agentik-os
- 502 skills
- 0 followers
- 2 repo stars
- last month last updated
- ▌ Wireframe Spec · agentik-osSpecify wireframe layouts with content priority, component placement, and annotation.
- ▌ A B Test Design · agentik-osDesign rigorous A/B tests with hypotheses, variants, metrics, and sample size calculations.
- ▌ Business Design · agentik-osA practitioner's toolkit for thinking and communicating as a designer in a business context — reading financials, mapping competitive landscapes, and defending design decisions in the language of value.
- ▌ Click Test Plan · agentik-osDesign click/first-click tests to evaluate navigation and information findability.
- ▌ Design Critique · agentik-osFacilitate structured design critiques with clear feedback frameworks and actionable outcomes.
- ▌ Jobs To Be Done · agentik-osMap user Jobs-to-Be-Done with functional, emotional, and social dimensions plus outcome expectations. Use when reframing product decisions around user motivations rather than features.
- ▌ Pattern Library · agentik-osStructure a pattern library entry with problem context, solution pattern, usage examples, and related patterns.
- ▌ Affinity Diagram · agentik-osOrganize qualitative research data into an affinity diagram with themes, clusters, and insight statements. Use when synthesizing large amounts of qualitative data from interviews, observations, or surveys.
- ▌ Dark Mode Design · agentik-osDesign effective dark mode interfaces with proper color adaptation, contrast, and elevation.
- ▌ Design Rationale · agentik-osWrite clear design rationale connecting decisions to user needs, business goals, and principles.
- ▌ Diary Study Plan · agentik-osDesign a diary study plan with prompts, duration, participant criteria, and analysis framework. Use when you need to understand user behavior over time in natural contexts.
- ▌
- ▌ Interview Script · agentik-osCreate a structured user interview script with warm-up, core exploration, and wrap-up sections. Use when preparing for user research interviews to ensure consistent, insightful conversations.
- ▌ Law Of Proximity · agentik-osApply the Law of Proximity to group related elements through spatial relationships.
- ▌ Readable Measure · agentik-osSet optimal line lengths for readability across typography scales and responsive layouts.
- ▌
- ▌ Typography Scale · agentik-osCreate a modular typography scale with size, weight, and line-height relationships.
- ▌ Visual Hierarchy · agentik-osEstablish clear visual hierarchy through size, weight, color, spacing, and positioning.
- ▌ Design Debt Audit · agentik-osIdentify, categorize, and prioritize accumulated design inconsistencies and structural problems across a product.
- ▌ Design Principles · agentik-osDefine a set of actionable design principles that guide decision-making and resolve trade-offs.
- ▌ Doherty Threshold · agentik-osApply the Doherty Threshold — keep system response times under 400ms to maintain user flow and perceived performance.
- ▌
- ▌ Feedback Patterns · agentik-osDesign system feedback for user actions including confirmations, status updates, and notifications.
- ▌ Naming Convention · agentik-osEstablish a naming convention system for design elements, components, and tokens with clear rules and examples.
- ▌ North Star Vision · agentik-osArticulate a compelling north-star product vision that aligns teams and inspires strategic design decisions.
- ▌ Onboarding Design · agentik-osDesign first-run experiences that get users to value quickly without overwhelming them.
- ▌ Presentation Deck · agentik-osStructure compelling design presentations for stakeholders, reviews, and showcases.
- ▌ Responsive Design · agentik-osDesign adaptive layouts and interactions that work across all screen sizes and input methods.
- ▌ Service Blueprint · agentik-osMap the end-to-end service delivery system including frontstage actions, backstage processes, and supporting infrastructure.
- ▌ User Flow Diagram · agentik-osCreate user flow diagrams showing paths, decisions, and branch logic.
- ▌ Card Sort Analysis · agentik-osAnalyze card sorting results to inform information architecture and navigation structure. Use after conducting open or closed card sort studies.
- ▌ Design Negotiation · agentik-osAdvocate for design quality, scope, and time with cross-functional partners and leadership using evidence and shared goals.
- ▌ Design Sprint Plan · agentik-osPlan and facilitate design sprints from challenge framing through prototype testing.
- ▌ Design Token Audit · agentik-osAudit design token usage across a product for consistency and coverage.
- ▌ Illustration Style · agentik-osDefine an illustration style guide with visual language, color usage, and application rules.
- ▌ Metrics Definition · agentik-osDefine UX metrics and KPIs that connect design decisions to measurable business and user outcomes.
- ▌ Prototype Strategy · agentik-osChoose the right prototyping fidelity and method for the design question.
- ▌
- ▌ Aesthetic Usability · agentik-osApply the Aesthetic-Usability Effect — visually consistent, polished interfaces are perceived as more usable.
- ▌ Context Engineering · agentik-osDesigning what information goes into the context window and in what order.
