all publishers

agentik-os

@agentik-os source repo

502 published skills · page 5 of 6

  1. ▌
    Debugaudit · agentik-os
    Forensic runtime bug hunter v1 (Gestalt-Popper). 23-phase deep analysis of everything that is BROKEN RIGHT NOW: console errors, network failures, visual regressions, security injections, responsive breakage, performance bottlenecks, dead features, race conditions, state corruption, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Replaces /hunt + /maniac as the single forensic-grade runtime bug hunting pipeline. Score /360. Preamble v1.0 compliant. Audit → Plan → Fix → Re-audit. Use when user says "/debugaudit", "find bugs", "what's broken", "hunt bugs", "debug everything", "hunt", "maniac", "find all bugs".
    2 repo stars
  2. ▌
    Logicaudit · agentik-os
    Forensic systems logic audit v1 (Gestalt-Popper). 20-phase deep analysis by a systems architect genius: redundant logic, suboptimal algorithms, wasted computation, architectural bottlenecks, unnecessary complexity, missed abstractions, pipeline inefficiencies, orchestration waste, data flow entropy, configuration drift, dead paths, over-engineering, under-engineering, state machine defects, retry/fallback anti-patterns, caching opportunities, parallelization gaps, single-threaded bottlenecks, plus verdict, fix plan, fix execution, re-audit. Score /360. Preamble v1.0 compliant. Think like Einstein — simplify everything, optimize everything. Use when user says "/logicaudit", "optimize logic", "audit logic", "system optimization", "architecture optimization", "improve system design", "make it smarter", "optimize everything".
    2 repo stars
  3. ▌
    Identity Shift Os · agentik-os bundle
    Turn 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
    2 repo stars
  4. ▌
    Motionaudit · agentik-os
    Forensic motion design audit v1 (Gestalt-Popper). 23-phase deep analysis of everything that MOVES on the site: CSS transitions, JS animations, WebGL effects, scroll-driven choreography, P5.js/canvas, page transitions, micro-interactions, loading sequences, easing systems, duration consistency, choreography composition, reduced-motion compliance, mobile motion, brand motion DNA, performance budget, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Score /360. Preamble v1.0 compliant. ABORTS on non-UI projects (CLI, library, backend-only, headless). Audit -> Plan -> Fix -> Re-audit. Use when user says "/motionaudit", "motion audit", "animation audit", "why does it feel lifeless", "motion review", "animation quality", "easing audit", "scroll animation check", "does the motion make sense", "audit the animations".
    2 repo stars
  5. ▌
    Refontaudit · agentik-os
    Senior Dashboard REFONTE engine v2. Three modes: EVOLUTION (default — surgical improvement), REVOLUTION (ground-up when unsalvageable), VERIFY (post-impl measurement 2-4 weeks later). 25-phase pipeline ALWAYS, scored /540, driven by real user data + user stories. Keep Audit classifies KEEP/IMPROVE/RETHINK/KILL. Component Forge writes real shadcn code. Reference patterns from shadcn official blocks/components (Context7 MCP) + product design knowledge. Confidence score per proposal. shadcn/ui + Tailwind v4 foundation. Use when user says "/refontaudit", "/refonte", "refonte", "refund audit", "redesign dashboard", "repenser dashboard", "comme Linear", "comme Vercel", "comme ElevenLabs", "dashboard pro", "dashboard senior", "vérifie la refonte", "verify refonte".
    2 repo stars
  6. ▌
    Design Taste Frontend · agentik-os
    Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
    2 repo stars
  7. ▌
    Higgsfield Soul Id · agentik-os bundle
    Train a face-faithful Soul Character on a person's photos for identity-consistent image and video generation — the visual-identity anchor reused across all Soul-powered output. Use when the user says "/omg-higgsfield-soul-id", "/higgsfield-soul-id", "train my face", "create my Soul", "digital twin", "consistent character", or "brand avatar". R-VISUAL-ID: plugs into the brand-identity pipeline and chains into higgsfield-generate via --soul-id. Requires the higgsfield CLI, auth, and a paid plan.
    2 repo stars
  8. ▌
    Relationship Network Os · agentik-os bundle
    Help build, protect and deepen valuable human relationships through attention, memory, generous relevance, follow-through, boundaries, communication and thoughtful introductions. Contains 12 specialist agents, 18 skills, 7 protocols and 6 schemas. Use for relationship tracking, follow-up planning, introduction crafting, boundary setting, or network stewardship. Trigger words: relationship, network, follow up, introduction, boundaries, relationship memory; FR: relation, reseau, suivi de contact, introduction, limites, memoire relationnelle.
    2 repo stars
  9. ▌
    Featureaudit · agentik-os
    Forensic feature completeness audit v1 (Gestalt-Popper). 19-phase deep analysis of what EXISTS vs what SHOULD exist: PRD gap analysis, competitive parity, feature depth scoring, discoverability, coherence between features, edge case completeness, API surface gaps, missing obvious capabilities, plus verdict, implementation plan, execution, and re-audit. Answers: "Is this product COMPLETE?" Score /320. Preamble v1.0 compliant. Audit → Plan → Implement → Re-audit. Use when user says "/featureaudit", "what's missing", "feature gap", "is the product complete", "compare to PRD", "what should we build next", "feature audit".
    2 repo stars
  10. ▌
    Privacyaudit · agentik-os
    Forensic privacy & data-protection audit v1 (Gestalt-Popper). 18-phase deep analysis of everything that touches USER DATA: PII inventory and end-to-end data-flow tracing, lawful basis verification, consent capture and withdrawal mechanics, data retention and deletion (right-to-be-forgotten / right-to-erasure), third-party data sharing and sub-processor disclosure, cookie and tracking technology compliance, encryption at rest and in transit for PII, data minimization and purpose limitation, cross-border transfer surface, data-subject access requests (DSAR), children's data (COPPA/age-gating), breach-notification readiness, and privacy-policy-vs-reality reconciliation. Covers the GDPR and CCPA/CPRA surface. Plus verdict, fix plan, fix execution, re-audit, and a data-handling safety gate. Score /360. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/privacyaudit", "privacy audit", "is user data handled lawfully", "gdpr audit", "ccpa audit", "data protection audit", "pii audit", "con
    2 repo stars
  11. ▌
    Releaseaudit · agentik-os
    Forensic release & shipping-safety audit v1 (Gestalt-Popper). 20-phase deep analysis of whether shipping is SAFE and REVERSIBLE: CI/CD pipeline integrity, build reproducibility (deterministic, hermetic, lockfile-pinned), semantic versioning correctness, changelog accuracy (does it match the diff?), database migration safety (forward AND rollback, expand-contract, backfill ordering), blue-green / canary / rolling deployment strategy, the rollback procedure (does it actually exist, is it tested, is it one command?), feature-flag hygiene (stale flags, kill switches, default-safe), deploy gates (required checks, approvals, smoke tests), secret handling in the pipeline (no plaintext in logs, masked, least-privilege deploy tokens), post-deploy verification (health checks, 200 probe, error-budget burn), artifact provenance & supply-chain signing, environment parity (dev/staging/prod drift), zero-downtime guarantees, dependency-on-deploy ordering, plus verdict, fix plan, fix execution, re-audit, and a deploy-safety g
    2 repo stars
  12. ▌
    Higgsfield Generate · agentik-os bundle
    Generate brand-quality images, videos, audio (voiceover / text-to-speech, voice cloning, and video dubbing — Seed Audio 1.0 plus ElevenLabs and other selectable TTS engines), and ads via Higgsfield (Marketing Studio: branded ads, avatars, products, hooks; Soul/Cinema/Kling models). Use when the user says "/omg-higgsfield-generate", "/higgsfield-generate", "generate an image", "make a video", "make a voiceover", "text to speech", "voice clone", "dub this video", "brand video", "UGC ad", "product demo", or "marketing studio". R-VISUAL-ID: the visual-generation engine; consumes Soul IDs from higgsfield-soul-id. Requires the higgsfield CLI, auth, and a paid plan.
