agentik-os
- 502 skills
- 0 followers
- 2 repo stars
- last month last updated
- ▌ SEO Content Writer · agentik-osWrites a single, finished SEO-optimized article in one coherent voice from a keyword + topic brief — comprehensive coverage, natural keyword integration, E-E-A-T signals, scannable formatting, title/meta/FAQ package. Use when the user says "write SEO content", "write an SEO article/blog post", "draft optimized content", "écris un article SEO", "rédige du contenu SEO", "article optimisé pour le référencement", or provides keywords/a brief to turn into a published piece. NOT for keyword research, content planning/calendars, meta-tag-only optimization, or snippet hunting (use ag-seo-content-planner / ag-seo-meta-optimizer / ag-seo-snippet-hunter). Use PROACTIVELY for content-writing tasks.
- ▌ SEO Meta Optimizer · agentik-osWrites click-optimized SEO metadata — meta titles, meta descriptions, and URL slugs — within strict character/pixel limits, with keyword placement, power words, and CTAs. Produces 3-5 A/B variations per element plus platform config (Yoast/RankMath, Next.js/Astro). Use PROACTIVELY for new or refreshed pages, blog posts, landing pages, and product pages. Triggers (EN): "meta title", "meta description", "title tag", "SEO metadata", "optimize the slug/URL", "SERP snippet", "improve CTR on search", "Yoast/RankMath". Triggers (FR): "balise title", "meta description", "metadonnees SEO", "optimiser le slug/URL", "extrait Google", "ameliorer le CTR", "titre SEO". NOT for: full SEO audits (use seoaudit), content planning (seo-content-planner), or writing the page body (seo-content-writer).
- ▌ SEO Snippet Hunter · agentik-osFormats content to win featured snippets / position-zero and SERP features (paragraph, list, table, FAQ, PAA) by rewriting question-based content into snippet-eligible blocks with FAQPage/HowTo schema. Use when the user says "seo snippet hunter", "featured snippet", "position zero", "rich snippet", "PAA / People Also Ask", "answer box", "FAQ schema", "snippet optimization", or in FR "snippet vedette", "position zero", "optimiser pour Google snippet", "bloc de reponse", "schema FAQ". Use PROACTIVELY when rewriting question-based or how-to content for search visibility. Not for keyword research or full SEO audits (use the SEO planner / audit skills instead).
- ▌ Stitch Design Taste 2 · agentik-os bundleSemantic Design System skill for Google Stitch — generates an opinionated, agent-friendly DESIGN.md that enforces premium, anti-generic UI standards (strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, hardware-accelerated performance). Use when the user says "/stitch-design-taste", "Stitch design system", "DESIGN.md for Stitch", "design tokens for Google Stitch", "anti-slop UI rules", "système de design Stitch", "génère un DESIGN.md", "règles de design premium pour Stitch", or wants a single curated design-language doc to prompt Stitch screen generation. NOT for auditing an existing UI (use /uiuxaudit) or writing frontend code (use design-taste-frontend).
- ▌ Market Copy · agentik-osWebsite copywriting analysis & generation in one consistent brand voice. Analyzes existing page copy (headlines, subheads, body, CTAs, meta), scores it across clarity/ persuasion/specificity/emotion/action, and writes optimized before/after rewrites + a swipe file. Triggers (EN): "/market copy", "market-copy", "rewrite my copy", "improve website copy", "headline rewrite", "CTA copy", "copy suggestions", "value proposition copy". Triggers (FR): "réécris mon copy", "améliore le texte du site", "réécriture des titres", "optimise les CTA", "suggestions de copy", "proposition de valeur". NOT for: full copy QA/forensic scoring (use /copyaudit), ad creatives (use market-ads), email sequences (use market-emails), or brand voice guidelines (use market-brand).
- ▌
- ▌ Mk Page Cro · agentik-osWhen the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or blog posts. EN triggers "CRO," "conversion rate optimization," "this page isn't converting," "improve conversions," "why isn't this page working," "my landing page sucks," "nobody's converting," "low conversion rate," "bounce rate is too high," "people leave without signing up," "this page needs work," "optimize my landing page." FR triggers "optimise ma page," "améliore les conversions," "ma landing page ne convertit pas," "taux de conversion trop bas," "audit CRO," "pourquoi cette page ne convertit pas," "personne ne s'inscrit," "trop de rebond." Use this even if the user just shares a URL and asks for feedback — they probably want conversion help. For signup/registration flows, see mk-signup-flow-cro. For post-signup activation, see mk-onboarding-cro. For forms outside of signup, see mk-form-cro. For popups/modals, see mk-popup-cro.
- ▌ Mk Paid Ads · agentik-osWhen the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, TikTok, or other ad platforms — campaign strategy, audience targeting, bidding, scaling, and optimization. EN triggers: 'PPC', 'paid media', 'ROAS', 'CPA', 'ad campaign', 'retargeting', 'audience targeting', 'Google Ads', 'Facebook ads', 'Meta ads', 'LinkedIn ads', 'TikTok ads', 'ad budget', 'cost per click', 'CPC', 'CPM', 'ad spend', 'lookalike', 'should I run ads', 'scale my ads', 'optimize my campaigns'. FR triggers: 'pub payante', 'publicité Google/Meta/Facebook/LinkedIn', 'campagne publicitaire', 'budget pub', 'optimiser mes pubs', 'ciblage audience', 'reciblage', 'coût par acquisition', 'devrais-je lancer des pubs'. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see page-cro.
- ▌ Meta Ads Extractor · agentik-osExtract and save ad creative assets (images + videos) from the Meta Ads Library via browser automation, with dimensions, aspect ratios, and CTA destination URLs. Use when user says "/meta_ads_extractor", "extract Meta ads", "download competitor ads", "swipe file", "save Facebook ad creatives", "scrape ad library", or in French "extrais les pubs Meta", "telecharge les pubs concurrentes", "recupere les creatives Facebook", "fais un swipe file". For analyzing extracted ads into a strategy report, see /meta_ads_analyser. For the full extraction + analysis pipeline in one command, see /ads_analyst.
