Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Marketing & growth
Write and sequence multi-email nurture or launch campaigns. Use when asked for an email sequence, drip campaign, onboarding emails, product launch emails, or nurture flow. Produces subject lines, preview text, full email body, and send-timing recommendations for each email in the sequence.
Skip the learning curve of professional editing software. Describe what you want — create a 30-second video from this text: 'Introducing our new coffee blend — rich, smooth, and ethically sourced.' — and get ready-to-share videos back in 1-2 minutes. Upload TXT, DOCX, PDF, plain text files up to 500MB, and the AI handles AI video creation automatically. Ideal for marketers, content creators, small business owners who want videos without cameras, actors, or editing software.
Write prose that sounds authentically human rather than AI-generated. Use this skill whenever writing long-form content, emails, articles, reports, documentation, blog posts, creative writing, social media copy, proposals, memos, or any text where sounding like a real person matters. Triggers on requests like "write this naturally," "make it sound human," "don't sound like AI," "write like a real person," or any writing task where the user has indicated they want authentic, non-robotic prose. Also use when editing existing text to remove AI-sounding patterns.
Use when mentioning Chaos courses, course study, methodologies, mental models, course search, or distilling course transcripts; when extracting value points / sparking ideas / summarizing selling points / pricing products & services / uncovering startup opportunities; or when asked general business decision questions.
Design intentional internal link graphs for SEO, UX, and LLM-readable sites. Use this skill when the user asks for links between short briefs, longform articles, topics, projects, author pages, breadcrumbs, source trails, related stories, orphan-page checks, overlink checks, anchor intent, or validation that a link graph reinforces the canonical content model without creating duplicate story bodies or hidden links.
Toutiao content and operations methodology. Use for: (1) producing and self-checking Toutiao headlines against four headline formulas, (2) writing articles/micro-posts with three high-completion-rate structures, (3) diagnosing impression and click-through data using recommendation algorithm logic (cold start/tag matching/interaction weight), (4) account positioning and publishing-time planning. Toutiao content methodology: headline formulas, retention-optimized structures, recommendation-algorithm-informed diagnostics.
Find content topics and prioritize them without expensive SEO tools. Use when planning a content strategy, deciding what to write about, or doing keyword research on a budget. Uses the 6 Circles Method for systematic topic discovery and prioritization.
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Fixes the catalogue of tells — gradient/glow defaults, glassmorphism, badge & pill spam, pastel tiles, AI-drawn icons, AI copywriting voice ("not just X — it's Y"), emoji everywhere, and more — see `references/taxonomy.md` for the full list. Works on HTML/CSS, React/Vue/Svelte/Astro, Tailwind, PHP, and Markdown copy. For plain-text editing of Chinese or English writing outside a codebase, use `de-slop` instead.
Find Key Opinion Leaders (KOLs) in a given domain by combining web research with LinkedIn post search. Given a company/idea and target domain, generates authority keywords, searches LinkedIn posts to find prolific authors with high engagement, and merges with web-researched influencers. Use when someone wants to "find influencers in X space" or "who are the KOLs for Y industry."
Prepare and run a Hacker News "Show HN" launch end to end — HN is STRICTER than every other channel: it **forbids all vote mobilization** (no supporter waves, no asking anyone to upvote, ever). Grounds in the real product (real stack, honest limits), then writes a small, paste-ready package to `.ulpi/launch/hacker-news/`: `POST.md` (the standard `Show HN: <thing> – <plain description>` title + the URL + the founder's technical, no-hype first comment), `PLAN.md` (US-Eastern timing, the first-1–2-hours plan, a thread-engagement plan with prepared answers to hard questions, and the post-launch / second-chance plan), and `CHECKLIST.md` (a blocking readiness gate). The HN runner of the launch-* family: it owns Show HN rules, HN policy, the thread runbook, and the gate, and composes the shared `launch-copy` (title + first comment) and `launch-analytics` (UTM + conversion tracking), degrading to built-in fallbacks if a companion isn't installed. Rewards technical honesty and a present, non-defensive founder; punishes hype and signup-walled products. Use when the user wants to post a Show HN or plan an HN launch.
Research competitors, analyze their messaging, and generate a positioning document with category definition, differentiation claims, value propositions, and proof points. Chains web research, competitor site analysis, and review mining to produce a positioning doc ready for website copy and sales deck use. Use when a product marketing team needs to define or refresh positioning ahead of a launch, rebrand, or competitive shift.