    2 repo stars
  13. ▌
    Operations Automation Os · agentik-os bundle
    Interview and observe how a product or business actually works, reveal waste and control gaps, decide what to remove, simplify, standardize, delegate or automate, and produce production-ready automation blueprints with monitoring and recovery. Contains 24 specialist agents, 39 skills, 9 protocols and 9 schemas. Use for process audits, workflow simplification, automation design, standard operating procedures, or control-gap review. Trigger words: operations, automation, process audit, workflow, standardize, delegate, automation blueprint, SOP; FR: operations, automatisation, audit de processus, flux de travail, standardiser, deleguer, blueprint d'automatisation.
    2 repo stars
  14. ▌
    Audit Tracker · agentik-os
    Audit setup + tracking dashboard. Use when user says "/audit-tracker", "audit status", "audit dashboard", "audit history", "list audits", "where am I with audits", "setup audits", "init audits". Ensures audits/ folder exists, .gitignore configured, tracks all audits run with scores + freshness, recommends re-runs when stale (>30 days). Reads audits/.<audit-id>/verdict.json across all audit subdirs to build dashboard.
    2 repo stars
  15. ▌
    Design System · agentik-os bundle
    Senior Design System Auditor & UI/UX Consistency Engine. Activate when: user wants to audit UI consistency, fix design issues, establish a design system, review dashboard layout, check component coherence, or make a frontend look professional and polished.
    2 repo stars
  16. ▌
    UI UX Pro Max · agentik-os bundle
    UI/UX design intelligence for web and mobile. 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: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
    2 repo stars
  17. ▌
    Marketing Strategist · agentik-os
    Senior B2B SaaS / tech marketing strategy — go-to-market, product marketing, demand generation, positioning, category creation, and scaling the marketing org into a revenue engine. Use when the user says "/omg-marketing-strategist", "/marketing-strategist", "marketing strategy", "GTM strategy", "demand gen", "marketing plan", or "scale marketing". R-MARKETING: the strategist lens that frames the tactical marketing skills.
    2 repo stars
  18. ▌
    Agent Ecosystem Watch · agentik-os bundle
    Agent-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
    2 repo stars
  19. ▌
    Retentionaudit · agentik-os
    Forensic retention + opportunity audit v1.1 (Gestalt-Popper, READ-ONLY). 20-phase parallel deep analysis applying 4 expert frameworks: Hooked (Eyal), Jobs-To-Be-Done (Christensen), Power of Moments (Heath), and Fogg B=MAT. Inventories user-journey gaps, drop-off forensics, aha-moment latency, hook strength, personalization debt, onboarding completeness, empty-states, network effects, sales angles, monetization hooks, friction surfaces, reactivation flows, community surfaces, discoverability, power-user delight. Outputs RICE-prioritized roadmap with Fogg adoption likelihood per top idea. Answers: "What would a senior CPO of a $1B SaaS find that we MISSED to satisfy users 3x more and drive retention compounding?" Score /400. READ-ONLY — proposes, never codes. Hands off to /planner or /implement. Use when user says "/retentionaudit", "what would a CPO suggest", "retention audit", "feature opportunities", "improve user satisfaction", "make it sticky", "retention hooks", "growth opportunities", "what are we missin
    2 repo stars
  20. ▌
    Automationaudit · agentik-os
    Forensic automation infrastructure audit v1 (Gestalt-Popper). 22-phase deep analysis of everything that RUNS AUTOMATICALLY: cron jobs, shell scripts, Python scripts, daemons, systemd timers, CI/CD pipelines, dispatch chains, orchestration logic, scheduling order, dependency graphs, error recovery, log rotation, dead automations, race conditions between scheduled tasks, secret exposure in scripts, idempotency violations, silent failures, monitoring gaps, plus verdict, fix plan, fix execution, re-audit. Score /400. Preamble v1.0 compliant. Use when user says "/automationaudit", "audit automations", "audit cron", "audit scripts", "check all my crons", "what scripts are running", "automation health", "scheduled tasks audit".
    2 repo stars
  21. ▌
    Agentic Engineering Lab · agentik-os
    AGK Agentic Engineering Lab loop that Omega oracles actually run, not a blog post. Walk Understand → Explain → Design → Build → Debug → Test → Evaluate → Secure → Deploy → Observe → Improve. Required coding-agent dimensions: repo context, editing, shell, tests, git, sandbox, verification, human-in-the-loop, finish reports. Writers cannot self-approve. Fake-done is forbidden. Use when the user says "/lab", "/omg-lab", "agentic engineering lab", "run the lab loop", or when an Omega oracle is dispatched.
    2 repo stars
  22. ▌
    Delivery Customer Success Os · agentik-os bundle
    Manage the complete customer journey after commercial commitment: handoff, onboarding, discovery, success planning, delivery, scope, communication, acceptance, adoption, value proof, renewal, expansion, referral and offboarding. Contains 19 specialist agents, 30 skills, 9 protocols and 9 schemas. Use for client onboarding, delivery tracking, scope management, customer success planning, adoption/value-proof reporting, or renewal and expansion handoffs. Trigger words: delivery, customer success, onboarding, scope, adoption, renewal, expansion, offboarding; FR: livraison, succes client, integration client, perimetre, adoption, renouvellement, expansion.
    2 repo stars
  23. ▌
    Quality Evaluation Release Os · agentik-os bundle
    Prove that a product conforms to its contracts, manages risk, can be observed and recovered, and is ready for controlled release and operation. Independent certification authority positioned between Builder OS and production. Contains 16 specialist agents, 26 skills, 7 protocols and 8 schemas. Use for release readiness review, quality gates, contract conformance checks, observability and recovery validation, or go/no-go release decisions. Trigger words: quality, evaluation, release, release readiness, conformance, observability, go no-go; FR: qualite, evaluation, mise en production, conformite, observabilite, decision de lancement.
    2 repo stars
  24. ▌
    Audit Orchestrator · agentik-os
    Intelligent audit orchestrator — detects project type + user intent, recommends optimal audits with three bounded modes (Focused/Standard/Forensic). Use when user says "/audit", "what should I audit", "full audit", "audit my project", "audit fast", "audit deep", "find issues", "improve quality", "production ready check", "ship-ready audit". Auto-detects project stack and intent keywords (speed, security, design, content, accessibility, full) to pick best 1-N audits. Dispatches in parallel waves. Reads results from audits/.<audit-id>/verdict.json after each run.
    2 repo stars
  25. ▌
    Observabilityaudit · agentik-os
    Forensic observability audit v1 (Gestalt-Popper). 18-phase deep analysis of whether you can SEE WHAT THE SYSTEM DOES IN PRODUCTION: structured logging coverage, log-level correctness, trace/span propagation (OpenTelemetry), correlation/request IDs, metrics instrumentation (RED: Rate-Errors-Duration, USE: Utilization-Saturation-Errors), dashboard coverage, alerting rules and thresholds, SLO/SLI definition and error budgets, error tracking (Sentry/Rollbar) coverage and grouping, log retention + PII-in-logs hygiene, sampling strategy, cardinality control, health/readiness probes, log/metric/trace correlation, on-call runbooks, and the "3am incident" debuggability test, plus verdict, fix plan, fix execution, re-audit, and instrumentation safety gate. Score /360. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/observabilityaudit", "observability audit", "can we see what it does", "are we observable", "logging audit", "tracing audit", "metrics audit", "do we have dashboards", "alerti
    2 repo stars
  26. ▌
    Product Marketing Context · agentik-os
    Create and maintain the product-marketing context document (positioning, ICP, audience, messaging) at .agents/product-marketing.md that every other marketing skill reads, so foundational info is never repeated. Use when the user says "/omg-product-marketing-context", "/product-marketing-context", "positioning", "ICP", "ideal customer profile", "target audience", "product context", or "set up marketing context". R-MARKETING: run this FIRST, before the other marketing skills.