- ▌
- ▌
- ▌ Market Audit · agentik-osMarketing Audit Orchestrator — runs the flagship `/market audit <url>` pipeline: fans out 5 parallel subagents (content, conversion, competitive, technical SEO, strategy), adversarially verifies their scores, and synthesizes a client-ready, revenue-scored MARKETING-AUDIT.md. Use when the user asks to audit / score a website's marketing, run a full marketing audit, grade a landing page or funnel, or wants a marketing report card for a URL. FR triggers: "audit marketing", "audite le marketing de", "analyse marketing complète", "note marketing du site", "audit complet du site". EN triggers: "market audit", "marketing audit", "audit my marketing", "score this site's marketing", "marketing report card", "/market audit". Do NOT trigger for single-angle asks already owned by a sub-skill (use /market copy, /market funnel, /market competitors, /market seo for those); this is the full multi-angle orchestrator.
- ▌ Market Brand · agentik-osBrand Voice Analysis and Guidelines Generation — examines a brand's copy across every channel (homepage, about, product, blog, social, email, ads, microcopy), scores voice on 4 dimensions, maps personality archetype, compares to competitors, audits cross-channel consistency, and produces an evidence-backed BRAND-VOICE.md with Do's/Don'ts and sample copy. Use when the user says "/market brand <url>", "/market brand", "analyze brand voice", "brand voice guidelines", "tone of voice audit", "brand voice consistency", "document our voice", "voice and tone guide", "analyse de la voix de marque", "guide de ton de marque", "charte de voix", "auditer le ton de la marque", "cohérence de la voix de marque". NOT for general marketing strategy, ad campaigns, or copywriting a single asset (use /market-copy, /market-ads, /market-social instead).
- ▌ Mk Popup Cro · agentik-osCreate or optimize popups, modals, overlays, slide-ins, or banners for conversion. EN triggers — "exit intent", "popup conversions", "modal optimization", "lead capture popup", "email popup", "announcement banner", "overlay", "collect emails with a popup", "exit popup", "scroll trigger", "sticky bar", "notification bar". FR triggers — "popup", "fenêtre surgissante", "bandeau d'annonce", "capture d'email", "intention de sortie", "optimiser un popup", "modale de conversion". Use for any overlay or interrupt-style conversion element. For forms outside of popups, see mk-form-cro. For general page conversion, see mk-page-cro.
- ▌ Scriptwriter · agentik-osWrite production-ready video ad scripts with full production notes — scene-by-scene breakdowns with dialogue, B-roll, on-screen text, camera direction, hooks, and timing. Outputs individual script files plus a combined approval overview. Use when user says "/scriptwriter", "write a video script", "video ad script", "reels script", "Meta ad script", "scene-by-scene", "écris un script vidéo", "script de pub vidéo", "script reels", "rédige un script", "storyboard de pub".
- ▌
- ▌
- ▌ Body Energy Protocol Builder · agentik-os bundleUse when a creator, founder, consultant, CAIO client, or solopreneur wants a personal non-medical Body OS (sleep, nutrition, training, energy, recovery, biometrics baseline) — NOT a generic biohacking stack and NOT medical diagnosis/prescription. EN triggers build my Body OS, body protocol, sleep optimization, nutrition protocol, energy map, training plan, recovery system, biometrics baseline, focus optimization, ADHD performance, manage my energy, optimize my sleep, design my body system. FR triggers construis mon Body OS, protocole corps, protocole sommeil, plan nutrition, plan d'entrainement, carte d'energie, systeme de recuperation, baseline biometrique, optimiser mon sommeil, gerer mon energie, optimiser ma concentration. Do NOT trigger for clinical diagnosis, medication dosing, or treatment changes (those escalate to a clinician).
- ▌
- ▌ Mk Marketing Psychology · agentik-osWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also fires on EN: 'psychology', 'mental models', 'cognitive bias', 'persuasion', 'behavioral science', 'why people buy', 'decision-making', 'consumer behavior', 'anchoring', 'social proof', 'scarcity', 'loss aversion', 'framing', 'nudge'; and FR: 'psychologie marketing', 'modèles mentaux', 'biais cognitif', 'persuasion', 'sciences comportementales', 'pourquoi les gens achètent', 'prise de décision', 'comportement du consommateur', 'ancrage', 'preuve sociale', 'rareté', 'aversion à la perte', 'cadrage', 'nudge'. Use whenever someone wants to understand or leverage how people think and decide in a marketing context.
- ▌
- ▌ Art Director Content Engine · agentik-os bundleDirecteur artistique IA pour contenu de marque award-level. Catalogue de 100 types de contenu (carrousels, reels, long-form, pub, packshot produit, mode/éditorial, b-roll, branding, 3D/CGI, avatars IA) avec à quoi sert / pourquoi / impact, specs de génération IA et niveau de difficulté — plus un guide how-to studio par famille (architecture de prompt, lumière, compo, palette) et une carte des modèles image/vidéo (Veo, Kling, Seedance, Hailuo, Nano Banana, Seedream, Flux, Soul, Recraft, Marketing Studio). À utiliser quand on veut choisir un format, briefer une création, écrire un prompt image/vidéo de niveau studio, ou apprendre à un non-créatif à générer proprement. Déclencheurs : "quel format", "type de contenu", "carrousel", "reel", "b-roll", "spot", "packshot", "prompt image/vidéo", "direction artistique", "contenu de marque", "award".
