Marketing & Growth

nicolasakf Bundle

Install, configure, deploy, verify, or troubleshoot Agentize in website-owner repositories to expose first-party semantic search under /agents/*. Use for Agentize integrations, not arbitrary-site crawling or general SEO search.

nageshwarreddyl Bundle

Customer Marketing Response Skill

paulohfs Skill

Checklist técnico de pré-lançamento para Frontend. Use ao preparar releases de aplicações web, SPAs, sites estáticos ou qualquer interface voltada ao usuário final. Cobre layout, SEO, performance, acessibilidade, resiliência e formulários.

gaojuzhang Bundle

Audit and improve website SEO and Google Analytics/Search Console setup. Covers on-page SEO, technical SEO, content strategy, ethical backlinks, GA4 gtag, sitemap/robots, canonical/indexing. Use when the user asks about SEO, Search Console, Google Analytics, gtag, sitemap, robots.txt, meta tags, schema, 外链, backlinks, 收录, or how to analyze/optimize a page for Google.

gaojuzhang Bundle

Deploy a local static HTML/CSS/JS marketing site to Cloudflare using Workers Static Assets (Git + wrangler), custom domain, and apex→www redirect. Use when the user asks to deploy a static website to Cloudflare, Cloudflare Workers, Cloudflare Pages, workers.dev, custom domain DNS from Namecheap, 404.html, wrangler.jsonc, .assetsignore, or kakar/ForgeLumen-style static hosting.

conn-skill Bundle

Prepare a local market check, domain-ranking snapshot or keyword-demand task for an AI agent. Resolve location, read the free quote and approve one paid JSON result via x402 (USDC on Base). Use for local Google search and Maps observations, observed competitor domains, optional own-domain presence, rankings or keyword research. Additional services are discoverable at agent.connskill.com; missing and partial results remain explicit.

designupadm Bundle

Builds conversion-oriented cold outreach email campaigns, including ICP segmentation, research-backed personalization, subject line generation, opener writing, deliverability preflight checks, multi-email sequencing, measurement planning, and final QA. Asks for the product, audience, and campaign goal before drafting when they are missing. Use when drafting outbound prospecting emails, preparing launch-ready cold email campaigns, rewriting underperforming cold email copy, or building reply-focused assets for sales, partnerships, or founder-led outreach.

supershary Bundle

Use when the user types /council, says use or using the council, asks to convene, summon or ask the council, wants a board of advisors, an expert panel, a roundtable, a debate, a second opinion or a devil's advocate on a decision, or asks what Warren Buffett, Charlie Munger, Elon Musk, Steve Jobs, Albert Einstein, Richard Feynman, Chanakya, Sun Tzu, Marcus Aurelius or another legendary mind would do or say about their situation. Also use when the user faces a hard, high-stakes or many-sided decision and wants several expert perspectives argued and a final call - money and investing, savings, debt or buying a home; quitting a job to start, fund or pivot a startup; software, AI or infrastructure architecture and build vs buy; product, design and what to build or cut; marketing, sales, pricing and YouTube or social media growth; negotiation, competition and strategy; leadership, hiring, firing and co-founder conflict; career, purpose and life choices.

jeetaksh25 Bundle

Use when building, redesigning, styling or polishing any user interface - landing pages, marketing or SaaS pages, dashboards, admin panels, web apps, mobile screens, or a single component - where the result should look designed by a senior product designer rather than generated by AI. Use it whenever the user asks for UI work or mentions a landing page, hero, pricing page, dashboard, shadcn, Tailwind, animations or transitions, or "make it look good/professional/modern", even if the skill is not named and the task looks small. It installs the upstream design skills, scouts award-winning galleries, template prompts and animated component registries, then composes from shadcn/ui and those libraries instead of inventing layout, motion and styling from scratch. Trigger phrases include "beyond-ui", "no AI slop", "make it beautiful", "award-winning", "awwwards level", "design a landing page", "build the UI", "redesign this page", "it looks AI generated", "add animations", "polish the UI".

jeetaksh25 Bundle

Use when a project must be taken from "it works" to production-ready - a full autonomous hardening pass over performance, database, API, security, UX, accessibility, SEO, legal, observability, ops and code hygiene. Trigger phrases include "make it production ready", "production-suite-completion", "harden this app", "professional pass", "audit and fix everything", "ship-ready", "run the full production checklist", "verify everything and fix until green". Not for single-file bug fixes or one-off feature work.