    2 repo stars
  27. ▌
    Caio Run And Optimize · agentik-os bundle
    Use when a Chief AI Officer (or fractional CAIO) runs a LIVE, delivered Company AI OS — measures ACTUAL post-go-live ROI from real telemetry (never invented), monitors system health with alert thresholds, runs the weekly/monthly optimization loop, operates the deliberately-light 1h/week strategic quota, and drives client retention + land-and-expand to the next department. The Phase-5 RUN step that closes the accompaniment chain into a compounding loop back to the architect. EN triggers run the AI system, measure actual ROI, re-measure ROI, post-go-live ROI, cohort ROI, North Star Metric of the system, AI health dashboard, alert thresholds, optimization loop, weekly AI quota, 1h/week retainer, Quarterly Business Review, QBR, NRR expansion, next department, client-as-reference, retention and expansion, prove the projected ROI. FR triggers faire tourner le système IA, mesurer le ROI réel, re-mesurer le ROI, ROI après mise en prod, ROI par cohorte, métrique étoile du système, tableau de bord de santé IA, seuils d
    2 repo stars
  28. ▌
    Stitch Design Taste · agentik-os bundle
    Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
    2 repo stars
  29. ▌
    Product Development System · agentik-os bundle
    The OmegaOS way of doing product work. Use this WHENEVER a mission touches a product decision: defining a vision, brainstorming ideas, framing an opportunity, proposing or scoping a feature, running discovery, prioritizing a backlog, or modelling a workflow/process. It is the operating method every oracle and worker follows so we never jump from "we have an idea" straight to "let's build it". The chain is always: Outcome -> Opportunity -> Idea -> Feature (Discovery -> Prioritization -> Specification) -> Workflow -> Build -> Measure. Seven sub-systems, each with its own objects, fields, statuses, and relations: Vision Board, Brainstorming System, Opportunity Board, Feature System, Feature Discovery, Feature Prioritization, Workflow Builder. Triggers (EN): "new feature", "should we build", "product vision", "roadmap", "brainstorm ideas", "prioritize", "RICE/ICE", "opportunity", "user problem", "spec this feature", "discovery", "acceptance criteria", "map the workflow". Triggers (FR): "nouvelle feature", "faut-i
    2 repo stars
  30. ▌
    Caio Discovery Interview · agentik-os bundle
    Run a guided, role-adaptive AI discovery interview with one employee (usually a C-level or manager) so a Chief AI Officer can understand how the company really works before automating anything. Asks — in the person's own professional language (tech to a developer, marketing to a CMO, finance to a controller, plain words to non-technical people), never AI jargon — about their role, week and month, repetitive vs one-off tasks, handoffs between people, tools, integrations, what's automated vs manual, shadow IT, frictions, what to keep, what to improve, current vs ideal position, and the gap. Scans the company website first, handles consent and anonymization, then exports one standardized ZIP of .md files (identical for every person) ready for the CAIO. ALWAYS use this for an employee discovery interview, AI readiness intake, role or workflow discovery, a "decouverte" or "audit de poste", or CAIO onboarding — even if the word "skill" is never said.
    2 repo stars
  31. ▌
    High End Visual Design · agentik-os
    Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
    2 repo stars
  32. ▌
    Mm 10 Selling · agentik-os
    Invoke when a project must convert leads into paying customers and you need to decide the revenue engine (sales-led vs PLG) and the closing/onboarding mechanism before writing copy or coding an onboarding. Also fires on EN: 'sales-led vs PLG', 'founder-led sales', 'B2B sales process', 'discovery call', 'Jobs-to-be-Done', 'demo to close', 'handle objections', 'feel-felt-found', 'aha moment', 'activation / time-to-value', 'signup-flow CRO', 'behavioral follow-up sequence', 'how do I price the sales motion'; and FR: 'vente B2B', 'PLG ou sales-led', 'founder-led sales', 'appel de discovery', 'diagnostic avant pitch', 'closing', 'traiter les objections', 'feel-felt-found', 'aha moment', 'activation / time-to-value', 'onboarding qui vend', 'séquence de relance comportementale', 'la fortune est dans le follow-up'. Use when intérêt existe mais le revenu ne suit pas, ou avant d'automatiser une vente jamais réussie à la main.
    2 repo stars
  33. ▌
    Caio Implementation Runbook · agentik-os bundle
    Use when a Chief AI Officer (or fractional CAIO) moves from blueprint to BUILD — taking caio-enterprise-workflow-architect's company-ai-os/ and EXECUTING the build of a centralized, federated Company-AI-OS: one dedicated client-owned server + one function-specific micro-SaaS per C-Level (CIO/CTO, CMO, CFO, CDO, COO, CHRO, CSO), wired by an inter-dashboard API contract so a COO metric can trigger a CFO alert, integrated via Composio's 6 critical connectors, with automated reports, built-in monitoring + cost/usage tracking, and a per-deliverable ship-gate that ships value in week 1 — anti-black-box, everything documented, readable, auditable, transferable. EN triggers: CAIO implementation, build the company AI OS, implementation runbook, realize the architecture, centralized federated dashboards, server provisioning, micro-SaaS per C-level, inter-dashboard API contract, dashboard federation, Composio wiring, automated reports, AI observability, instrumentation, ship-gate, go-live, Next.js Convex Clerk Stripe Co
    2 repo stars
  34. ▌
    Mm 07 Paid Ads · agentik-os
    Invoke this doctrine when deciding whether, when, and how to spend money on paid acquisition — the why/when/sequence behind ads, before reaching for an execution skill. Also fires on EN: 'paid ads', 'CAC LTV', 'LTV:CAC ratio', 'payback period', 'creative testing', 'UGC ads', 'ad angles', 'should I run ads', 'scaling ad budget', 'blended CAC', 'iOS 14 attribution', 'retargeting trap', 'creative is the targeting'; and FR: 'pub payante', 'acquisition payante', 'CAC LTV', 'ratio LTV:CAC', 'payback', 'créatif testing', 'pub UGC', 'angles publicitaires', 'dois-je lancer des pubs', 'scaler le budget pub', 'CAC blended', 'attribution post-iOS 14', 'ROAS plateforme', 'quand commencer le paid'. Use when a founder asks if they are ready for ads, how to structure a first campaign, how to read performance honestly, or when to scale spend.