- ▌ Taste And Aesthetic Director · agentik-os bundleUse when a creator, founder, consultant, or CAIO client wants to translate personal taste into a recognizable aesthetic OS — visual codes, cultural references, lifestyle signals, moodboard prompts, signature world that makes them readable in 3 seconds before the logo. Single-voice creative direction (NOT a fan-out audit). Triggers EN "aesthetic identity", "creative direction", "art direction", "moodboard", "visual identity", "personal brand world", "signature aesthetic", "taste profile", "define my aesthetic", "build my visual world", "make my brand recognizable"; FR "ma direction artistique", "mon univers visuel", "construire mon esthetique", "mon identite visuelle", "mon monde de marque", "rendre ma marque reconnaissable", "signature world". Do NOT trigger for logo rendering, generic UI design systems, or one-off image generation.
- ▌
- ▌ Offer And Revenue Architect · agentik-os bundleUse when an operator, CAIO, consultant, fractional executive, agency, or solopreneur has a capability but no clear paid offer, quotes a price range or discounts, or bills hourly for productized work — to extract ONE offer, lock a single defended price, ship a sell sheet, scaffold a pipeline, and model unit economics. EN triggers offer architecture, pricing, productize, productized offer, sell sheet, sales pipeline, unit economics, CAC, LTV, contribution margin, payback, retention, revenue model, "what should I charge", "my offer is not selling", "stop quoting ranges", "package my consulting". FR triggers productiser mon offre, fixer mon prix, arrêter les fourchettes de prix, construire mon pipeline de vente, modèle de revenus, marge, mon offre ne se vend pas, combien facturer. NOT for general copywriting, ad creative, brand identity, or sending traffic to an offer (use audience-growth-engine downstream).
- ▌ Ad Creative 2 · agentik-os bundleGenerate and iterate paid-ad creative at scale — headlines, descriptions, primary text, RSA variants — for any ad platform, iterating on real performance data. Use when the user says "/omg-ad-creative", "/ad-creative", "ad copy", "generate headlines", "ad variations", "creative testing", or "Facebook/Google/LinkedIn ad copy". R-MARKETING: paid creative; reference docs document optional user-invoked third-party generation APIs (user keys only).
- ▌
- ▌ Gsap · agentik-os bundleGSAP animation reference + craft for HyperFrames compositions. Covers gsap.to()/from()/fromTo()/set(), easing, stagger, defaults, transform aliases (x/y/scale/rotation/autoAlpha), function-based values, matchMedia (responsive + reduced-motion), timelines (gsap.timeline(), position parameter "<"/">"/labels, nesting, playback control), and compositor-safe performance (transforms, will-change, quickTo). Use when writing, sequencing, debugging, or optimizing GSAP animations/tweens/timelines in HyperFrames — EN ("animate this with GSAP", "GSAP timeline", "stagger animation", "ease/easing", "scroll/entrance animation", "make it smooth", "fix janky animation") and FR ("anime avec GSAP", "timeline GSAP", "animation au scroll/d'entrée", "easing/courbe", "rends-le fluide", "corrige l'animation saccadée", "séquence d'animation").
- ▌ Ads Copy · agentik-osWrites 10+ platform-ready ad copy variations (Google, Meta, LinkedIn, TikTok, YouTube, Pinterest) with A/B pairs, exact character-count compliance, and four direct-response frameworks (PAS, AIDA, BAB, 4Ps). Use when the user says "/ads copy", "write ad copy", "generate ads", "ad variations", "Google/Meta/LinkedIn/TikTok ad text", or in French "écris des annonces", "rédige des pubs", "copy publicitaire", "textes d'annonces", "variantes d'annonces". Also runs as a subagent of /ads strategy.
- ▌ Sculp · agentik-osSenior UX/UI design agent that produces a structured, reference-grounded UX narrative — emotional journey, section-by-section structure, and named real-world references — clear enough for a developer or designer to build from without a mockup. Desktop-first, emotion before aesthetics, no generic patterns. Trigger on "/sculp", "design the UX", "UX narrative", "structure this page/landing/product page", "section-by-section design", "emotional journey", "how should this experience feel", "give me a design direction grounded in real references", "sculpte l'UX", "structure cette page", "parcours émotionnel", "direction design", "comment doit se sentir l'utilisateur". Use after /mono and /lense have clarified and validated the idea. NOT an audit (use /uiuxaudit) and NOT a visual/brand system (use /brand-identity or /deepux).
- ▌ Graphify · agentik-os bundleTurn any input (code, docs, papers, images, videos) into a navigable knowledge graph, then answer questions against it. Use when the user wants to build/map/index a codebase or corpus, OR asks any natural-language question about a codebase, documents, or project content ("how does X work", "what calls Y", "trace the data flow", "map this repo", "comment fonctionne X", "construis un graphe", "indexe ce projet", "qu'est-ce qui appelle Y") - especially if graphify-out/ exists, treat the question as a /graphify query rather than reading files by hand. Triggers on /graphify and on codebase/corpus questions when a graph is present or wanted.
- ▌ Lense · agentik-osResearch scout for an already-refined idea — finds 2-3 high-quality external references (design precedents or knowledge sources) and shows how each both supports AND challenges the idea. Activate when the user types /lense, or asks to find references / precedents / prior art / evidence / examples / sources / "qui a déjà fait ça" / "des références" / "des précédents" / "trouve des preuves" / "validate this idea against reality" for an idea that is already clear enough to act on. Use AFTER /mono has clarified the idea — not for brainstorming or clarifying a vague idea (that's /mono), and not for next-step recommendations (handled elsewhere).
- ▌ Ads Hooks · agentik-osGenerates 20+ scroll-stopping ad hooks in one consistent persuasive voice, organized by psychological angle (pain, curiosity, social proof, contrarian, urgency) with platform-specific formatting, A/B variations, and psychology breakdowns. Use when the user says "/ads hooks", "ad hooks", "scroll-stopping hooks", "hook generator", "opening lines", "attention grabbers", "improve CTR", "viral hooks", or in French "des hooks", "accroches publicitaires", "phrases d'accroche", "génère des hooks", "accroches qui stoppent le scroll", "améliore le CTR". Also runs as a subagent of /ads strategy.
