Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Marketing & growth
Weekly read of your Meta-ads performance Base: names in plain language whose problem this week's numbers are, and refuses to advise when an opening check fails. Installing the Base is /breakthrough-performance-db-setup.
One-time install of your Meta ad performance database: copy the template Lark Base, wire the daily sync to your own Meta token, reconcile it against Ads Manager, and leave a pointer note in your vault. The weekly read of the installed Base is /breakthrough-performance-analysis.
Amazon category automated product-selection analysis skill. Runs in-depth market research on Amazon categories using a five-dimension scoring model and generates a Markdown analysis report. Triggered when the user runs the /category-selection command or asks to "analyze category XX", "category XX market research", "category XX product selection", etc. Supports configuring the number of analyses, default Top20.
Comprehensive GTM analysis of any target company. Researches what a company is currently doing across all go-to-market dimensions — content/blog, founder LinkedIn activity, SEO/traffic, hiring signals, social/community presence, customer acquisition channels, podcast appearances, review sites, competitive positioning, and partnerships. Produces a structured report identifying what's working, what's missing, and where white space exists for new strategies. Use before designing GTM strategies for a client or prospect.
Enrich contacts with LinkedIn URLs, verified work/personal emails, and phone numbers through the ColdIQ marketplace, layering providers cheapest-first. Use when finding emails for a list, building an email waterfall, verifying deliverability, finding phone numbers, resolving company LinkedIn URLs from domains, or enriching contacts before a campaign. Triggers on "enrich contacts", "find emails", "email waterfall", "verify emails", "bounce check", "find phone numbers", "company LinkedIn URL", "enrich before campaign", "deliverability". Do NOT use for prospecting/search to BUILD a list (see coldiq-search-enrich / apollo-search) or list dedup (see list-dedup).
Improve an existing website or web app's decision clarity, trust, forms, UX copy, and accessibility without dark patterns. Use when an agent must polish CTAs, navigation, pricing, onboarding, empty or error states, keyboard behavior, semantic HTML, focus, contrast, or the end-to-end conversion path.
Generate high-converting, deep-dive growth case studies in MDX format. Use this skill when asked to write a case study or blog post about a company's growth, tech stack, or product-led strategy. It handles the full pipeline (researching the company via Tavily, generating a 16:9 cover image, quality checking the draft, uploading assets to cloud storage, and pushing directly to the target repository).
Design and audit creator, seller, developer, plugin author, marketplace contributor, community moderator, and content partner onboarding for marketplaces, app stores, skill repositories, template stores, game UGC, creator economies, affiliate programs, and developer ecosystems. Use when improving submission readiness, quality, trust, payout setup, review queues, publishing, analytics, support, and creator activation.
Render a cold-outreach email sequence from a fixed template set and a contact CSV whose input fields are already filled. Deterministic — variant routing + placeholder substitution, no per-row LLM call. The render contract (newline model, per-target escaping, operation order) is the core of this skill. Triggers on: "generate emails", "email generation", "run emails", "render emails", "create emails", "email pipeline", "generate outreach".
Use for data-first company, contact, lead, and prospect discovery or enrichment, including firmographic or technographic completion, named-company profiling, entity resolution, ICP matching, prospect-list building, segmentation, trigger or sales-signal analysis, market and territory scans, and enrichment-backed comparisons. Exclude meeting preparation, outreach-led company research, and prioritization of an already established account book.
Design enrichment columns that bridge research hypotheses to list enrichment. Two modes: segmentation (columns that score hypothesis fit per company) and personalization (columns for company-specific hooks). Interactive column design with the user. Outputs ready-to-run column_configs for list-enrichment. Triggers on: "data points", "enrichment columns", "column design", "what to research", "data point builder", "build columns", "segmentation columns", "personalization columns".
Take a new feature or product update and generate the full launch kit: changelog entry, email announcement, LinkedIn post variants, in-app banner text, Twitter/X thread, and internal sales enablement one-pager. Pure reasoning skill that chains product context with audience-specific copy generation. Use when a product marketing team needs to turn a feature spec into launch-ready assets fast.
End-to-end funding signal composite. Takes any set of companies, detects recent funding events, qualifies against your company context, finds relevant people (buyers, champions, users), and drafts personalized outreach. Tool-agnostic — works with any company source, contact finder, and outreach platform.
Orchestrate the full GTM strategy flow for an IT agency from a website URL (cold audit). Use when the user wants a complete go-to-market strategy, a GTM audit, an agency-stage diagnosis followed by ICP, value prop, offers, competitor and buyer-journey work, or a 30-90-180 action plan from just a site. Ukrainian triggers include зроби GTM стратегію для url, GTM аудит агенції, побудуй go-to-market, стратегія з сайту, 30-90-180 план. Runs stage-adaptively, stops at 3 checkpoints, and writes every artifact to Notion in Ukrainian.
Elimina patrones de escritura típicos de IA en textos en español de España para que suenen naturales y humanos. Aplica esta skill siempre que generes, edites o revises textos en español: artículos, guías, tutoriales, emails, copy comercial, publicaciones en redes sociales, documentación, informes o cualquier prosa. Actívala también cuando el usuario pida humanizar texto, eliminar tono robótico, mejorar la naturalidad de un texto, o cuando mencione que algo suena a IA, a ChatGPT o a texto generado automáticamente.