    2 repo stars
  35. ▌
    Caio AI Readiness Assessment · agentik-os bundle
    Use BEFORE committing to a Chief-AI-Officer engagement — the pre-sign go/no-go qualification gate, the whitepaper's honest 30-minute discovery call ("I tell you honestly whether your case fits our approach; if not, I redirect you"). Maps a company against a 9-dimension AI-Readiness Maturity Model (0-4 per dimension with evidence), computes a weighted Readiness Index + maturity tier (Nascent / Emerging / Ready / Leading), and returns an honest GO / NOT-YET / REDIRECT verdict — willing to say "not yet, fix X first" or "you don't need us, you need Y". On GO it shapes the engagement (which of the 5 phases, 1-3 months, team size) + indicative investment anchored to the real grid (€2,500 setup + €2,500/member/month, monthly no-minimum) and hands to /market-proposal for the signed SOW. EN triggers AI readiness assessment, AI maturity model, go/no-go, qualify this client, is this company AI-ready, readiness scorecard, pre-engagement qualification, discovery call, should we take this client, CAIO qualification, disqua
    2 repo stars
  36. ▌
    Caio Enablement And Transfer · agentik-os bundle
    Use when a Chief AI Officer (or fractional CAIO) has a BUILT, working Company AI OS and must now drive ADOPTION (Phase 3 — onboard every role, train end-users, validate first use cases in real conditions) and then TRANSFER MASTERY (Phase 4 — teach the client's team to add an agent, connect a tool, adjust a report UNAIDED) so the client OWNS and EXTENDS the system instead of depending on the CAIO. The "internal mastery" half of the offer — your teams are not spectators of the system, they are its operational guardians. EN triggers AI adoption plan, onboarding sessions, end-user training, internal documentation, system runbook, knowledge transfer, handover, autonomy readiness, extension playbook, add an agent, connect a tool, adjust a report, adoption tracker, change management for AI, nobody uses the system, operational guardians, transfer to autonomy. FR triggers plan d'adoption IA, sessions d'onboarding, formation utilisateurs, documentation interne, runbook, transfert de compétences, passation, autonomie, p
    2 repo stars
  37. ▌
    Marketing Master · agentik-os
    Run the full Marketing Mastery doctrine on a real project — a 12-Part gap-check that audits positioning, message, funnel, content, paid, pricing, partnerships, selling, retention against the doctrine and corrects the landing + strategy, then ships a 90-day plan. Also fires on EN: 'marketing master', 'run the marketing doctrine', 'full marketing audit', 'marketing gap-check', 'align my marketing', 'marketing mastery', '90-day marketing plan', 'audit my go-to-market'; and FR: 'marketing master', 'audit marketing complet', 'aligner mon marketing', 'gap-check marketing', 'doctrine marketing', 'plan marketing 90 jours', 'audite mon go-to-market'. Use to run all 12 mm-* doctrine skills as one orchestrated, self-correcting pass over a project.
    2 repo stars
  38. ▌
    Mm 03 Why People Buy · agentik-os
    Invoke this doctrine when you need to understand WHY a prospect buys (or doesn't) before writing any message, page, or offer — the demand engine behind the product. Also fires on EN: 'why people buy', 'jobs to be done', 'JTBD', 'four forces of progress', 'switch interview', 'levels of awareness', 'buyer psychology', 'Cialdini persuasion', 'pain vs desire', 'emotion vs rationalization', 'value equation', 'demand before product'; and FR: 'pourquoi les gens achètent', 'jobs-to-be-done', 'les 4 forces du progrès', 'interview JTBD', 'niveaux de conscience', 'psychologie de l'acheteur', 'leviers de persuasion Cialdini', 'douleur vs désir', 'émotion vs rationalisation', 'équation de valeur', 'le vrai job du client'. Use when a SaaS stalls, conversion is flat, or copy lists features to a cold audience and you must diagnose the real job + forces before messaging.
    2 repo stars
  39. ▌
    Caio Enterprise Workflow Architect · agentik-os bundle
    Use when a Chief AI Officer (or fractional CAIO) audits an organization, interviews employees, maps daily work, identifies tools and automation needs, designs agentic systems, specifies an AI dashboard, builds a 30/60/90 roadmap, and produces ROI + governance docs — turning a company into a legible, automatable, agentic Company AI OS. EN triggers CAIO audit, enterprise AI audit, company AI strategy, workflow audit, automation backlog, agentic systems design, AI dashboard spec, AI ROI model, company AI OS, AI operating system, build-vs-buy AI, AI governance and HITL. FR triggers audit IA entreprise, audit complet entreprise IA, cartographie des workflows, opportunites d'automatisation, systeme agentique, tableau de bord IA, ROI IA, gouvernance IA, OS IA d'entreprise, rendre l'entreprise lisible. NOT for personal/solo productivity (use personal-os-builder) or implementing a single agent (use agentic-systems-builder).
    2 repo stars
  40. ▌
    Mm 05 Funnel Channels · agentik-os
    Invoke this doctrine when deciding WHERE to play and WHY — diagnosing funnel stage, channel fit, and the one or two channels to dominate before any tactic is touched. Also fires on EN: 'which channel', 'channel strategy', 'full funnel', 'TOFU MOFU BOFU', 'product-channel fit', 'AARRR pirate funnel', 'owned earned paid', 'bullseye framework', 'traction channels', 'growth loop vs growth hack', 'distribution architecture', 'where to spend marketing time'; and FR: 'quel canal choisir', 'architecture de distribution', 'full funnel', 'funnel pirate AARRR', 'product-channel fit', 'owned earned paid', 'cadre bullseye', 'canaux de traction', 'goulot d''étranglement acquisition', 'growth loop ou growth hack', 'dépendance au paid', 'actif owned'. Use when a founder is about to 'do SEO' or 'launch ads' without having chosen the channel the product structurally supports.
    2 repo stars
  41. ▌
    Mm 06 Content SEO Geo · agentik-os
    Invoke this doctrine to decide HOW a founder gets found in 2026 — topical authority, SEO by intent, GEO (being cited by AI), and distribution-first content. Also fires on EN: 'content engine', 'topical authority', 'topic cluster', 'pillar page', 'search intent', 'E-E-A-T', 'GEO', 'generative engine optimization', 'AI overview', 'zero-click', 'schema markup', 'build in public', 'content distribution', 'long-tail SEO'; and FR: 'moteur de contenu', 'autorité thématique', 'cluster de contenu', 'page pilier', 'intention de recherche', 'être cité par les IA', 'recherche sans clic', 'schema markup', 'build in public', 'distribution de contenu', 'long-tail', 'marque personnelle', 'newsletter founder'. Use when the founder asks what to publish, how to rank, how to be cited by ChatGPT/Perplexity, or how to turn knowledge into compounding distribution.
    2 repo stars
  42. ▌
    Mm 01 Foundations 2026 · agentik-os
    Invoke this doctrine when a solo founder or operator needs the 2026-2027 marketing map before any tactic — to separate what changed (channel) from what never changes (the buying mechanism), audit where they are in the system, and kill the three novice myths. Also fires on EN: 'marketing fundamentals', 'what changed in marketing 2026', 'zero-click search', 'GEO generative engine optimization', 'distribution over product', 'marketing vs advertising', 'marketing system map', 'jobs to be done basics', 'AI search killed SEO', 'why isnt my product selling', 'build in public', 'where do I even start marketing'; and FR: 'fondamentaux marketing', 'ce qui a changé en marketing', 'zéro-clic', 'GEO référencement IA', 'distribution vs produit', 'marketing ≠ publicité', 'carte du système marketing', 'par où commencer le marketing', 'mon produit ne se vend pas', 'mythes marketing', 'être cité par les IA', 'build in public'. Use when someone is about to spend on ads or content but the positioning is still fuzzy, or asks the
    2 repo stars
  43. ▌
    Mm 12 Novice To Expert · agentik-os
    Invoke when a solo / technical founder needs the doctrine that sequences a whole marketing practice — the 90-day plan from positioning to first scaling, then repeating it to build judgment and taste. Also fires on EN: 'where do I start with marketing', '90-day marketing plan', 'marketing sequence', 'novice to expert', 'how to learn marketing as a founder', 'multi-product without spreading thin', 'weekly marketing routine', 'keep delegate automate', 'build judgment and taste', 'mastery checklist'; and FR: 'plan 90 jours', 'par où commencer en marketing', 'séquence marketing', 'de novice à expert', 'fondateur multi-produits', 'routine marketing hebdo', 'garder déléguer automatiser', 'cultiver le goût', 'jugement marketing', 'checklist de maîtrise'. Use when the founder is overwhelmed by tactics and needs the ORDER, the cadence, and the path to expertise — not a single tactic.