- ▌ Ads Quick · agentik-os60-second single-pass ad readiness snapshot of a website/business — scores 5 dimensions (value prop, offer, CTA, landing page, trust) and recommends a platform + starting budget, with NO subagents. EN triggers "ads quick", "am I ready for ads", "should I run ads", "quick ad gut-check", "ad readiness snapshot". FR triggers "suis-je prêt pour les pubs", "check rapide pubs", "snapshot pub", "dois-je lancer des pubs". Use for a fast gut-check; for the full multi-agent strategy use /ads strategy, to analyze existing ad data use /ads audit.
- ▌
- ▌
- ▌ Growth Engine 2 · agentik-os bundleGrowth Engine — a bounded, gated X growth system for @Agentik_os aimed at real follower growth (north star 10k) by being genuinely useful in the right conversations, never by spam automation. A daily Reply Radar finds high-leverage AI-agents/Claude threads via last30days/ScrapeCreators, drafts genuine on-voice replies, passes them through an adversarial anti-spam gate, then (only when ARMED with a valid X session) posts a LOW-CAPPED number of replies + likes via Playwright driving the operator's logged-in session, with human pacing, dedup, and a kill-switch. Use when the user says '/omg-growth-engine', '/growth-engine', 'growth X', 'gagner des followers', 'reply radar', 'engager sur X', 'arm/disarm the growth engine'. NOT a mass like/follow/DM bot (that gets the account suspended and is refused), NOT the content publisher (that is agent-ecosystem-watch): this is the engagement layer, deliberately small-volume and quality-gated.
- ▌ Linear 2 · agentik-os bundleLinear feedback resolution pipeline. Auto-detects intent (fix feedbacks by default), loads the 10-step protocol with DYNAMIC audit chain (audit-selector.py picks 4-12 relevant audits per ticket, scoped to the ticket only), dispatches sequential work sessions, Oracle quality gate. Use when user says "/linear", "linear", "fix linear", "resolve feedback", "regler les feedbacks".
- ▌ Theme Factory · agentik-os bundleToolkit for styling artifacts (slide decks, docs, reports, HTML landing pages, dashboards) with a cohesive color + font theme. Pick one of 10 curated pre-set themes or generate a custom theme on-the-fly, then apply it consistently across the artifact. Use when the user says "/theme-factory", "apply a theme", "style this deck/doc/page", "pick a color palette", "font pairing", "make it look professional/branded", "themer ce deck", "applique un theme", "choisis une palette", "harmonise les couleurs et polices", "donne-lui un style coherent".
- ▌ UI UX Pro Max 2 · agentik-os bundleUI/UX design intelligence for web and mobile — produces design-system decisions and production UI code in ONE coherent designer voice. Use when the task changes how a feature looks, feels, moves, or is interacted with. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions (EN): plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX. Actions (FR): conçois, construis l'UI, crée une interface, design, refonte composant, améliore l'UX, corrige le design, palette de couleurs, choix de police, accessibilité, mode sombre, design système. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid
- ▌ Market Ads · agentik-osAd Creative & Campaign Generation engine for `/market ads <url>`. Builds production-ready paid-ad campaigns across Google, Meta, LinkedIn, TikTok and Twitter/X — full copy variations, audience targeting, retargeting funnels, budget allocation, ROAS/CPA benchmarks, A/B test plans and designer briefs, all written to AD-CAMPAIGNS.md. Triggers on (EN): "market-ads", "/market ads", "generate ads", "ad campaign", "ad copy", "paid ads", "Google/Meta/LinkedIn/ TikTok ads", "create ad creatives", "media buyer handoff". Triggers on (FR): "génère des pubs", "campagne publicitaire", "créatives publicitaires", "annonces payantes", "pub Google/Meta/LinkedIn/TikTok", "copies d'annonce". NOT for organic social calendars (use market-social), landing pages (market-landing) or email (market-emails).
- ▌ Market SEO · agentik-os bundleForensic SEO content audit of a URL or site — on-page (title/meta/headings/images/internal links/URL), content quality (E-E-A-T), keyword + search-intent fit, technical SEO (robots/sitemap/canonical/CWV), content-gap analysis, featured-snippet + schema opportunities, and a prioritized strategy roadmap. Produces SEO-AUDIT.md with a /100 health score. Use when the user gives a URL and asks to audit/improve SEO, organic rankings, or search visibility — EN: "seo audit", "audit this page's seo", "why am I not ranking", "improve organic traffic", "on-page seo check", "content gap analysis"; FR: "audit seo", "audite le seo de cette page", "pourquoi je ne ranke pas", "améliorer mon référencement", "trafic organique", "analyse de contenu seo". Also triggers on: market-seo, /market seo <url>. NOT for ad copy, social posts, or generic marketing strategy (use market-ads / market-social / market). For deep technical-only SEO use /seoaudit.
- ▌ Meta Ads Analyser · agentik-osAnalyze extracted Meta ad creatives and generate a professional competitive strategy report with inline videos/images grouped by funnel and landing page. Use when user says "/meta_ads_analyser", "analyze ads", "analyse les pubs", "rapport de stratégie pub", "ad strategy report", "review competitor creatives", "analyse créatives concurrentes", or "audit pub Meta". Run /meta_ads_extractor first to extract assets. For the full extraction + analysis pipeline in one command, see /ads_analyst.