Assesses pre-launch readiness across every function and produces an explicit Go / Conditional Go / No-Go recommendation. Use when preparing for any product or feature launch, running a pre-launch review, or determining whether a release is safe to ship. Produces a function-by-function readiness status, a ranked blockers list with owners and deadlines, a risk register, and a clearly reasoned launch recommendation.
Prepare and run a product launch on X (formerly Twitter) end to end — the external link goes in a REPLY, not the main tweet, so reach isn't penalized. Grounds in the real product, then writes a paste-ready package to `.ulpi/launch/x/`: `POST.md` (the launch **thread** — a scroll-stopping hook tweet, the thread body, native media, and the product link in a reply), `PLAN.md` (timing, the **golden-hour** engagement runbook, cross-promotion, and the post-launch plan), and `CHECKLIST.md` (a blocking pre-flight gate). The X runner of the launch-* family: it owns X mechanics, format rules, and the gate, and composes the shared `launch-copy` (thread copy), `launch-outreach` (team amplification, mode `x`), and `launch-analytics` (UTM + conversion tracking), degrading to built-in fallbacks if a companion isn't installed. Reads the shared `.ulpi/launch/positioning.md`. Engagement asks to your own audience are fine (no vote-ring rules), but it avoids what X penalizes — a link in the main tweet, engagement-bait, and bought engagement. Use when the user wants an X launch thread written and launch day planned.
Plan and record evidence-backed LLM and AI-search citation checks across approved assistant/search surfaces with timestamped queries, locales, modes, cited URLs, snippets, screenshots or transcripts, and caveats. Use this skill when the user asks whether ChatGPT, Perplexity, Claude, Gemini, Copilot, or another assistant cites a target site, but do not claim citation without direct evidence.
Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when the user asks for llms.txt, LLM discovery plans, visible TLDR or direct-answer blocks, source trails, entity pages, markdown alternates, AI crawler policy, topic-to-URL maps, assistant-readable public content, or LLM-friendly architecture that must preserve canonical SEO strategy without hidden bot-only facts or duplicate story bodies.
Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template phrases, transition word density, sentence uniformity, paragraph pattern repetition, and other signals that WeChat uses to flag AI content. Outputs a risk report and an optional humanized rewrite. Use when the user wants to check if an article looks AI-generated, make an article more human-like, bypass WeChat AI detection, or humanize AI-written content. Also trigger when the user mentions "去AI痕迹", "人性化润色", "微信AI检测", "anti-ai-check", "humanize article", "公众号发文检查".
Indie maker playbook for bootstrapped apps inspired by Pieter Levels' MAKE: The Indie Maker Blueprint. Use when a user is starting or sizing an app idea, choosing what to build next, building a minimal product, preparing a launch, diagnosing stalled growth, deciding pricing or monetization, automating operations, maintaining a per-app MAKE.md tracker, or evaluating whether to sell a product.
When the user wants to optimize markdown strategy, price optimization for clearance, or minimize inventory markdowns. Also use when the user mentions "markdown," "clearance pricing," "price elasticity," "promotional pricing," "discount optimization," "sell-through," "inventory liquidation," or "dynamic pricing." For initial allocation, see retail-allocation. For promotional planning, see promotional-planning.
Use when you need marketing ideas, inspiration or strategies. Trigger words: marketing ideas, growth ideas, how to market, marketing strategies, marketing tactics, ways to promote, ideas to grow. Provides 140 proven marketing methods, organized by category.
Plan safe website migrations when existing URLs, redirects, sitemap, robots, schema, canonical pages, metadata, analytics, webmaster tools, or launch monitoring may change. Use after existing-site analysis or rebuild decisions; never apply production redirects, DNS, deploy, or webmaster mutations without explicit approval.
Use when Viktor wants to invent offers FAST for an IT-agency client and test them with outbound. From a client website URL, generates 5–10 testable offer-bets (ICP × pain × mechanism), scores them, and expands the winners into outbound-ready cards with built-in test design. Trigger when the user says “придумай офери для клієнта,” “що продавати цій агенції,” “офери під аутбаунд,” “build offers from this URL,” “offer factory,” “розроби офер для [клієнт],” or pastes an agency URL and asks what to sell/test. NOT for choosing WHO+WHICH-SIGNAL to target (use hypothesis-builder / hypo-generator for that) — this skill is about the OFFER itself.