    2 repo stars
  44. ▌
    Applying Brand Guidelines · agentik-os bundle
    Apply a brand system PROGRAMMATICALLY to generated documents and decks — colors, typography, layout and messaging — then validate the output against the guidelines and report violations. Use for 'brand this document', 'apply our brand guidelines', 'make this on-brand', 'check brand compliance', or in French 'applique la charte graphique', 'mets ca aux couleurs de la marque', 'verifie la conformite de marque'. Ships apply_brand.py and validate_brand.py. NOT for DESIGNING the identity (that is brand-identity) and NOT a design critique (that is critique-brand-consistency).
    2 repo stars
  45. ▌
    Creating Financial Models · agentik-os bundle
    Build a financial model: discounted cash flow (DCF) valuation, sensitivity tables, Monte Carlo simulation and scenario planning for an investment or a business decision. Use for 'build a DCF', 'value this company', 'what is it worth', 'sensitivity analysis', 'model the downside', 'run scenarios', or in French 'construis un DCF', 'valorise cette boite', 'analyse de sensibilite', 'modelise les scenarios'. Ships dcf_model.py and sensitivity_analysis.py. NOT for reading existing statements (that is analyzing-financial-statements).
    2 repo stars
  46. ▌
    Mm 02 Positioning Category · agentik-os
    Invoke when a founder must decide HOW their product is perceived — the context that makes its value obvious — before spending a euro on any channel. Also fires on EN: 'positioning', 'category design', 'join or create a category', 'differentiation', 'me-too / parity trap', 'ICP / ideal customer profile', 'Jobs-to-be-Done', 'beachhead / niche-first', 'repositioning', 'house of brands vs founder brand', 'build in public', 'AI search / GEO positioning'; and FR: 'positionnement', 'catégorie de marché', 'rejoindre ou créer une catégorie', 'différenciation', 'piège du me-too', 'ICP / client idéal', 'viser étroit', 'tête de pont', 'repositionner', 'marque-fondateur', 'phrase de positionnement', 'lisibilité IA'. Use when the message is flou, the homepage could name a competitor without sounding wrong, or distribution amplifies something nobody understands.
    2 repo stars
  47. ▌
    Mm 04 Messaging Copy Offer · agentik-os
    Invoke this doctrine when a project's strategy must be translated into the words, the offer, and the page that make an unknown, hurried stranger act. Also fires on EN: 'messaging', 'copywriting', 'value proposition', 'irresistible offer', 'value equation', 'landing page copy', 'headline / hook', 'PAS / BAB / AIDA', 'guarantee', 'value stacking', 'brand voice', 'CTA', 'social proof'; and FR: 'message', 'copywriting', 'proposition de valeur', 'offre irrésistible', 'équation de valeur', 'copy de landing', 'accroche / titre', 'PAS / BAB / AIDA', 'garantie', 'empilement de valeur', 'voix de marque', 'verbatims', 'preuve sociale'. Use when positioning is set but the copy, the offer, or the conversion page underperform, sound abstract, talk about 'us' instead of 'you', or fail the 3-second test.
    2 repo stars
  48. ▌
    Mm 08 Pricing Monetization · agentik-os
    Invoke when a founder must SET, package, test, or raise a price — to capture the value created instead of leaving it on the table. Also fires on EN: 'pricing strategy', 'how much to charge', 'value-based pricing', 'good better best tiers', 'value metric', 'decoy pricing', 'AI/token pricing', 'usage vs seat pricing', 'raise prices', 'NRR / net revenue retention', 'Van Westendorp', 'packaging', 'expansion revenue'; and FR: 'fixer un prix', 'combien facturer', 'pricing à la valeur', 'trois tiers good/better/best', 'value metric', 'pricing leurre', 'pricing IA/tokens', 'usage vs siège', 'augmenter les prix', 'rétention nette de revenu', 'Van Westendorp', 'packaging', 'revenu d'expansion'. Use when the price is set by fear/cost instead of value, or when margin, packaging, or expansion revenue is the bottleneck.
    2 repo stars
  49. ▌
    Analyzing Financial Statements · agentik-os bundle
    Calculate and interpret financial ratios from real statement data — liquidity, profitability, leverage, efficiency and valuation multiples — and turn them into an investment read rather than a table of numbers. Use for 'analyse these financials', 'compute the ratios', 'is this company healthy', 'read this balance sheet / income statement / 10-K', or in French 'analyse ces comptes', 'ratios financiers', 'cette boite est-elle saine'. Ships calculate_ratios.py and interpret_ratios.py. NOT for building a forecast model (that is creating-financial-models).
    2 repo stars
  50. ▌
    Mm 11 Measure Loops Retention · agentik-os
    Invoke when a solo founder wants to 'do growth' and reaches for traffic first — this doctrine forces the compounding order retention -> monetization -> acquisition, picks the North Star Metric, reads the retention curve, and routes the right growth loop. Also fires on EN: 'North Star Metric', 'retention curve', 'cohort analysis', 'growth loop vs funnel', 'churn and NRR', 'product-market fit signal', 'Sean Ellis PMF test', 'LTV CAC payback', 'viral k factor', 'ICE RICE prioritization', 'aha moment onboarding', 'analytics stack for a solo'; and FR: 'rétention avant acquisition', 'North Star Metric', 'courbe de rétention', 'analyse par cohortes', 'growth loop vs funnel', 'churn et expansion', 'NRR', 'test PMF Sean Ellis', 'LTV CAC payback', 'facteur viral k', 'priorisation ICE RICE', 'seau percé', 'système qui compose'. Use when growth feels like a treadmill — you keep paying for acquisition that evaporates.
    2 repo stars
  51. ▌
    Mm 09 Partnerships Network Effects · agentik-os
    Invoke when growth has to come from OTHER people's audiences, not just your own product or paid spend — partnerships, integrations, referral, viral loops, borrowed audience, community-as-moat. Also fires on EN: 'partnership strategy', 'co-marketing', 'integration / marketplace distribution', 'affiliate vs referral', 'viral loop', 'viral coefficient k', 'growth loop vs funnel', 'borrowed audience', 'community moat', 'build in public', 'network effects', 'channel partners', 'GEO / cited by AI'; and FR: 'stratégie de partenariat', 'co-marketing', 'intégration / marketplace', 'affiliation vs referral', 'boucle de croissance', 'coefficient viral k', 'audience empruntée', 'communauté comme douve', 'build in public', 'effets de réseau', 'distribution embedded', 'être recommandé par les IA'. Use when a solo founder with a good product is stuck because nobody knows it exists and the question is HOW to grow on distribution others already built.
    2 repo stars
  52. ▌
    10x · agentik-os
    10x Thinking Mode — ambition reframe engine, not a pep talk. Takes the user's idea, plan, or goal and rethinks it 10x bigger: names the implicit ceiling they silently assumed, splits REAL constraints (physics, law, cash today) from ASSUMED ones (habit, fear, convention, identity), redesigns the mechanism — a different machine, not the same machine working harder — then runs a reality pass (what breaks first, riskiest assumption) and commits ONE concrete first step within 48h. Use when the user says '/10x', '/omg-10x', 'think 10x bigger', 'am I thinking too small', '10x this idea', 'what would the ambitious version look like', or in French 'pense 10x plus grand', 'vois plus grand', 'la version ambitieuse'. NOT for execution-planning the current-size plan (that is /omg-planner) — /10x changes the ambition, then planning follows.