- ▌ Agent Ecosystem Watch 2 · agentik-os bundleAgent-Ecosystem Watch — a daily autonomous intelligence pass over the Claude and AI-agent ecosystem on X. Reads a topic watchlist via last30days/ScrapeCreators, extracts CONCRETE improvements that make Claude / Claude Code / OmegaOS better (new features, prompting techniques, MCP servers, subagent/orchestration tricks, hooks, eval methods, model updates), scores each for integratability into OmegaOS, writes an HTML report + Telegram alert for the operator to decide, and (only when ARMED, behind an adversarial quality gate + daily cap + dedup) auto-publishes vetted best-practice tweets to @Agentik_os via omega-zernio. Use when the user says '/omg-ecosystem-watch', '/ecosystem-watch', 'veille Claude', 'veille agents IA', 'watch the Claude ecosystem', 'run the ecosystem watch', or wants to inspect/arm/disarm the daily watch. NOT a live web research primitive for one question (that is last30days / deep-research) and NOT a general social scheduler (that is the marketing suite): this is the standing daily radar tha
- ▌
- ▌ Mk Site Architecture · agentik-osWhen the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user mentions "sitemap," "site map," "visual sitemap," "site structure," "page hierarchy," "information architecture," "IA," "navigation design," "URL structure," "breadcrumbs," "internal linking strategy," "website planning," "what pages do I need," "how should I organize my site," "site navigation" — or in French "plan du site," "arborescence," "structure du site," "hiérarchie des pages," "architecture de l'information," "navigation," "structure des URL," "fil d'Ariane," "maillage interne," "quelles pages me faut-il," "comment organiser mon site." Use this whenever someone is planning what pages a website should have and how they connect. NOT for XML sitemaps (that's technical SEO — see seo-audit). For SEO audits, see seo-audit. For structured data, see schema-markup.
- ▌
- ▌ Freedom Lifestyle Designer · agentik-os bundleUse when a creator, founder, consultant, CAIO client, or solopreneur wants a mature freedom-lifestyle architecture (bases, seasons, quests, cost ratios, experiments) — not a nomad fantasy. EN triggers design my freedom lifestyle, where should I live, digital nomad strategy, seasonal living, city fit, cost of freedom, anti-sedentary life, freedom ratio, base vs seasonal vs quest, slow travel architecture, location strategy for my business. FR triggers concevoir ma vie libre, rythme saisonnier, où devrais-je vivre, stratégie nomade, ratio de liberté, coût de la liberté, vie nomade mature, choisir ma ville de base, design de vie. Do NOT trigger for one-off trip planning, tourist itineraries, or visa/tax legal advice (point to official sources instead).
- ▌ Mk Analytics Tracking · agentik-osWhen the user wants to set up, improve, or audit analytics tracking and measurement. Fires on EN "set up tracking", "GA4", "Google Analytics", "conversion tracking", "event tracking", "UTM parameters", "tag manager", "GTM", "analytics implementation", "tracking plan", "how do I measure this", "track conversions", "attribution", "Mixpanel", "Segment", "are my events firing", "analytics isn't working"; and FR "mettre en place le tracking", "suivi analytics", "suivi des conversions", "plan de tracking", "comment mesurer ça", "mes events se déclenchent-ils", "le tracking ne marche pas", "attribution", "balises GTM". Use whenever someone asks how to know if something is working or wants to measure marketing results. For A/B test measurement, see mk-ab-test-setup.
- ▌
- ▌
- ▌
- ▌ Redesign Existing Projects · agentik-osUpgrades an existing website or app to premium quality — audits the current design, finds generic "AI-looking" patterns, and applies high-end standards without breaking functionality. Works with any CSS framework or vanilla CSS. Use when the user says "redesign this", "refonte", "améliore le design", "make this look premium / less generic / less AI", "upgrade the UI of my existing project", "de-AI-ify the design", "polish the design", "rends ça moins générique". Not for net-new design from scratch (use a fresh design skill) and not a pure forensic UI score (use /uiuxaudit).
- ▌ Imagegen Frontend Mobile · agentik-osElite mobile-app image-generation art director for premium, app-native screen concepts and multi-screen flows on iOS, Android, and cross-platform. Generates images only — never code (no SwiftUI / React Native / Flutter / HTML). Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone-mockup framing (subtle premium iPhone/Android frame by default, content stays the hero). Use when the user asks (FR or EN) for a mobile app screen concept, app mockup, onboarding/auth/home/profile/settings/chat/ecommerce/fintech/health/productivity/social flow, "design une app mobile", "écran d'app", "maquette mobile", "flow onboarding", "app concept", "mobile app screens", "premium mobile redesign", "phone mockup". NOT for websites, landing pages, desktop dashboards, image-to-code, or frontend implementation (route those to imagegen-frontend-web / image-
- ▌ Stax 2 · agentik-os bundleConvert ANY project fully to Stax — the panels-inside-panels dashboard grammar (Miller columns, evolved): one mechanic (open-right), one action zone (the footer), one way back (close / breadcrumb). No pages, no modals, no tabs — the whole UI derives from a single serializable panel-workspace state (URL-synced, pinnable references, per-type sizing). Use when the user says "/stax", "/omg-stax", "convert to stax", "panelize this app", "make this a panel stack", "stax layout", "miller columns", "panels inside panels", "dashboard vision structure", or in French "convertis en stax", "passe en panneaux", "structure de dashboard". This is the OmegaOS dashboard vision structure — tracks github.com/agentik-os/stax main.
- ▌ Ads · agentik-osAI ads strategist + campaign generation orchestrator. Builds complete advertising strategies, platform-specific ad copy, audience personas, competitive intel, funnel architecture, budget allocation, A/B test plans, and client-ready PDF reports. Fans out to 5 parallel specialist agents for the flagship strategy audit. Use when the user says "/ads", "ads strategy", "ad campaign", "ad copy", "audience personas", "ad budget", "ad funnel", "competitor ads", "PPC", "Meta/Google/TikTok/LinkedIn ads", or in French "stratégie pub", "campagne publicitaire", "copy de pub", "audit pub", "budget pub", "personas pub", "tunnel de pub".
- ▌ Cleanup 2 · agentik-os bundleNettoyage intelligent du VPS/projets — analyse disque, fermeture des sessions de travail détachées (protège la connexion + l'infra), purge sûre (cache Docker/APT/journal, résidu /tmp, caches Bun/npm/go), purge des artefacts de build rebuildables (target/ Rust, node_modules, .next) avec garde-fou anti-session-active, et audit de cohérence de la documentation des projets.