m1nga Bundle

Turn visual references and feedback into brand direction, web design, and verified implementation within the requested scope. Use for reference-led design collaboration, refining AI-generated interfaces, or when the user says 照这个参考做 / 品牌方向 / 改这个界面 / 网页设计 / 视觉稿 / 这版看着不对. Keep project assets and decisions in the project, not in this skill. Not for unrelated coding, marketing copy alone, or a first-time-user experience report (product-experience-officer).

markkirby125 Bundle

Use when designing, writing, auditing, or refactoring landing page hero sections to maximize conversion through text-first visual hierarchy, objection demolition, and eliminating decorative visual friction.

abdussalam-mujeeb-ur-rahman Bundle

Research, plan, visually explore, implement, and quality-assure a credible business website from an existing site, public business information, supplied materials, or a brief. Use for client website concepts, redesign pitches, complete business sites, industry-specific web design, three-option section exploration, selected-design implementation, responsive QA, SEO planning, or when continuing an existing website project without repeating the full workflow.

heznpc Bundle

Turn external research from GitHub trending, similar repos, blog posts, PM/marketing tools, and agent skills into evidence-backed product TODOs for starter-series projects, especially take-a-repo demo/store-asset automation. Use when asked to scout tools or patterns, compare research candidates, reduce missed research, evaluate adopt/adapt/reject decisions, or hand off work across role-separated scout, critic, and integrator prompts.

jenkinsjamall Bundle

Strip AI-writing tells out of LONG-FORM PROSE — nurture emails, sales pages, product docs, lead magnets, landing copy, anything buyer-facing that reads like a chatbot wrote it. Use WHENEVER the user wants copy to sound human, says a draft "sounds like AI" or "sounds like ChatGPT", asks to de-slop / humanize / clean up marketing copy, or is reviewing a raw Claude draft of an email or sales page before it ships. Trigger on "/humanizer", "humanize this", "make this sound human", "remove the AI tells", "does this sound like AI?", "de-slop this email". Applies the full 33-pattern Wikipedia "Signs of AI writing" ruleset (vendored in references/patterns.md), calibrated to the user's OWN stated voice so it does NOT flatten it. Do NOT use this on short-form VIDEO SCRIPTS — those have their own de-slop pass (gate C in content-script-generation), tuned for spoken word with different overrides. This skill EDITS existing prose; it does not write new copy from scratch.

igdigitallab Bundle

Build a client a real small-business marketing site end to end: 10-question intake, fact mining from their Instagram / old site / flyer, a spec, a design system, mobile-first build on Astro + Tailwind, SEO/AEO, a lead form, legal pages, deploy, QA, and handoff. Use when a client wants a business site, a landing page, or a one-pager, or has sent back a filled-in intake form.

mantlecurve Bundle

Build or improve SEO-ready websites and CMS editors with service and location hierarchies, metadata, social previews, structured data, AI-assisted content editing, mobile performance, and verifiable audit reports. Use for implementing SEO/AEO/GEO features, adapting WordPress SEO plugin patterns to a custom CMS, or auditing a local-service site.

nitroxinteligence Bundle

Audita e corrige a landing page React + Vite antes do encerramento da aula, cobrindo mobile, contraste, acessibilidade prática, navegação, WhatsApp, SEO, performance, imagens, movimento e aparência não genérica. Use somente quando o usuário invocar $skill-aula-revisao-final. Não publica o site nem inventa dados para eliminar pendências.

comedianhhh Skill

Reposition real experience for a target role using only career/facts.md — positioning line, summary, bullet rewrites into career/blocks.md, a LinkedIn recruiter note, cold email, and a short self-introduction. Use when the user types /great-resume, asks to strengthen or rewrite experience or project bullets, or wants recruiter outreach text. Building the HTML/PDF file is /make-resume.

ldphuong-vn Bundle

Orchestrator for the validation pipeline. Use this whenever the user wants to validate an idea, product, feature, pivot, or a point decision (pricing, channel, kill/sunset) — to prepare for GTM or to run a full-lifecycle operating review. Triggers on "validate this", "should we build/ship/kill X", "stress-test this idea", "is this worth pursuing", "GTM readiness", or any request to vet a concept and produce a decision with evidence and critique. This skill runs Intake (classifies the case and routes the stages), executes the staged gates in order, streams progress to the console, and renders an HTML Validation Dossier at the end. Always use this rather than improvising an ad-hoc analysis, so the result is gated, evidence-based, and recorded in a reusable Dossier.

ldphuong-vn Skill

GTM Plan (Stage 7)

ldphuong-vn Skill

Stage 4 of the validation pipeline — market and go-to-market viability. Use to size the market (TAM/SAM/SOM), pick a beachhead, and pressure-test positioning against incumbents. Triggers when the orchestrator routes to MARKET_GTM. Apply the red-team lens here. Always run before committing to a business model.