Discover product ideas, validate them, and build MVPs. Search trending tools across Product Hunt, GitHub, Indie Hackers, XiaoHongShu, V2EX, SSPAI, etc. Validate feasibility via market research and competitive analysis. Build MVPs. Send reports via email. Triggers: 'find ideas', 'search products', 'trending tools', 'product ideas', 'validate my idea', 'build MVP', 'market research', 'competitive analysis', 'indie hacker', 'send email', '找想法', '搜产品', '找灵感', '产品调研', '验证想法', '构建MVP', '发邮件', '发送报告'.
Remove the AI tells readers react to in an Instagram caption or carousel slide: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, emoji storms; caps em dashes. Includes --mode audit (first-125 hook, length, hashtags, emoji, CTA, media) and --mode profile. Not for beating AI detectors (no edit reliably does). Not for writing from scratch (use ig-caption-writer or ig-carousel-planner). Keywords: humanize, de-AI caption, audit before posting.
Manage a Nexor customer's iMessage (Apple blue-bubble) channel end to end through Nexor MCP tools: read the paid add-on offer and price, buy and provision a dedicated iMessage number (via Dial), poll it to ready, assign it to an agent, set the name and profile photo leads see, and send iMessage. Use whenever a customer asks about iMessage / blue bubble, its price or cost, wants to see, buy, provision, or assign an iMessage number, wants to change the name or photo shown on their iMessage, asks whether their iMessage is set up or which agent owns it, or wants to send an iMessage. iMessage bills at a FLAT $350/month per number — currently the only Nexor channel on a flat rate (all others are usage-based). iMessage has its OWN inventory and tools — it is NOT the Phone/SMS voice line, so never read its state from list_phone_numbers.
Triages all inbound leads from a given period — demo requests, free trial signups, content downloads, webinar registrations, chatbot conversations. Classifies by urgency, qualifies against ICP, enriches with context, and produces a prioritized action queue with recommended response for each lead. Tool-agnostic — works with any CRM, form tool, or lead source.
Strategic guidance for setting up the right data integration -- workflow selection, field mapping, and configuration. Use when the user needs help choosing the right integration approach, wants advice on field mapping, or needs to plan a data integration.
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.
Detect buying intent from job postings. When a company posts a job in your problem area, they've allocated budget and are actively thinking about the problem. This skill finds those companies, qualifies them, extracts personalization context, and outputs everything to a Google Sheet. Does NOT do outreach — just delivers qualified leads with reasoning.
Track what key opinion leaders (KOLs) in your space are posting on LinkedIn and Twitter/X. Surfaces trending narratives, high-engagement topics, and early signals of emerging conversations before they peak. Chains linkedin-profile-post-scraper and twitter-mention-tracker. Use when a marketing team wants to ride trends rather than create them from scratch, or when a founder wants to know which topics are resonating with their audience.
Create and critique launch narratives for products, features, SaaS, apps, games, developer tools, marketplaces, pricing changes, public repositories, and campaigns. Use when shaping launch positioning, audience, category, story arc, proof, demo, objections, announcement copy, changelog, founder note, launch post, press angle, community post, or go-to-market message.
Produce a LinkedIn-native 1:1 (or 16:9) launch video using HyperFrames. Caption-first, sound-off, B2B register, anti-corporate-jargon. Optionally hand off to LinkedIn Ads to launch as a sponsored content campaign with ICP-aligned targeting.
Build targeted company lists for outbound campaigns using Extruct. Use when the user wants to: (1) find companies matching an ICP, (2) build a prospect or outbound list, (3) search for companies by description, (4) discover companies in a market segment, (5) create a target account list, (6) research a competitive landscape, (7) find lookalike companies from a seed list. Triggers on: "find companies", "build a list", "company search", "prospect list", "target accounts", "outbound list", "discover companies", "ICP search", "lookalike search", "seed company".
Add research-powered enrichment columns to Extruct company tables. Use when the user wants to add enrichment columns (e.g. funding, verticals, tech stack) to an existing Extruct table, run column configs from enrichment-design, or monitor enrichment progress. Triggers on: "enrich", "add column", "add data point", "research column", "enrich table", "enrichment", "add a field", "run enrichment", "monitor enrichment".
Generates and maintains a standards-compliant llms.txt file for any website — either by crawling the live site OR by reading the website's codebase directly. Use this skill when asked to create an llms.txt, add AI discoverability to a site, improve GEO (Generative Engine Optimization), make a website readable by AI agents, generate an llms-full.txt, check if a site has llms.txt, or audit a site's AI readiness for generative search. Trigger this skill any time a user mentions llms.txt, AI discoverability, LLM site readability, or wants their site to appear in AI-generated answers. Also trigger when the user is inside a website codebase and asks about SEO, AI readiness, or content structure.
Make websites, docs, blogs, or landing pages visible and readable to LLMs and AI agents — ChatGPT, Claude, Perplexity, Cursor, Claude Code, and other coding agents that fetch URLs. Use this for any request involving llms.txt, llms-full.txt, serving .md/Markdown versions of pages, Accept text/markdown content negotiation, Link rel="alternate" headers, Cloudflare Content-Signal in robots.txt, GEO (generative engine optimization), AI-friendly / AI-readable / LLM-discoverable sites, getting cited in ChatGPT or Perplexity answers, or fixing pages where AI tools fetch JavaScript bundles or empty React roots instead of content. Also use to push back on debunked patterns: ai.txt, AI meta tags, hidden HTML comments, AI toggle buttons, User-Agent sniffing, JSON-LD aimed at LLMs. Do NOT use for traditional Google SEO, sitemap.xml, schema.org rich snippets for search engines, WCAG/accessibility audits, or CSP/security headers.
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.