- ▌ E2e · agentik-os bundleForensic end-to-end test of an entire Next.js + Clerk + Convex SaaS application. Inventories all dashboard pages, maps each to its feature spec (docs/FEATURES/F-XXX-*.md), runs Playwright tests with authenticated Clerk sessions (sign-in-token + ticket strategy), captures screenshots per workflow step, identifies placeholder pages (DeferredFeatureShell detection), optionally dispatches dev workers to ship MVP UI for placeholders, re-tests, and produces a comprehensive markdown report with verdicts per page + workflow. Re-invocable: each call relaunches the full pipeline (recon -> tests -> dev -> re-test -> report). Use ONLY for whole-app validation, never a single page/endpoint (route those to /debugaudit, /uiuxaudit, /apiaudit). Use when user says "/e2e", "fais un test complet de l'application", "teste toute l'app", "big test avant lancement", "test toute l'application", "final pre-launch test", "test complet", "full app test", "valide que tout marche", "validate everything works", "pre-launch QA", "QA avant
- ▌ Monitor 2 · agentik-osPoint a monitor at a running rmux session (on this box or on any ssh host) and get an ANSWER instead of a screen. A cheap 60s watcher classifies the session as QUESTION, STALLED, BLOCKED or WORKING and answers each one differently: a question goes to a human because it needs judgement, a stall gets a mechanical nudge, a block is NEVER nudged because that is manufactured thrash, and working stays silent. A deep audit team of parallel read-only sub-agents runs on a slower cadence, with dimensions derived from the WATCHED project's own rules. Use when the user says "/monitor", "/omg-monitor", "monitor this session", "watch this build", "keep an eye on the oracle", "babysit that session", "is it stuck", "did it stall", "why did it stop", "audit that session continuously", or in French "surveille cette session", "surveille ce build", "garde un oeil sur l'oracle", "est-ce qu'il est bloque", "il s'est arrete", "pourquoi il ne bouge plus", "audite la session en continu". NOT for MIRRORING a session so a human can rea
- ▌ Omg Audits · agentik-os bundleComplete Quality Arsenal in one installable skill — 18 forensic Gestalt-Popper audits (code, security, performance, UX, accessibility, SEO, data, API, copy, DX, motion, flow, feature, automation, logic, retention, debug, refonte) plus intelligent orchestration, power levels, parallel waves, output templates, and a verification contract. Use when the user says "/omg-audits", "audit my project", "full audit", "quality audit", "audit complet", "is it production ready", "security audit", "performance audit", "design audit", "make it bulletproof", or names any single audit (codeaudit, secaudit, perfaudit, uiuxaudit, etc.). Self-contained: every audit protocol, orchestration doc, and template ships inside this skill.
- ▌ Stepper Os 2 · agentik-osDrive a project through Stepper OS (AgentikOS suite) - the execution operating system around coding agents. Compiles a Blueprint into a dependency-aware graph of modules/epics/slices/steps, then executes it step by step through the `omega-stepper` CLI: plan -> start -> implement -> verify -> done, where DONE is gated by a deterministic verifier (never self-report). Use when the user says "/stepper-os", "/omg-stepper-os", "stepper", "execute the blueprint", "run the steps", "next step", "step plan", or in French "execute le blueprint", "etape par etape", "prochaine etape", "lance le stepper". NOT for designing the blueprint itself (that is /blueprint-os or /omg-blueprint-os) and NOT a generic todo list (that is the harness task tool).
- ▌ Builder Os 2 · agentik-os bundleExecute software projects from an approved Blueprint {OS} handoff and a BUILD READY Stepper {OS} graph into tested, reviewed, integrated, documented, release-ready code. Use for `/build`, Builder {OS}, Build {OS}, autonomous implementation, following a Stepper roadmap, resuming an interrupted build, repairing failed steps, auditing implementation evidence, reporting build status, or producing the final engineering and operations handoff. Consume rather than redefine Blueprint and Stepper; preserve repository work; require real verification and never claim fake completion.
- ▌ Journal Os 2 · agentik-os bundleRun MIRROR, a nightly daily-journal agent that reconstructs the day truthfully and turns it into evidence, spanning a one-question-at-a-time voice-first interview in French or English, strict separation of fact from emotion from interpretation from lesson, contradiction detection between declared intention and observed behavior (pattern-based, never from a single day), identity evidence in behavioral language, memory extraction, unfinished loops, a Tomorrow Protocol capped at three missions with success conditions, an identity challenge, a content handoff that exposes raw material without ever writing posts, and a reflection layer drawn from Stoicism, Jim Rohn and Taoism applied at most once per entry and always bound to that day's evidence. Use for the daily journal, evening review, day debrief, telling the agent about your day, weekly rollups, working out where the time actually went, checking whether behavior matches stated priorities, and capturing what happened before it is forgotten. Life first and cont
- ▌ Mindset Os 2 · agentik-os bundleBuild and operate a comprehensive personal transformation system spanning identity, personal philosophy, Jim Rohn's philosophy-attitude-activity-results-lifestyle framework, purpose, values, written goals, self-education, journaling, discipline, mental and emotional fitness, spirituality and prayer, evidence-aware manifestation, meditation, breathwork, sleep, nutrition, training, recovery, habits, focus, wealth behavior, marketplace value, relationships and associations, life seasons, environment, routines, reviews, and relapse recovery. Use for mindset coaching, life audits, identity redesign, Jim Rohn plans, millionaire or founder mindset, purpose or why work, philosophy compilation, goal systems, 30/90-day transformations, daily or weekly protocols, limiting-belief work, visualization, wellbeing routines, accountability, personal scorecards, and personal operating-system requests.
