Скилл в Claude Code — это папка с SKILL.md внутри. При старте сессии модель видит метаданные и сама выбирает нужный под задачу. У меня сейчас 201 штук, из них 37 поставлены 27 мая по карусели @russgamzatov в Instagram. Ниже — кто за что отвечает.
npx repomix).content-matrix> Generate 32+ LinkedIn post ideas in a single table by pairing the user's content pillars with 8 proven content formats. Based on the Justin Welsh content matrix. Use this skill whook-generator> Generate 6 clickbait-style LinkedIn hook variations for any topic. Two-line hooks built on the formula: a 40-char opening line, a 40-char bold contrast line. Includes digits, "Honewsletter-voice> Build newsletter writing instructions inside a Cowork project. Runs after voice-builder. Produces newsletter-voice.md, a single file Claude references when drafting newsletters iniche-research> Surface the 20 most relevant stories in a niche from the last 7 days using Claude for Chrome. Verified dates, real links, shareable angles. Claude drives the browser to scroll Repost-formatter> Turn a topic into a ready-to-publish LinkedIn post using PAS, AIDA, BAB, STAR, or SLAY frameworks. 200 to 250 words, 20 lines max, mobile-formatted with blank lines between sentepost-scorer> Score a LinkedIn post using real performance data. Pulls the user's own post history via Apify (or uses cached data) to identify what actually performs, then scores the draft agapost-writer> Write LinkedIn posts that match the user's voice system (about-me.md and voice.md). Use this skill whenever the user says "write a post", "draft a post", "LinkedIn post", "post aprofile-optimizer> Rebuild a LinkedIn profile for maximum conversions. Produces new headline options, about section, experience section, featured section strategy, and 4 image generation prompts (breels-scripting> Turn a reference Instagram Reel into a script for your own Reel, tuned to your voice and repurposed from your newsletter content. Takes a Reel URL or Notion reference link, uses voice-builder> Build a personalised voice profile inside a Cowork project from a short interview plus 3 to 5 sample pieces of writing. Works for any content format: LinkedIn posts, newsletters,kb-ad-angle-multiplierExpand a core idea into multiple distinct ad angles. Trigger on "more ads", "creative testing", "scale campaigns".kb-avatar-extractionUse when you need to define exactly who the buyer is, what they want, what they’ve tried, and what’s driving their decisions. Trigger on "target audience", "ideal client", "who is kb-conversion-path-builderDesign the optimal funnel from click to conversion. Trigger on "funnel", "conversion path", "booked calls".kb-full-funnel-campaign-orchestratorCoordinate all skills to build a complete advertising campaign. Trigger on "build a campaign", "full funnel", "ads + funnel".kb-generic-language-killerRemove vague, corporate, or AI-sounding language and replace it with clear, specific, human wording. Trigger on "improve copy", "sounds generic", "too fluffy".kb-headline-matrixGenerate high-performing headline variations across different angles. Trigger on "headlines", "hooks", "ad copy", "email subject lines".kb-mechanism-builderUse when you need to explain why your solution works and others failed. Trigger on "unique mechanism", "why this works", "different angle", "positioning".kb-objection-crusherIdentify and neutralize buyer objections. Trigger on "why wouldn't someone buy", "objections", "hesitation", "conversion issues".kb-offer-extractionUse when you need to turn a product or service into a compelling, high-converting offer. Trigger on "offer", "why would someone buy", "improve conversions", "value proposition".kb-performance-diagnosisDiagnose why campaigns are underperforming. Trigger on "low performance", "high CPL", "bad ads".kb-schwartz-awareness-mapperUse when you need to determine audience awareness level and the correct messaging approach. Trigger on "awareness stage", "cold vs warm audience", "Schwartz", "message to market makb-scroll-stopping-creativeCreate ad concepts that stop attention in the first 3 seconds. Trigger on "ad creative", "thumbstopper", "video ideas".balancedConstructive, evidence-based dialogue mode that avoids sycophancy. This skill should be used when the user wants balanced multi-perspective analysis, critical feedback, or rigorouscognitive-toolkitEvidence-based CBT and DBT intervention skills — guided thought records, opposite action, DEAR MAN roleplay, crisis skills with optional HRV biofeedback. Configurable therapeutic pcontext-builderGenerate interactive AI transformation context-builder prompts for consulting clients. Use when creating structured discovery session prompts that guide a company through context gdaydream—decision-toolkitGenerate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dashboards. Use when facing significant choices requiring systemdeep-researchThis skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. It automates prompt enhancement through interactive clarifying quefirecrawl-researchThis skill should be used when the user requests to research topics using FireCrawl, enrich notes with web sources, search and scrape information, or write scientific/academic papegpt-image-2Generate and edit