    2 repo stars
  53. ▌
    Duo · agentik-os
    Binome multi-modele Claude ⇄ Codex/Sol (⇄ GLM opt-in). Chaque modele joue sa force : Claude stratege et arbitre, Codex critique profonde + deep code review + implementation complexe, GLM coder mecanique sur demande explicite. Quatre profils : build (defaut), build coder GLM, review (Codex relit un diff existant), reflect (reflexion architecture sans code). Bascule automatique sur Claude si le quota Codex est epuise. Use when the user types /duo, /omg-duo, or says: build/implement/refactor/fix with the binome, code this with Codex, delegate to Codex/Sol, pair Claude and Codex, deep review this diff with Codex, fais relire par Codex, or FR 'code ça avec Codex', 'délègue à Sol', 'binome Claude Codex', 'fais coder Codex et relis', 'review profonde de ce diff'. NOT for pure questions, reads, or one-liners (Claude handles those directly — no need to burn the Codex quota).
    2 repo stars
  54. ▌
    Prd · agentik-os
    OmegaOS-shipped product documentation suite generator (requirements, features, user stories, tech stack, milestones) for AI-agent implementation. Use when user says "/omg-prd", "generate PRD", "product docs", "product requirements". Supports --new, --skip-research, --input, --platform flags. Step 2 of the OmegaOS new-project pipeline; run /omg-vision first, then /omg-planner.
    2 repo stars
  55. ▌
    Books Os · agentik-os bundle
    Operate the canonical ALEXANDRIA librarian for book analysis, comparison, teaching, recall, knowledge maps, decision support, reading paths and durable application. Use for Books OS, reading, learning, book synthesis, knowledge retention, author comparison, quizzes, flashcards, or applying a book to a real decision.
    2 repo stars
  56. ▌
    Stax · agentik-os bundle
    Convert 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.
    2 repo stars
  57. ▌
    Design Os · agentik-os bundle
    Compile 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.
    2 repo stars
  58. ▌
    Ghost · agentik-os
    Ghost — Persona Simulator (Honest Ghost). Master-level thinking mode that role-plays a target persona — user, client, investor, partner — reacting HONESTLY to a pitch, page, product, or offer: the real objections (including the unspoken one), the questions they would actually ask, and a BUY / NO-BUY / CONDITIONAL verdict with a concrete commitment, then an out-of-character debrief of the top 3 conversion fixes. The ghost is the person who is never in the room when you rehearse. Use when the user says '/ghost', '/omg-ghost', '/ghost <persona>' (e.g. '/ghost investor', '/ghost dentiste'), or in French 'joue le client', 'simule un investisseur'. NOT for real user research (a simulation never replaces talking to real users) and NOT for multi-model deliberation (that is /llm-council) — /ghost is one persona's honest reaction.
    2 repo stars
  59. ▌
    Pitch · agentik-os
    Pitch — 30-Second Pitch Generator. Distills any idea, product, or project into a tight 30-second SPOKEN pitch — hook, problem, solution, proof, ask — on a hard 75-85 word budget, plus a one-line version. Pulls the five raw materials (who it is for, the pain, the one mechanism, the strongest real proof, the specific ask) from whatever exists — idea text, a repo, a page, the conversation — lists honest inferences [ASSUMED] in a separate ASSUMPTIONS section (beat text stays clean speakable words), and never invents numbers or traction: no real proof reads 'none yet'. Use when the user says '/pitch', '/omg-pitch', 'elevator pitch', '30-second pitch', 'pitch this', 'pitch my idea/startup/product', 'how do I explain this in 30 seconds', or in French 'pitch 30 secondes', 'pitche', 'pitche-moi ça', 'présente mon projet en 30 secondes'. NOT for landing pages or long-form marketing copy (that is the marketing suite, e.g. /omg-ad-creative) — /pitch is the spoken 30-second distillation.
    2 repo stars
  60. ▌
    Stack · agentik-os bundle
    Build the canonical AgentikOS app stack — Next.js + Convex + Clerk + Stax, with Stripe as an opt-in flag — from scratch or from a Blueprint OS blueprint folder. Pulls the live Stax checkout before every scaffold (R-BLUEPRINT-STACK), vendors the panel engine, wires Convex auth to Clerk, and (with --stripe only) stubs subscriptions with an explicit list of the IDs the operator must provide. Use when the user says "/stack", "/omg-stack", "new app", "scaffold the stack", "build the app", "start a new OS", "nouveau projet Next Convex", "monte la stack", "construis l'app", "build from the blueprint", or names any subset of Next.js / Convex / Clerk / Stripe / Stax as the thing to set up. This is the BUILD half of the Blueprint OS chain: /blueprint-os designs, /stack builds.
    2 repo stars
  61. ▌
    Watch · agentik-os bundle
    Watch and analyze any video like a marketer with eyes. Give it a URL (YouTube, TikTok, Instagram, Loom, X, anything yt-dlp supports) or a local file: it downloads, extracts scene-change frames, runs a 0-10s hook microscope (dense 2fps frames plus word-level opening transcript), builds a captions-first transcript (Whisper fallback via GROQ_API_KEY or OPENAI_API_KEY, optional), and writes a structured report.md with pacing, hook words, key moments, and quotables. The canonical video-analysis primitive of the marketing machine: competitor hook analysis feeding ads-hooks, ads-video, ad-creative, scriptwriter, social-content, YoutubeContent, art-director-content-engine. Use when the user says '/watch', '/omg-watch', 'watch this video', 'analyze this video', 'analyze this ad', 'hook analysis', 'what does this competitor video do', 'transcribe this video', or in French 'regarde cette vidéo', 'analyse cette vidéo', 'analyse le hook', 'décortique cette pub', 'transcris cette vidéo'. NOT for generating videos (that is
    2 repo stars
  62. ▌
    Builder Os · agentik-os bundle
    Execute 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.
    2 repo stars
  63. ▌
    Content Os · agentik-os bundle
    Operate the full content lifecycle from positioning and daily capture through story mining, research, writing, visual/audio/video production, platform-native packaging, publishing, community engagement and performance learning. Contains 38 specialist agents, 44 skills, 12 protocols and 10 schemas. Use for content strategy, daily capture, story mining, pillar assets, multi-platform cascades (Instagram, TikTok, YouTube, LinkedIn, X, newsletter, article), visual/video/sound briefs, editorial calendars, or performance review. Trigger words: content, capture, story mine, pillar, cascade, platform package, visual brief, video brief, content calendar; FR: contenu, capture du jour, mine d'histoires, cascade multi-plateforme, brief visuel, brief video, calendrier editorial.
    2 repo stars
  64. ▌
    Mindset Os · agentik-os bundle
    Build 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.
    2 repo stars
  65. ▌
    Revenue Os · agentik-os bundle
    Operate a conversational revenue brain and governed database for offers, positioning, pricing, leads, sales pipeline, customers, contracts, invoicing, payments, expenses, cash flow, reserves, forecasting, retention and expansion. Contains 24 specialist agents, 40 skills, 10 protocols and 14 JSON schemas. Use for CRM work, pricing and offer design, sales calls, invoicing and collections, cash flow forecasting, monthly revenue close, or renewal and expansion planning. Trigger words: revenue, offer, pricing, pipeline, invoice, collections, cash flow, forecast, CRM, sales call, proposal, renewal; FR: chiffre d'affaires, tarification, pipeline commercial, facture, recouvrement, prevision de tresorerie, CRM, appel de vente, renouvellement.
    2 repo stars
  66. ▌
    Stepper Os · agentik-os bundle
    Drive 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).
    2 repo stars
  67. ▌
    Linear · agentik-os bundle
    OmegaOS Linear feedback-resolution pipeline (v2 — Workflow-driven). Resolves Linear feedback tickets end-to-end: deep ticket analysis, BEFORE/AFTER browser evidence, surgical fix, strict Fix-Verification comment, the /omg-audit quality gate (100/100), then a neutral In-Review handoff for the operator — the agent NEVER self-marks Done. Auto-detects four modes (FIX / VERIFY-DONE / RE-REVIEW / REGRESSION) and a trigger-guard keeps Linear silent unless the operator named it. The v2 engine fans tickets out in parallel through the OmegaOS Workflow primitive (per-ticket triage → fix → /omg-audit → adversarial verify), then synthesizes — not a sequential one-ticket-at-a-time loop. Single source of truth: the shipped ${OMEGA_DIR}/skills/linear/RULES.md. Use when user says "/omg-linear", "/linear", "fix linear", "resolve feedback", "regler les feedbacks", "verify done linear", "revérifie linear".