When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," or "overlay." For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro.
The EU public procurement corpus searchable offline, with contactable leads from contract award winners. Trigger phrases: `find EU procurement contracts`, `who won construction contracts in Germany`, `leads from tender award winners`, `open tenders expiring soon`, `use eu-tenders`, `run eu-tenders-pp-cli`.
Etsy niche research whose scores come with their evidence attached — seeded search, honest confidence, and a local store that turns repeat research into trends. Trigger phrases: `research the dad shirt niche on Etsy`, `is this Etsy niche low competition`, `find low-competition Etsy sub-niches under dad`, `what tags do winning Etsy listings use for this niche`, `size up the competitors in this Etsy niche`, `use everbee`, `run everbee`.
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.
When the user needs to research a prospect before a sales call, wants a pre-call intelligence brief, needs to understand a potential customer or partner, or says things like 'research this company,' 'I have a call with [company],' 'what should I know about,' 'prep me on this prospect,' 'look into [company] before my call.' For discovery call planning, see meeting-prep.
Russian-language project editorial policy: a short interview, extracting voice from examples, and a `.agents/redpolitika.md` file for editorial skills. Use this skill whenever the user asks to create, update, remember, formalize, or apply a project editorial policy, tone of voice, style guide, vocabulary, forbidden words, or reusable writing context. Triggers: «настрой редполитику», «редполитика», «запомни мой стиль», «создай гайд по стилю», «tone of voice», «ToV», «настрой скилл под наш проект», «как нам писать», «зафиксируй голос», «добавь в редполитику», «обнови правила тона», «словарь проекта», «запрещённые слова», «пиши в нашем стиле», «сохрани правила редакции». Also suggest this skill when redaktura, statya, or ux-copy lacks project context and the user will keep working with the same product. For editing a finished text, see the redaktura skill; for writing articles from scratch — statya; for interfaces — ux-copy.
Mobile and web push notification strategy — opt-in optimization, rich push, segmentation, timing, frequency capping, deep linking, A/B testing, and analytics. Covers strategy and implementation across Braze, OneSignal, Airship, Firebase/FCM, Customer.io, Klaviyo, Iterable, and MoEngage. Use when push opt-in rates are low, users are disabling notifications, push campaigns get poor click-through, you're unsure which push provider to pick, or notifications feel spammy and drive uninstalls. Do NOT use for in-app messages (use /sales-in-app-messaging), email marketing (use /sales-email-marketing), SMS/WhatsApp messaging (use /sales-braze or platform-specific skill), or cold outbound (use /sales-cadence). For Braze-specific help, use /sales-braze. For Customer.io-specific help, use /sales-customerio.
Build evidence-labeled semantic cores for SEO, LLM-readable architecture, and site information design. Use this skill when the user asks for semantic core, query clusters, search intents, audience segments, entity/topic maps, language or locale priorities, competitor/source evidence, pillar-topic planning, or a structured handoff before URL architecture and internal linking. It must mark unknown search volume, difficulty, and ranking data as unknown instead of inventing metrics.
Build an evidence-labeled semantic core and crawlable site structure from keyword harvests, existing content, or user-provided search-demand data. Use before SEO/LLM site architecture, concept prototypes, paid traffic planning, IA, or public-site redesign decisions.
Expert guide for Schema.org structured data and JSON-LD implementation. Use when creating schema markup, validating structured data, implementing rich results (FAQ, HowTo, Product, Article, LocalBusiness, Breadcrumb, Organization, etc.), troubleshooting rich snippet eligibility, or understanding Google's structured data requirements.
Xiaohongshu personal note data review — based on the note data from the user's own creator backend (Creator Center / Pugongying), it does funnel diagnosis, bottleneck attribution and cross-note pattern discovery. Use when the user says "note data review", "why did this one get no traffic", "take a look at this one's data for me", "Xiaohongshu data analysis", "high impressions but no clicks", "follower growth is bad", "which type of content should I double down on", "I exported my backend data, help me take a look", or directly pastes backend data screenshots/CSV/Excel/a few numbers. It only analyzes the performance of notes on the user's own account; it does not scrape platform data or do engagement farming.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.