- ▌ AI Logic Os 3 · agentik-os bundleAudit, diagnosis and design agent for optimizing workflows and challenging agentic systems with automation and AI, with a default bias of NO. Use it to evaluate an existing process, decide what to automate, arbitrate between deterministic code and AI judgment, spec an automation before building, and to challenge an agentic system (OmegaOS itself, an agent, a skill, an LLM pipeline, a coding tool, an AI use case). It finds where a model does the job of a simple rule, where an unverifiable output has a consequence, where an irreversible action lacks a human gate, where the feedback loop is missing, and what primitive is absent and should exist. Enforces about 80 percent deterministic code and 20 percent AI judgment, no baseline no optimization, a human gate on irreversible actions, and a verifiable output for anything with a consequence. Ends in an argued decision plus an executable spec, never a list of ideas. Use for /ai-logic, /ailogic, AI Logic OS, workflow audit, automation triage, code-vs-AI arbitration,
- ▌ Design Os 2 · agentik-os bundleCompile an approved product Blueprint into a challenged, coherent, modern UX/UI definition and a machine-readable Design Handoff for Stepper. Use after Blueprint OS and before roadmap, implementation, or Builder work for apps, SaaS, mobile products, dashboards, AI/chat products, internal tools, marketplaces, websites with application flows, redesigns, and design-system migrations. Trigger for Design OS, UX architecture, user-flow challenge, information architecture, screen contracts, interaction design, shadcn/ui or STAX mapping, visual system definition, responsive/accessibility states, prototype specification, or pre-Stepper design validation.
- ▌ Alignment Os 3 · agentik-os bundleA personal wisdom, decision and inner-alignment operating system — a rigorous, compassionate, action-oriented second brain for questions about life, decisions, identity, work, relationships, money, purpose, fear, discipline, ambition and meaning. It does not tell you what to believe; it helps you see reality clearly, separate control from non-control, reconnect decisions to chosen values, widen perspective without magical thinking, choose the right level of effort, turn insight into a concrete next action, and learn from the result. Synthesizes Stoicism, Daoism (wu-wei), Jim Rohn, grounded manifestation and accurate quantum guardrails, routing across a council of specialist voices. Use for /coach, /align, Alignment Coach OS, a decision, a belief audit, a morning/evening protocol, a reset, true-north work, virtue check, dichotomy-of-control, reframing, shadow work, fear work, meaning, or personal-philosophy work. NOT the software Blueprint/Stepper/Builder pipeline.
- ▌ Execution Os 2 · agentik-os bundleOperate an LLM-first personal execution system that converts ambitions, goals, obligations, and ideas into focused commitments, protected work, shipped evidence, reviews, and adaptive recovery. Use when the user asks for Execution OS, /execute, a daily or weekly execution plan, outcome planning, prioritization, accountability, deep-focus support, anti-procrastination or anti-ADHD rescue, a reset after falling behind, progress review, personal operating cadence, or help finishing what they start. This is a personal success and delivery OS adjacent to Mindset OS and Habit Tracker OS; it is not the Blueprint/Stepper/Builder software-development pipeline.
- ▌ Intuitive Os 2 · agentik-os bundleTrain, test and calibrate intuition as a measurable skill, spanning raw intuition capture before analytical contamination, five-layer separation (observation, interpretation, affect, intuition, decision), intuition provenance (expert pattern, weak signal, emotion, incentive signal, bias, noise), falsifiable probabilistic forecasting with resolution criteria, base rates and Bayesian updating, decision journaling and premortems, red-teaming a hunch, Brier scoring and calibration buckets by domain, pattern-card and mental-model libraries, and a 90-day observe/calibrate/compress curriculum. Use for gut-feel checks, should-I-trust-this-instinct questions, forecasting and prediction logging, decision protocols and reviews, separating decision quality from outcome quality, spotting bias in your own judgment, weak-signal analysis, overconfidence and calibration audits, and intuition training plans. Trigger words: intuition, gut feeling, instinct, hunch, calibration, forecast, prediction, Brier, base rate, decision jo
- ▌ Seductive Os 2 · agentik-os bundleBuild personal magnetism as a real capability, spanning presence and embodiment, conversational craft, warmth, humour, curiosity, attraction fundamentals, social calibration, reading and respecting another person's actual interest, flirtation and consent-gated escalation, dating strategy, apps and texting, style and self-presentation, rejection resilience, approach anxiety, long-term desire, and the inner game underneath all of it (self-worth, outcome dependence, authenticity). Consent-first and script-free: it builds a more attractive person, it never teaches manipulation, pressure, deception or routines that treat a person as a target. Use for charisma coaching, presence work, conversation practice, dating and romantic confidence, social calibration, style audits, app profile and texting review, post-rejection recovery, approach-anxiety ladders, keeping desire alive in a long relationship, and personal magnetism audits. Trigger words: seduction, charisma, magnetism, presence, flirting, dating, attraction, c
- ▌ Brainstorm Os 3 · agentik-os bundleRun a rigorous multi-agent imagination, evolution, and decision council with independent chambers, Founder DNA, frame fission, idea genomes, collisions, counterfactual worlds, structural mutation, incubation, adaptive specialists, adversarial debate, evidence routing, quality gates, concept lineage, experiments, and handoffs. Use for /brainstorm, Brainstorm {OS}, ideation, challenging or evolving an idea, wilder non-obvious directions, agent councils, blind spots, red teams, premortems, evidence return, debate audits, or convergence. Also use to choose mobile, web, desktop, multi-surface, chat, API, ambient, physical, service, or no-interface embodiment, and to prepare ideas for Market Research {OS}, Blueprint {OS}, decisions, experiments, or creative/project briefs. Preserve project boundaries and prior decisions, separate evidence from hypotheses, require genuine dissent, and maintain lineage across “challenge”, “continue”, “evolve”, and “go deeper”.