    2 repo stars
  68. ▌
    Pdfgen · agentik-os
    Generate polished OmegaOS PDF deliverables with the canonical branded renderer and optionally send them to the operator on Telegram. Use whenever the user explicitly asks for a PDF, a printable report, a whitepaper, an audit PDF, a marketing PDF, or a document that must be delivered as a PDF.
    2 repo stars
  69. ▌
    Vision · agentik-os
    OmegaOS-shipped product identity + emotional positioning via Socratic discovery. Generates VISION.md with internal compass, personas, and design principles. Pure discovery, no code. Use when user says "/omg-vision", "define brand", "product identity", "emotional positioning". Step 1 of the OmegaOS new-project pipeline; follow with /omg-prd then /omg-planner.
    2 repo stars
  70. ▌
    AI Logic Os · agentik-os bundle
    Audit, 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,
    2 repo stars
  71. ▌
    Cleanup · agentik-os bundle
    Nettoyage 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.
    2 repo stars
  72. ▌
    Diagram · agentik-os bundle
    Deterministic diagram / visual-explainer generator — turns intent into precise, editable, brand-themeable diagram-as-code (Mermaid or D2) and renders it to SVG + PNG via CLI. Use for flowcharts, architecture diagrams, sequence diagrams, state machines, ER/data models, agent/system flows, mindmaps, timelines/Gantt, and quadrant/comparison charts — anything that must be technically correct and editable, not photoreal. Use when the user says "/omg-diagram", "/diagram", "draw a diagram", "flowchart", "architecture diagram", "sequence diagram", "state diagram", "ER diagram", "mindmap", "diagram this", or in French "schéma", "diagramme", "organigramme", "fais-moi un schéma". NOT for quote-cards/posters/photoreal art (route to image-gen) or animated data-viz (route to /hyperframes).
    2 repo stars
  73. ▌
    Monitor · agentik-os
    Point 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
    2 repo stars
  74. ▌
    Planner · agentik-os bundle
    OmegaOS-native implementation planner. Reads Vision/PRD/CLAUDE.md, decomposes the work into a DAG of single-worker-dispatch steps, and emits a typed `.planner/tracker.json` that the Rust engine (`omega plan-run`) executes with structural can't-skip enforcement (Gate) and independent verify-command proof (Guardian). Replaces the prose-only VPS planner: sequential execution is enforced by the engine, not by instructions. Use when user says "/omg-planner", "plan this", "make a plan", "build the plan", "decompose", "planifie", "fais le plan".
    2 repo stars
  75. ▌
    Alignment Os · agentik-os bundle
    Alignment Coach {OS}
    2 repo stars
  76. ▌
    Blueprint Os · agentik-os bundle
    Compile software, AI, platform, service, marketplace, mobile, web, or internal-tool ideas and existing project context into a complete, coherent, traceable Product + Technical Definition Pack before implementation planning or coding. Trigger on /blueprint, Blueprint {OS}, product blueprint, product-definition audit, recovery, revision, extension, delta, or preparation for Stepper {OS}. Also trigger on French requests such as "compile ce blueprint", "definition produit et technique", "audit de definition produit", or "prepare le blueprint pour le stepper". Preserve project decisions and stable IDs, separate evidence from assumptions, define product/UX/domain/data/API/AI/security/operations/test contracts, run gates, and continue across outputs without declaring partial work complete.
    2 repo stars
  77. ▌
    Execution Os · agentik-os bundle
    Operate 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.
    2 repo stars
  78. ▌
    Cookbook · agentik-os
    Anthropic's OWN reference implementations, on tap. 94 recipes from anthropics/claude-cookbooks (MIT, pinned) covering RAG and retrieval, agent patterns (prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer), evals and LLM-judge harnesses, tool use and structured output, prompt caching and cost optimization, multimodal and PDF extraction, citations, extended thinking, the Claude Agent SDK, and Claude Managed Agents. Use BEFORE hand-rolling any of those: read the reference, adapt the code, do not re-derive it from memory. Triggers on "/cookbook", "/omg-cookbook", "anthropic cookbook", "claude cookbook", "reference implementation", "how does Anthropic do X", "is there a recipe for", or in French "recette anthropic", "implementation de reference", "comment Anthropic fait X". NOT for Claude Code harness questions (that is claude-code-guide) and NOT for the Claude API reference itself (that is the claude-api skill): this is worked EXAMPLES.
    2 repo stars
  79. ▌
    Pixelrag · agentik-os bundle
    Give the agent EYES on a web page or document: render it to screenshot tiles with `pixelshot` and READ the image, instead of fetching HTML and parsing it. Charts, diagrams, infoboxes, tables and layout survive; markup noise, cookie walls and JS-rendered text stop mattering. Also queries a public 26M-vector visual index of 8.28M Wikipedia pages (no API key) and returns the matching screenshot CROP. Use when the user says "/pixelrag", "/omg-pixelrag", "screenshot this page", "look at this page", "read this page as an image", "what does this page look like", "visual search", or in French "regarde cette page", "fais une capture", "lis cette page comme une image", "recherche visuelle". NOT for scripted E2E of our own apps (Playwright, R-TEST) and NOT for open-ended agentic browsing of an unknown UI (browser-use, R-BROWSER) — this one is READ-ONLY LOOKING, one page at a time.
    2 repo stars
  80. ▌
    Powerups · agentik-os
    Router into the Power-Ups corpus — 907 purchased business/marketing Claude skills (30 Power-Up packs of 406 skills + the 501-skill Ultimate Bundle) plus 272 companion assets (prompt libraries, swipe files, templates, tutorials) installed at ~/.omega/powerups. Use whenever a request matches a business, marketing, content, sales, launch, email, SEO, social, ads, pricing, course, community, podcast, newsletter, YouTube, LinkedIn, Etsy, outreach, branding, ops, HR, legal, finance, nonprofit or client-consulting task and no first-class OmegaOS skill already owns it. Also use when the user says "/powerups", "power up", "power-ups", "the skills I bought", "the 501 bundle", "youraipowerup", or in French "les skills que j'ai achetés", "le pack de 501 skills", "mes power-ups".
    2 repo stars
  81. ▌
    Ramflush · agentik-os bundle
    Purge la RAM et fait le point perf du VPS — `sync` + drop des caches noyau (pagecache/dentries/inodes), compaction mémoire, puis rapport avant/après + top consommateurs RAM/CPU + load average. À lancer quand le VPS est sous charge / rame. Sans risque (les caches sont reconstruits à la demande) ; nécessite root (drop_caches).
    2 repo stars
  82. ▌
    Brainstorm Os · agentik-os bundle
    Run 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”. Also trigger on French requests such as “brainstorm sur c
    2 repo stars
  83. ▌
    Reel Lint · agentik-os bundle
    Note un script de reel /100 contre les patterns viraux mesurés (hook, rétention, format, CTA, outil branché) AVANT de tourner. Use when the user wants to check, score, or validate a reel script or short-form video script.
    2 repo stars
  84. ▌
    Habit Tracker Os · agentik-os bundle
    Operate 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.
    2 repo stars
  85. ▌
    Storyteller Os · agentik-os bundle
    Coach, 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.
