rudometkin/GenAI-intensive - Page 2

clone-spec-writer

Generate full technical specification (TZ) from architecture analysis

clone-testing

Comprehensive testing -- unit, E2E, visual comparison with original, performance, security

cddc-canvas

This skill should be used when the user asks to "create CDDC", "review CDDC", "improve CDDC", "customer development design canvas", "hypothesis validation", "custdev canvas", "CDDC for project", "review CDDC", "improve CDDC", "hypothesis decomposition", "from…

code-reviewer

Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback,…

de-ai-ify

Removes AI jargon and cliches from text, making it sound human. Use when user says "remove AI style", "de-ai-ify", "humanize text".

jtbd-analysis

This skill should be used when the user asks to "analyze a product by JTBD", "find segments", "build a job graph", "generate a landing page using JTBD", "compare landing with a reference site", "recruit respondents for JTBD research", or mentions "jtbd",…

market-research

This skill should be used when the user asks to "research a market", "analyze competitors", "estimate market size", "find market problems", "validate business model", "analyze search demand", or mentions "market research", "competitors", "market size", "unit…

product-pipeline

This skill should be used when the user asks to "run the full product pipeline", "from idea to product", "analyze the product fully", "product pipeline", "full product analysis", "from idea to product", or mentions running market research + JTBD + TZ as a…

senior-prompt-engineer

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization,…

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

think-through

This skill should be used when the user asks to "think through a problem", "let's think about this", "think through", "how best to", "help me decide", "let's figure out", or needs structured analysis of any non-code problem -- life decisions, business…

tsa-progon

Simulate audience reactions to any artifact (landing, post, feature, product, CustDev guide) through parallel multi-agent avatars. Each avatar provides honest first-person feedback. This skill should be used when the user says "audience test", "run through…

telegram-telethon

Use when user wants to parse Telegram channels/chats, monitor messages live, send messages, fetch participants, or do anything else via Telegram MTProto user-API. Antiban defaults baked in (flood-wait handling, rate limits, human-like sleeps, realistic device…

yd-find-segments

Находит семантические сегменты для рекламных кампаний и лендинга. Строит психологические слои аудитории, seed-фразы для Wordstat, анализирует статистику (CSV/XLSX), ищет неожиданные кластеры, выдаёт таблицу групп с ключами и минус-словами. Вызывай когда…

Source text: Russian

daily-dashboard

Generates a daily report from Claude Code sessions — groups by project, stats, HTML dashboard. Writes to DAILY_LOG.md, updates a single-page HTML dashboard, and optionally deploys.

Source text: Mixed languages

pushtogenai-public

Закидывает файл (или контент) в публичный репозиторий GenAI-intensive на GitHub. Копирует файл в локальную синкаемую папку, коммитит и пушит сразу. Триггеры - "закинь в GenAI", "опубликуй в GenAI", "/PushToGenAI_public", "в публичный GenAI", "в репо курса".

Source text: Russian