- ▌ Storyteller Os 2 · agentik-os bundleCoach, mine, verify, shape, write, perform, adapt, score, and preserve truthful stories without erasing the user's voice. Use for personal stories, founder narratives, brand and customer stories, lessons, keynotes, pitches, reels, carousels, threads, podcasts, YouTube scripts, case studies, data stories, story banks, story interviews, narrative strategy, or requests such as “help me find my story,” “coach me, don't write for me,” “turn this moment into content,” “make this story deeper,” and commands beginning with /story, /mine, /interview, /deepen, /shape, /write, /adapt, /truthcheck, /score, /rehearse, or /storybank.
- ▌ Habit Tracker Os 3 · agentik-os bundleOperate a conversation-first, LLM-assisted habit system for creating good habits, reducing unwanted habits, running daily check-ins, handling urges and lapses, producing adaptive reviews and visual progress reports, and integrating habits with Mindset {OS}, Life {OS}, or Omega {OS}. Use for habit setup, routine design, accountability, morning/evening check-ins, “I did it/I missed/I’m tempted” messages, weekly or monthly reviews, recovery seasons, behavior experiments, habit analytics, and durable tracking from natural-language conversations.
- ▌ Identity Shift Os 2 · agentik-os bundleTurn a declared future identity into daily evidence, spanning the identity contract, a 180-day transformation protocol, daily journaling and the Mirror pass, gap analysis against what you actually did, contradiction detection across declared priority versus time spent, the Tomorrow Protocol capped at three objectives, proportional challenges, an evidence ledger, weekly review and monthly recalibration, plus a content-worthiness filter and anti-cringe pass before anything is published. Use for identity and transformation work, daily or weekly reviews, journaling and reflection, spotting the gap between what you say matters and how you spend your time, designing tomorrow, building or rebuilding discipline, 180-day plans, evidence tracking, and deciding whether a personal event is worth posting. Life first, content second: it never shames, never optimizes a metric at the expense of the whole person, and routes medically sensitive goals to safe framing and professional evaluation. Trigger words: identity, transfo
- ▌ Fitts Law 2 · agentik-osApply Fitts's Law to size and position interactive targets for fast, accurate interaction.
- ▌ Hicks Law 2 · agentik-osApply Hick's Law to reduce decision time by limiting the number of simultaneous choices presented to users.
- ▌ Search UX 2 · agentik-osDesign search experiences that help users find what they need, recover from failure, and refine results.
- ▌ Case Study 2 · agentik-osCraft portfolio-ready case studies that tell the story of a design project.
- ▌ UX Writing 2 · agentik-osWrite effective UI copy including microcopy, error messages, empty states, and CTAs.
- ▌ Empathy Map 2 · agentik-osBuild a 4-quadrant empathy map (Says, Thinks, Does, Feels) to synthesize user research into actionable insights. Use when you need to quickly capture and share user understanding across the team.
- ▌ Form Design 2 · agentik-osDesign forms that minimize friction, prevent errors, and guide users to successful completion.
- ▌ Icon System 2 · agentik-osCreate an icon system specification covering grid, sizing, naming, categories, and implementation guidance.
- ▌ Journey Map 2 · agentik-osCreate an end-to-end user journey map with stages, touchpoints, emotions, pain points, and opportunity areas. Use when mapping the full user experience for a product, feature, or service.
- ▌ Layout Grid 2 · agentik-osDefine responsive layout grid systems with columns, gutters, margins, and breakpoint behavior.
- ▌ Millers Law 2 · agentik-osApply Miller's Law — chunk information into groups of ~4 to work within working memory limits.
- ▌ Color System 2 · agentik-osBuild a comprehensive color system with palette generation, semantic mapping, and accessibility compliance.
- ▌ Design Brief 2 · agentik-osWrite a comprehensive design brief that defines the problem space, constraints, audience, and success criteria.
- ▌ Handoff Spec 2 · agentik-osCreate developer handoff specifications with measurements, behaviors, assets, and edge cases.
- ▌ User Persona 2 · agentik-osCreate refined user personas from research data with demographics, goals, frustrations, and behavioral patterns. Use when synthesizing user research into actionable persona profiles for design decisions.
- ▌ Market Research Os 2 · agentik-os bundleCompile a business, product, service, AI, marketplace, consumer, B2B, local, hardware, media, luxury, or regulated-market idea into a decision-grade market research and validation pack before Blueprint or implementation. Use when the user invokes /market-research, says Market Research {OS}, asks to validate or challenge an idea, study a market, size TAM/SAM/SOM, analyze competitors, mine customer pain or social/review signals, test feature or pricing demand, conduct commercial due diligence, plan ethical scraping, compare opportunities, audit an existing market study, or create a Blueprint input manifest. Recover prior decisions, distinguish evidence from inference, use current sources, quantify uncertainty, design primary research and real-behavior experiments, and never declare an idea validated from desk research alone.
- ▌
- ▌ State Machine 2 · agentik-osModel complex UI behavior as finite state machines with states, events, and transitions.
- ▌ Survey Design 2 · agentik-osDesign surveys that collect reliable, unbiased quantitative data to validate hypotheses and measure user attitudes at scale.
- ▌ Team Workflow 2 · agentik-osDesign team workflows covering task management, collaboration rituals, and tooling.
- ▌ Test Scenario 2 · agentik-osGenerates structured usability test scenarios with realistic tasks, success criteria, and facilitation notes — ready to run with real participants or in a moderated session.
- ▌ Component Spec 2 · agentik-osWrite a detailed component specification including props, states, variants, accessibility requirements, and usage guidelines.
- ▌ Critique Color 2 · agentik-osCritique a screen's colour usage — contrast ratios, palette coherence, semantic meaning, and colour accessibility.
- ▌ Experience Map 2 · agentik-osCreate a holistic experience map showing the full ecosystem of user touchpoints, channels, and relationships.
- ▌
- ▌ Spacing System 2 · agentik-osCreate a consistent spacing system based on a base unit with contextual application rules.