images using OpenAI's GPT Image 2 API. Interactive skill that guides users through image creation with style presets, cost-aware draft/final workflow, thinking moinsight-extractor—jtbdTerminal-first JTBD engine for founders and product people. Interview fast, kill jargon, capture real switching forces (Push/Pull/Habit/Anxiety), score opportunities, and export stskill-studioInterview-driven automation design tool. This skill should be used when the user wants to design a new skill, agent, automation, shortcut, or any other automatable workflow. Runs athinking-patterns—transcript-analyzerThis skill analyzes meeting transcripts to extract decisions, action items, opinions, questions, and terminology using Cerebras AI (llama-3.3-70b). Use this skill when the user askavoid-ai-writingAudit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit wrcomposition-patternsReact composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers dogfoodSystematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "tehuashu-design花叔Design（Huashu-Design）——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审的一体化设计能力。HTML是工具不是媒介，根据任务embody不同专家（UX设计师/动画师/幻灯片设计师/原型师），避免web design tropes。触发词：做原型、设计Demo、交互原型、HTML演示、动画DemoimpeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend tasteSenior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balancten-articleСоздание SEO-статьи для блога ten-miass.ru/blog/ по теме ТЭНов через артель из 4 AI-агентов (Claude → DeepSeek V4 Pro → GPT-5.5 → Gemini 2.5 Pro → Руслан). Дизайн — standalone HTMLten-miass-blog-styleСтиль-гайд для статей блога ten-miass.ru/blog/. Применять ко ВСЕМ новым статьям и при переоформлении существующих. Основан на дизайн-системе new.ten-miass.ru (paper-палитра, шрифт tesarus-blogДоступы и операции с блогом blog.tesarus74.ru — клиентский WP-блог про сварные заборы. Используется когда нужно править контент, конфиг, robots.txt или массово удалять/обновлять стwriting-plansUse when you have a spec or requirements for a multi-step task, before touching codewriting-skillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentПрефикс seo-. Покрывают: контент, схему, технику, локальный, ecommerce, AI-search (geo). Главные:
seo-auditFull website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates heaseo-backlinksBacklink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Works with free APIs (Moz, Bing Webmaster, Common Crawl) and seo-cluster> SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusterseo-competitor-pages> Generate SEO-optimized competitor comparison and alternatives pages. Covers "X vs Y" layouts, "alternatives to X" pages, feature matrices, schema markup, and conversion optimizatseo-content> Content quality and E-E-A-T analysis with AI citation readiness assessment. Use when user says "content quality", "E-E-A-T", "content analysis", "readability check", "thin contenseo-dataforseo> Live SEO data via DataForSEO MCP server. SERP analysis (Google, Bing, Yahoo, YouTube, Google Images), keyword research (volume, difficulty, intent, trends), backlink profiles, onseo-drift> SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO — baseline, diff, and track changes to your on-pageseo-ecommerce> E-commerce SEO analysis: Google Shopping visibility, Amazon marketplace intelligence, product schema validation, competitor pricing analysis, and marketplace keyword gaps. Combin+ ещё 14 специализированных.
Префикс seedance-. Шаблоны под разные форматы: 3d-cgi, anime-action, brand-story, cartoon, cinematic, ecommerce-ad, fashion-lookbook, fight-scenes, food-beverage, motion-design-ad, music-video, product-360, real-estate, social-hook, comic-to-video.
Полный фреймворк управления работой: проекты → milestone → phase → todo. Префикс gsd-. Часто используемые:
gsd-audit-fixAutonomous audit-to-fix pipeline — find issues, classify, fix, test, commit" argument-hint: "--source gsd-autonomousRun all remaining phases autonomously — discuss→plan→execute per phase" argument-hint: "[--from N] [--to N] [--only N] [--interactive]" allowed-tools: - Read - Write - Bash - Glob gsd-code-reviewReview source files changed during a phase for bugs, security issues, and code quality problems" argument-hint: "gsd-execute-phaseExecute all plans in a phase with wave-based parallelization" argument-hint: "gsd-helpShow available GSD commands and usage guide" allowed-tools: - Readgsd-new-milestoneStart a new milestone cycle — update PROJECT.md and route to requirements" argument-hint: "[milestone name, e.g., 'v1.1 Notifications']" allowed-tools: - Read - Write - Bash - Taskgsd-new-projectInitialize a new project with deep context gathering and PROJECT.md" argument-hint: "[--auto]" allowed-tools: - Read - Bash - Write - Task - AskUserQuestiongsd-nextAutomatically advance to the next logical step in the GSD workflow" allowed-tools: - Read - Bash - Grep - Glob - SlashCommandgsd-plan-phaseCreate detailed phase plan (PLAN.md) with verification loop" argument-hint: "[phase] [--auto] [--research] [--skip-research] [--gaps] [--skip-verify] [--prd gsd-shipCreate PR, run review, and prepare for merge after verification passes" argument-hint: "[phase number or milestone, e.g., '4' or 'v1.0']" allowed-tools: - Read - Bash - Grep - Glob…и ещё 75 штук в каталоге.
researchConduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.research-add-fieldsAdd field definitions to existing research outline. allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestionresearch-add-itemsAdd items (research objects) to existing research outline. allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestionresearch-deepRead research outline, launch independent agent for each item for deep research. Disable task output. allowed-tools: Bash, Read, Write, Glob, WebSearch, Taskresearch-reportSummarize deep research results into markdown report, cover all fields, skip uncertain values. allowed-tools: Read, Write, Glob, Bash, AskUserQuestionagent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extractingkie-image-videoГенерация изображений и видео через Kie.ai (GPT Image 2, Seedance, Grok). Использовать для hero/иллюстраций к статьям блога ten-miass.ru и для рилсов/презентаций.elba-billСоздание и просмотр счетов в Контур.Эльбе для ИП Садыкбаев Р.В. через REST API. Авто-выбор банка по стране клиента (RU → Альфа, KZ → Райффайзен). Есть готовый исполняемый скрипт `cmail-applicationsПроверка заявок в почтовых ящиках ТЭН-Миасс. Показывает ТОЛЬКО неотвеченные заявки. Применять при запросах «проверь почту», «заявки за сегодня», «кто ждёт ответа», «что в почте».artelАртель — фиксированная команда из 3 Telegram-ботов + Claude + Руслан для создания контента (статей, лендингов, креативов). Использовать для всех контент-задач объёмом от лендинга. beget-accessПравильная процедура входа на BEGET-хостинг Руслана. SSH к shared-аккаунту cubik только через офисный WSL (с моего сервера таймит). 13 доменов: ten1.ru, 3dmiass.ru, miassruslan.ru,deploy-to-vercelDeploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a previegroq-sttРаспознавание речи через Groq Whisper API. Используется как альтернатива/фолбэк офисному self-hosted Whisper на 178.46.162.246:8080 в Telegram-боте @Tenmiassbeget_bot.proxyHTTP/SOCKS5 прокси для обхода RU-блокировок (Groq, Telegram, OpenAI). Использовать когда сервис возвращает 403 с RU-IP или TCP к Telegram-DC не открывается.slackInteract with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conusing-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection yandex-metrika-stats—brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design befodispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesexecuting-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsfinishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for mreact-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimareceiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verificatirequesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirementssubagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionsystematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixestest-driven-developmentUse when implementing any feature or bugfix, before writing implementation codeusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questionsverification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any succmiassruslan-channelПубликация постов и Stories в личный Telegram-канал Руслана @miassruslan_blog. Канал зеркалит сайт miassruslan.ru и синхронизируется в Дзен через @zen_sync_bot. Используется для лиmiassruslan-hostingКак устроен хостинг сайта https://miassruslan.ru на офисном ПК (WSL Ubuntu + nginx). Цепочка проброса портов, конфиг nginx, поддомены test1-5, SSL Let's Encrypt.miassruslan-personal-blogПубликация ЛИЧНЫХ статей Руслана на сайте miassruslan.ru. Сайт лежит на офисном ПК (WSL Ubuntu, nginx, /var/www/miassruslan.ru/), НЕ на Vercel. Личное — кейсы автоматизации, разборseoComprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability, indexability, Core Web Vitals with INP), schema maniche-research → тему по запросам.
daydream → угол.
post-writer + avoid-ai-writing → черновик.
kb-headline-matrix → заголовок.
kb-generic-language-killer → почистить шаблонщину.
post-scorer → оценить ДО публикации.
seo-content + seo-geo + seo-schema → SEO + AI-поиск.
kb-objection-crusher → FAQ-блок.
impeccable → финальный аудит на AI-слоп.
kb-avatar-extraction → портрет покупателя (для инженера-снабженца, фермера, технолога).
kb-offer-extraction → что именно продаётся.
kb-schwartz-awareness-mapper → 5 уровней осведомлённости.
kb-mechanism-builder → техническое обоснование «почему наше работает».
kb-conversion-path-builder → CTA на каждый уровень.
balanced заменяет «да, делаю» на сократический диалог: «вот три причины, почему это не сработает». Особенно когда я ловлю модель на лёгком согласии с плохой идеей.
decision-toolkit — для важных переключений.
de-ai — детектор AI-стиля в своих же текстах.
jtbd — преобразует расшифровку интервью в JTBD-фреймворк.
transcript-analyzer — общий разбор переписки.
insight-extractor — извлечь паттерны.
В связке с cognitive-toolkit и thinking-patterns — слепые зоны.
skill-seekers берёт PDF/доки/GitHub-репо и конвертирует в формат Claude skill за несколько минут. То есть из документации Wazzup API → готовый wazzup-helper.skill.
skill-studio — собирает скилл из коротких инструкций.