Audits Claude Code system token overhead (CLAUDE.md, MEMORY.md, skills, MCP servers, daily logs) and generates a report with cleanup recommendations. Use monthly or when sessions feel slow. Trigger: "token hygiene", "context audit", "audit tokens".

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.

Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices. Expert in the latest Go ecosystem including generics, workspaces, and cutting-edge frameworks. Use PROACTIVELY for Go development, architecture design, or performance optimization.

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or debugging race conditions.

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Master of defensive Bash scripting for production automation, CI/CD, pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...

Use this skill when the task is clearly connected to the user's YouMind workspace, YouMind APIs, or the youmind CLI. It helps agents search, inspect, and call YouMind OpenAPI endpoints to work with boards, groups, YouMind files, picks, chats, and YouMind skills.

Extract and summarize YouTube video transcripts via YouMind API — no yt-dlp, no proxy needed. Batch extract up to 5 videos at once with parallel processing. Saves videos to your YouMind board with timestamped transcripts in markdown. Automatically summarizes video content after extraction. Works from any IP (cloud, VPS, CI/CD, corporate networks). Use when user wants to "get YouTube transcript", "extract video subtitles", "transcribe YouTube video", "batch transcribe videos", "get video captions", "summarize YouTube video", "YouTube video summary", "summarize this video", "what does this video say", "YouTube 字幕", "YouTube 总结", "视频总结", "YouTube 文字起こし", "YouTube 자막", or "download YouTube transcript".

Write and publish tweets to X (Twitter) with AI — topic research via YouMind knowledge base, 280-char optimized writing, numbered multi-tweet sequences, and one-click publishing through the X account already connected in YouMind. Use when user wants to "tweet", "post on X", "publish to Twitter", or "write a thread".

Write and publish WordPress articles end-to-end with AI — topic mining via YouMind knowledge base, de-AI voice writing, Markdown-to-HTML conversion, featured image upload, and one-click publishing. Use when user wants to "wordpress article", "publish to wordpress", "wp article", "wp post", "WordPress 文章", "发布到 WordPress". Do NOT trigger for: WeChat articles, Ghost posts, emails/newsletters, PPT, short video scripts.

Write and publish WeChat Official Account articles end-to-end with AI, or take an existing draft straight into the skill's built-in formatting + direct-send capability. Supports full pipeline from topic, plus ready-article direct send when the article is already written. Use when user says "写公众号文章" / "微信推文" / "发布到草稿箱" / "微信排版" / "WeChat publish". Do NOT trigger for: generic blogs, newsletters, PPT, short-video scripts, non-WeChat SEO work.

Generate webpages from a description — landing pages, portfolios, event pages. View, edit, and share with one click via YouMind. Use when user wants to "create webpage", "make website", "generate page", "landing page", "创建网页", "生成页面", "ウェブページ作成", "웹페이지 만들기".

Save any URL to your YouMind board with one command — instant web clipper for articles, videos, and documents. Works from terminal, CI/CD, and any agent platform. Use when user wants to "save link", "bookmark", "clip", "web clipper", "save URL", "save page", "保存链接", "收藏网页", "ブックマーク", "링크 저장".

Write and publish Tumblr-native posts with AI — topic shaping via YouMind knowledge base, Tumblr-first long-form writing, image-led publishing, notes/activity review, and queue control through the Tumblr blog already connected in YouMind. Use when user wants to "tumblr post", "publish to tumblr", "tumblr article", "tumblr photo post", "read tumblr notes", "Tumblr 文章", "发布到 Tumblr", "看 Tumblr 评论". Do NOT trigger for: X threads, WeChat articles, newsletters, PPT, or short video scripts.

Generate professional presentation slides from a topic or outline — complete decks you can view, edit, and download. Use when user wants to "create slides", "make presentation", "generate PPT", "PowerPoint", "slide deck", "做PPT", "生成幻灯片", "プレゼン作成", "슬라이드 만들기".

Write and publish Qiita articles with AI — topic research via YouMind knowledge base, Japanese developer-audience adapted writing, GFM Markdown with Qiita extensions, and one-click publishing. Use when user wants to "write Qiita article", "publish to Qiita", "post on Qiita", "Qiita に記事を投稿".

Write and publish Kit broadcasts with AI — topic research via YouMind knowledge base, creator-profile-aware broadcast writing, Markdown-to-HTML conversion, and publishing through the Kit account already connected in YouMind. Use when user wants to "write Kit article", "publish to Kit", "Kit broadcast", "ConvertKit article", "写 Kit 文章", "发布到 Kit".