    2 repo stars
  86. ▌
    Acceptance · agentik-os bundle
    OmegaOS autonomous browser-acceptance + self-heal gate. The terminal phase of a build: Playwright-sweeps EVERY route (200 + render), captures EVERY console error and failed network request, and walks the authenticated golden path with a real persisted write — then AUTONOMOUSLY fixes whatever it finds (missing route, dead auth bridge, console/network error, broken flow) and re-runs, looping until the sweep is fully green or a hard external blocker (a missing secret) is hit. "It builds" is never "it works" — this proves it works. Use when user says "/omg-acceptance", "acceptance gate", "test everything", "verify the app works", "browser e2e", or as the last step of /omg-new-project + /omg-planner builds.
    2 repo stars
  87. ▌
    Alexandria · agentik-os bundle
    ALEXANDRIA OS — your personal librarian, knowledge architect, learning coach and intellectual sparring partner. Turns any book, idea, decision or problem into deep understanding, durable memory and concrete action, adapted to how YOU personally learn and remember. Seven functions (librarian, cartographer, teacher, learning architect, skeptic, strategist, personal archivist) and 20+ modes: X-ray a book chapter by chapter, distill an idea across many books, put authors in combat, challenge your plan with a 10-round sparring, run a council of perspectives, build flashcards and spaced-repetition, forge memory with stories and mind-palaces. Starts with /setup to calibrate on your learning style, ADHD/attention profile, memory sensibilities, domains and language. Use when the user says '/alexandria', 'librarian', 'analyse this book', 'x-ray this book', 'help me learn/remember X', 'teach me', 'challenge my idea', 'compare these books', or in French 'décortique ce livre', 'aide-moi à retenir', 'apprends-moi', 'challe
    2 repo stars
  88. ▌
    Cold Email · agentik-os bundle
    Write B2B cold outbound emails and multi-touch follow-up sequences that sound human and get replies — subject lines, openers, body copy, CTAs, personalization. Use when the user says "/omg-cold-email", "/cold-email", "cold outreach", "prospecting email", "outbound", "SDR email", "follow-up sequence", or "nobody replies to my emails". R-MARKETING: outbound acquisition.
    2 repo stars
  89. ▌
    Journal Os · agentik-os bundle
    Run 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
    2 repo stars
  90. ▌
    Ad Creative · agentik-os bundle
    Generate 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).
    2 repo stars
  91. ▌
    Browser Use · agentik-os bundle
    Run an agentic browser task from natural language on the Browser Use cloud — the LLM-driven agent navigates an unknown site, extracts data, or fills a form on its own (NOT a local scripted browser). Use when the user says "/omg-browser-use", "/browser-use", "agentic browser task", "browse this site", "extract from a website", "fill out this form", "agentic web automation", or "navigate an unknown site". Boundary R-BROWSER: agentic/unknown-UI/open-ended only; deterministic scripted steps for OUR apps stay in Playwright/acceptance. Requires the paid Browser Use cloud plan + BROWSER_USE_API_KEY.
    2 repo stars
  92. ▌
    LLM Council · agentik-os bundle
    Convene a multi-model Claude COUNCIL for a high-stakes, ambiguous, or irreversible decision — or whenever you want a genuine second opinion. Four different Claude models (Opus 5, Sonnet 4.6, Haiku 4.5, Fable 5) answer the SAME question independently and in parallel, then peer-review each other ANONYMOUSLY (answers shown as Response A/B/C, model identity hidden, so no model is favored by name), and an Opus 5 president synthesizes the final verdict WHILE surfacing the dissent. Inspired by Karpathy's LLM Council, re-implemented on the OmegaOS Workflow primitive. 100% Claude Code-native — NO API KEYS, no OpenRouter, no external provider, no extra cost: the members run as in-process Workflow sub-agents through your EXISTING Claude Code session. Use when the user says "llm council", "convene the council", "ask the council", "@council", "/llm-council", "second opinion", "deliberate", "multiple models", or faces a "high-stakes decision" / architecture choice / contradictory verification verdicts / a pre-commit design
    2 repo stars
  93. ▌
    New Project · agentik-os
    OmegaOS end-to-end new-project pipeline — guiding (client/works) → stack pick → AUTO-PROVISION external services (Vercel/Convex/GitHub/Clerk/Stripe) from ~/.omega/provisioning → scaffold the full stack → wire every key → register the project → vision/PRD → /omg-planner (typed DAG plan) → omega plan-run (the engine executes it with can't-skip Gate + Guardian verify). Launchable from the TUI [N] New Project menu or by typing /omg-new-project (alias /omega-new-project).
    2 repo stars
  94. ▌
    Open Design · agentik-os bundle
    Drive Open Design (self-hosted nexu-io/open-design) to build design systems and generate brand visuals from OmegaOS. It turns an agent into a design engine: prototypes, dashboards, landing pages, decks, images and video, rendered from a brand contract (DESIGN.md) using 150+ built-in design systems (apple, airbnb, ant, agentic, …), 100+ functional skills and render templates. Results are viewable in the browser over Tailscale (the OmegaOS server surface), so the operator SEES the build, not just files. Use for: building or applying a design system, a brand kit, a UI prototype, a pitch deck, marketing creatives for the marketing machine, product screens, or any "make it look designed" artifact that should be viewable at a link. Triggers (EN): "design system", "brand kit", "build a prototype", "landing page design", "pitch deck", "generate a dashboard", "marketing creative", "open design", "make a deck/prototype I can view". Triggers (FR): "design system", "kit de marque", "construire un prototype", "maquette",
    2 repo stars
  95. ▌
    Reel Script · agentik-os bundle
    Écrit un script de reel Instagram calibré sur les patterns viraux — hook chiffré dès la 1ʳᵉ seconde, structure en 3 étapes, cliffhanger de rétention, 175 mots max (≈ 60 s). Use when the user asks for a reel script, video script, or short-form content script.
    2 repo stars
  96. ▌
    Health Energy Os · agentik-os bundle
    Build and protect physical and cognitive capacity through sleep, movement, training, nutrition, recovery, stress regulation, environment design and appropriate professional care. Upstream capacity provider for Habit, Execution and Strategy OS. Contains 12 specialist agents, 18 skills, 8 protocols and 6 schemas. Use for sleep and recovery planning, training and nutrition design, stress regulation, energy audits, or deciding when to escalate to a professional. Trigger words: health, energy, sleep, movement, training, nutrition, recovery, stress, capacity; FR: sante, energie, sommeil, mouvement, entrainement, nutrition, recuperation, stress, capacite.
    2 repo stars
  97. ▌
    Intuitive Os · agentik-os bundle
    Train, 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
    2 repo stars
  98. ▌
    Linear Setup · agentik-os
    Complete Linear feedback system setup wizard (v2.1). Installs widget with priority selector + page-aware Scope labels, API routes with hardcoded label IDs and default CTO assignee, Linear label GROUPS (FEEDBACK / SOURCE / optional AGENTS), public feedback page, and MCP integration. Auto-detects dashboard pages from sidebar to generate Scope labels. Use when user says "/linear-setup", "setup linear", "add feedback system", or "install Linear widget". One-time setup. After setup, use /linear-fix to resolve tickets.
    2 repo stars
  99. ▌
    Project Tidy · agentik-os bundle
    Range un projet pollué par le sprawl des agents IA — regroupe la doc humaine dans docs/ et le tracking/junk agent visible dans agentic/, réécrit CLAUDE.md/AGENTS.md pour définir où va chaque fichier (les futurs agents s'y conforment), propose la suppression du périmé et signale les incohérences doc↔app. Ne touche JAMAIS au code, aux dotfolders système (.git/.planner/.audit/ .oracles…), ni au canon (vision/PRD/feature/step).
    2 repo stars
  100. ▌
    Seductive Os · agentik-os bundle
    Build 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
    2 repo stars