guysilvere Bundle

Validation complète d'une PWA avant commit et déploiement — tests locaux via Caddy (.test), lint, typecheck, tests unitaires, build, Lighthouse, audits a11y/SEO/sécurité, checklist pré-commit. Charger avant chaque commit (via ops-quality) pour valider build, performances, accessibilité et sécurité.

hiyabh Skill

Comprehensive pre-launch checklist for shipping a website to production. TRIGGER when the user says 'launch checklist', 'pre-launch', 'ready to publish', 'מוכן להשקה', or asks to prepare a website for production/public launch. Covers infrastructure, auth/security, SEO, analytics, performance, accessibility, legal, content/UX, and a final pre-publish sweep, organized in execution order.

808enzo Bundle

Carry a business account from the first known contact to the buying group's decision. Use when leads go to sales and nobody records whether sales accepted them, when sales says "these leads are junk" and marketing says "sales never calls", when an account sits in a sales stage for months with no recorded next step, when three people at one company get the same email in one week, when a champion answers every message and the deal still dies at the budget holder, or when a lost deal is archived with "no decision" and never comes back. Covers fit and decaying intent on the account, the handoff threshold agreed with sales and acceptance by a promised time, stage ownership, the account cadence, buying roles from your own won deals, next steps with promised times, loss codes with a re-entry date, and the record a won deal hands to retention. Not lead generation, not cold outreach, not the sales conversation itself, not trial activation, not renewal.

808enzo Bundle

Decide where the facts your program runs on actually live, which system owns each one, how fresh the events are, and how to change platform without losing the program. Use when two systems disagree and nobody can say which is right, when you are deciding what to send into a marketing platform and what to leave behind, when a segment stopped filling and nobody changed it, when you need to know how long after an action an event becomes visible to a trigger, or when you are choosing, buying, or moving to a new platform. Covers the register of facts and their owners, field formats, the event plan, freshness classes, event retention, and the order of a migration. Not segment design, not trigger design, not deliverability, and not consent as a lawful basis.

808enzo Bundle

Decide what changes inside a message or on a page from one person to the next, where each value comes from, and what happens when it is missing. Use when a message ships with an empty name in the greeting or a raw template token, when a recommendation block shows the same items to everybody, when a cart reminder arrives describing an empty cart, when a personalized campaign performs like a generic one, when nobody can say how many personalization rules are running or who owns them, when a block recommends what somebody bought last week, or when you need to decide whether a message should go at all once the personal part cannot be built. Covers the four source classes, the moment a value is resolved, format contracts, the three level fallback ladder, the anchor ladder and cold start, algorithm classes and catalog constraints, short fill, the register of live rules and how to switch one off. Not the copy, not the segment, not the display rule, not the discount economics.

808enzo Bundle

Decide who counts as lapsed, catch the ones heading that way before they go, and run one finite attempt to bring back the ones already gone. Use when nobody can say how many days without a purchase makes somebody lapsed, when a win-back message reaches people who bought yesterday in the store, when the lapsed segment only ever grows, when a re-engagement campaign has no end and no outcome, when returns happen but only ever with a discount attached, when customers leave and the team finds out at renewal, or when you need to know whether an attempt to win somebody back is worth making at all. Covers the qualifying action and the threshold derived from your own interval, the two axes of absence, the out of scope classes, retrospective signal building, scoring and validation, the sequence and its escalation, the channel cascade, the declared end and the five outcomes. Not the churn formula, not the tier cadence, not deletion, not discount economics.

808enzo Bundle

Build and run the channels where a carrier or a messaging platform stands between the sender and the person, such as SMS, RCS, WhatsApp and similar messaging apps. Use when deciding which registered number or name a message leaves from, when a template needs approval and a category, when a template gets paused or a number's limit stops a campaign, when an order update and a promotion share one number, when STOP has to work on every system that texts, when a send is billed per segment or per delivered message, or when a cascade has to know what "sent" and "delivered" mean. Covers the origin and its registration, the reply window and the template regime, segment budgets and encoding, cost before the send, statuses and the no-receipt class, and keyword handling. Not the order of channels in a cascade, not the cross-channel cap or quiet hours, not the lawful basis for texting, not the conversation after a reply, not the class of a service message.

