunk-summarized without truncation. Converts PDF to a markdown + paper_content.json workspace, extracts figures and tables as standalone files, then delegates to arxiv-latex-reader's progressive two-layer reading (section index + on-demand deep reads). Triggers: "read pdf", "pdf to markdown", "summarize pdf", "pdf paper", "extract figures from pdf", "extract tables from pdf", "marker pdf", "pymupdf", "docling", "paper digest", "pdf reader"

Use when capturing a single URL (X tweet, LinkedIn post, HN thread, short blog, news article, GitHub gist or issue) as a small persistent markdown entry the user can re-read later for motivation or grep across future sessions. Verbatim body + author + tags + a one-line "Why I saved this" hook. Writes to docs/wikis/YYYY-MM-DD-<slug>.md. WebFetch by default; CDP via Playwright MCP for login-walled hosts (x.com, twitter.com, linkedin.com). Redirects YouTube / arXiv / GitHub repo URLs to their specialized skills. Triggers: "insert wiki", "add to wiki", "insert this", "save this tweet", "capture this post", "add this to my wiki", "remember this link", "https://x.com/", "https://twitter.com/", "https://linkedin.com/posts/"

Use when evaluating whether a research or product idea is actually feasible — buildable, evaluable, and de-risked by available checkpoints, code, datasets, and GPU budget. Normalizes the idea, gathers primary-source evidence (arXiv, GitHub, project pages, model hosts), scores it against four mandatory hard gates, and emits a verdict + falsifiable MVP. Triggers: "idea feasibility", "is this idea feasible", "feasibility check", "can we do this", "is this practical", "worth pursuing", "评估想法可行性", "可行性分析", "这个 idea 能做吗", "这个想法靠谱吗"

Use when proposing new research ideas grounded in a seed paper or method — surfaces the gaps that the citation cone hasn't filled, the drawbacks the community already complains about in the official repo's GitHub issues, and the adjacent angles the literature suggests. Orchestrates followup-analysis (already-done exclusion), GitHub-issue mining (known drawbacks), and academic-deep-research (adjacent literature) into a ranked candidate-ideas report. Triggers: "idea explore", "idea-explore", "propose ideas", "explore ideas", "new directions", "research gaps", "what's missing", "build on this paper", "探索想法", "提出新想法", "研究空白"

Use when promoting an idea from a fleeting thought into a tracked artifact with a lifecycle. Defines a per-idea on-disk directory (./idea_box/<slug>/) and a hard-gated state machine (explored → feasible/blocked → building → built/killed) that the existing reader/evaluator skills (idea-feasibility, ml-ablation-design, academic-deep-research, followup-analysis, arxiv-latex-reader, pdf-reader, github-reader, blog-reader) plug into. Public repo ships only the convention; idea data lives in the user's private idea-box repo. Triggers: "idea box", "idea-box", "new idea", "advance idea", "list ideas", "kill idea", "想法箱", "新想法", "推进想法", "列出想法"

Use when reading a GitHub repository (especially a research code release with an accompanying paper) and producing a faithful digest that covers the implementation logic, the main insight, and the key reported results. Research-first with graceful fallback for non-paper repos. Handles arXiv link detection and delegates paper reading to arxiv-latex-reader / pdf-reader. Triggers: "read repo", "read this github", "analyze github", "digest repo", "github reader", "extract from github", "summarize this codebase", "read this code", "https://github.com/"

Use when reading a long technical blog post (ML research, engineering deep-dives, Distill/Lil'Log-style posts) and producing a faithful, figure-aware summary. Handles context-over-limit via section-based chunking, captures important figures via multimodal Read, and runs a coverage test to catch missing information. Triggers: "read this blog", "summarize this post", "read blog", "digest this article", "long blog post", "read this article", "blog summary", "distill post", "summarize url", "chunk and summarize"

Use when reading large arxiv papers without context overflow. Progressive two-layer reading: index all sections (~2k tokens), then deep-read on demand. Never truncates. Triggers: "read paper", "paper sections", "section index", "progressive reading", "paper_content.json", "section summary"