808enzo Bundle

Decide who can be reached by push, through which endpoint, and what each send does to the permission the channel depends on. Use when planning how and when to ask for notification permission on iOS, Android or the web, when opt-in looks fine but the channel keeps shrinking, when nobody knows how many people the push base reaches, when notifications get switched off and nobody notices, when one promotion lights up every device a person owns, when an offer arrives after it ended, or when deciding which endpoints a message should go to. Covers the ask budget of each platform, the pre-permission screen, provisional authorization, marketing opt-in apart from display permission, the endpoint registry and token staleness, the fan-out rule, interruption levels, expiry and collapse keys. Not the trigger, not the cross-channel cap or quiet hours, not consent as a lawful basis, not in-app messages.

808enzo Bundle

Control how many messages one person gets across every channel and every sending system, and decide what happens when two messages want the same person at the same time. Use when building a contact policy, setting or deriving a frequency cap, ordering message priority, setting quiet hours, deduplicating the same pitch across channels, working out why unsubscribes rise while each individual campaign looks fine, or auditing total load before adding a channel. Not the construction of one flow, one segment or one channel program, and not consent capture.

808enzo Bundle

Decide on what basis the program may write to a person, in which channel and for what, what the person chose afterward, how far and how fast a withdrawal takes effect, and which uses of their data beyond sending (selection, scoring, inferred attributes) rest on which basis. Use when a base was imported with a "subscribed" flag and no record behind it, when a person unsubscribes and keeps getting texts from another system, when a checkout ticks the marketing box for everyone, when a segment is built on a purchase that reveals a health condition, or when somebody wants to re-permission the whole base by email. Covers the basis record and its proof, confirmed opt in, basis lifetime, the preference center, withdrawal scope and propagation, special categories, and erasure that keeps the suppression entry. Not the capture form, not the merge of records, not the cap, not the envelope, not the class check of a service message, and not legal advice.

808enzo Bundle

Decide which service messages a person gets about something they set in motion (an order, a booking, a payment, an account request), what triggers each one, what it has to contain, how fast and through which channel it has to arrive, what it may carry besides, and how to tell whether the set does its job. Use when people keep asking support where their order is, when a delay notice arrives after the promised date, when a sign-in code arrives after the person gave up, when somebody wants a cross-sell block in the order confirmation, or when service messages are judged on revenue. Covers the service register and status map, the four kinds (access, confirmation, progress, exception), promise timers, the content contract, channels and failover by kind, and testing without withholding required messages. Not the trigger machinery of marketing flows, not the cap, not the sending identity, not the review request, not the order handling process itself.

shahbazaliofficial Bundle

Build a polished, client-facing Meta Ads (Facebook/Instagram) proposal deliverable — a multi-page visual PDF (built as a designed slide deck) covering strategy, audience, budget, timeline, and projected results. Use this whenever the user wants to pitch, propose, or present a Meta/Facebook/Instagram ads plan to a client or prospect — including phrases like "make a proposal for [client]", "pitch deck for meta ads", "client presentation for our ads plan", "proposal for a Facebook ads campaign", or requests to turn a strategy/budget into something presentable, professional, or client-ready. This is a different job from analyzing an existing account's performance (see the meta-ads-account-analysis skill for that) — this skill is for proposing new or planned work, before or instead of running it. Always run the client interview first; never generate a proposal from assumed details.

shahbazaliofficial Bundle

Audit a website's SEO (traditional search), AEO (Answer Engine Optimization — snippets, answer boxes), and GEO (Generative Engine Optimization — visibility/citation in ChatGPT, Perplexity, Google AI Overviews) health, and deliver either a drill-down dashboard artifact or a client-presentable report. Use whenever the user wants a site's search or AI-visibility health reviewed — "audit my site's SEO", "SEO audit", "AEO audit", "GEO audit", "how visible are we in AI search/ChatGPT/Perplexity", "are we being cited by AI", "site audit", "technical SEO review", "on-page SEO check", "is our content optimized for AI search" — or when given a URL for a health check, a crawl export, or an ask to connect an SEO tool. Trigger even for just "SEO" or just "AI search visibility" — cover the relevant pillar(s), asking only if genuinely unclear. Different from meta-ads-account-analysis/google-search-console-analysis (traffic performance) — this is a site health/readiness audit, not a performance report.

shahbazaliofficial Bundle

Search for businesses matching given criteria (search term, industry, category, location), extract their contact details (phone, email, and lightly-sourced executive contacts) from the web, prepare the data for import into Brevo (already connected), and create/send Brevo email campaigns to the collected leads in batches of up to 320. Use this whenever the user wants to build a prospect list for email marketing — "find me [industry] businesses in [location]", "get leads for a Meta Ads campaign", "build an email list for [category]", or "send a campaign to the leads we found". Always confirm search criteria before searching, always ask which email template to use before creating any campaign, and always get explicit confirmation before scheduling/sending a campaign since that sends real email to real people.