- ▌ Critique Affordance · agentik-osCritique a screen's interactive affordances — what looks clickable, state visibility, CTA clarity, and action discoverability.
- ▌ Critique Typography · agentik-osCritique a screen's typography — scale usage, readability, consistency, and token compliance.
- ▌
- ▌ Localization Design · agentik-osDesign interfaces that adapt gracefully to multiple languages, writing directions, and cultural contexts.
- ▌ Navigation Patterns · agentik-osSelect and design navigation patterns that match product structure, user tasks, and platform conventions.
- ▌ Research Repository · agentik-osBuild and maintain a research repository that makes findings findable, reusable, and cumulative across the organization.
- ▌ Summarize Interview · agentik-osSummarize a user interview transcript into structured insights with key themes, quotes, and action items. Use after conducting user interviews to extract and share findings efficiently.
- ▌ Usability Test Plan · agentik-osDesign a usability test plan with tasks, success metrics, participant criteria, and facilitation guide. Use when planning moderated or unmoderated usability testing sessions.
- ▌ Von Restorff Effect · agentik-osApply the Von Restorff Effect to make the most important element distinctly different from its surroundings.
- ▌ Competitive Analysis · agentik-osConduct a structured competitive analysis comparing UX patterns, features, strengths, and gaps across rival products.
- ▌ Critique Composition · agentik-osCritique a screen's composition — balance, whitespace, rhythm, and gestalt principles.
- ▌ Heuristic Evaluation · agentik-osConduct expert heuristic evaluations using Nielsen's heuristics and domain-specific criteria.
- ▌ Interfaces That Feel · agentik-osApply an emotional resonance lens to any UI. Use when a design is technically correct but flat — to identify what's missing and prescribe specific changes at the copy, motion, and interaction layer.
- ▌ Law Of Common Region · agentik-osApply the Law of Common Region to group elements using containers, backgrounds, and boundaries.
- ▌ Design Review Process · agentik-osEstablish design review gates with criteria, checklists, and approval workflows.
- ▌ Opportunity Framework · agentik-osIdentify, evaluate, and prioritize design opportunities using impact-effort frameworks and strategic criteria.
- ▌ Stakeholder Alignment · agentik-osCreate stakeholder alignment artifacts including responsibility matrices, decision frameworks, and communication plans.
- ▌ Design System Adoption · agentik-osCreate adoption strategies and materials to drive design system usage across teams.
- ▌ Documentation Template · agentik-osGenerate structured documentation templates for components, patterns, or guidelines within a design system.
- ▌ Micro Interaction Spec · agentik-osSpecify micro-interactions with trigger, rules, feedback, and loop/mode definitions.
- ▌ Accessibility Test Plan · agentik-osCreate accessibility testing plans covering assistive technologies and WCAG criteria.
- ▌ Design Impact Reporting · agentik-osCommunicate design's contribution to business and user outcomes in terms that resonate with stakeholders.
- ▌ Design System Governance · agentik-osDefine how a design system evolves — contribution models, versioning, change management, and deprecation.
- ▌ Information Architecture · agentik-osDesign the structure, hierarchy, and navigation model for a product's content and features.
- ▌ Version Control Strategy · agentik-osDefine version control strategies for design files, components, and libraries.
- ▌ Critique Visual Hierarchy · agentik-osCritique a screen's visual hierarchy — entry point, eye flow, weight distribution, and emphasis.
- ▌ Critique Brand Consistency · agentik-osCritique a screen's brand consistency against mood.md, voice.md, and tokens.md.
- ▌ Critique Information Density · agentik-osCritique a screen's information density — cognitive load, content prioritisation, scanning patterns, and progressive disclosure.
- ▌ AI Logic Os 2 · 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,
- ▌ Habit Tracker Os 2 · 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} and Context & Memory {OS} (an external "Life OS" life-tracking app, if the user has one, is an out-of-suite dependency, not a member of this suite). 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.
- ▌ Brainstorm Os 2 · 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”.
- ▌ Alignment Os 2 · 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.
- ▌ Blueprint Os 2 · agentik-os bundleCompile 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}. 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.
- ▌ Growth Engine · 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.
- ▌ Secrets Vault · agentik-os bundleEncrypted-in-repo secret vault (SOPS + age) so a lost laptop never means lost keys: every project's secrets are committed to git as age CIPHERTEXT and a fresh `git clone` + ONE master key restores everything (`sops -d`). A repo leak yields only ciphertext. Implements the R-SECRETS-VAULT doctrine. Use when the user says "vault", "encrypt my secrets", "secret backup", "recover my keys", "commit my API keys", "sops", "age", "never lose a key", or in French "coffre-fort", "chiffrer mes secrets", "sauvegarder mes cles", "recuperer mes cles". NOT for live secret INJECTION into a running app (that stays a plaintext .env in ~/.omega); NOT for public repos (they NEVER carry ciphertext).
- ▌ Market Research Os · 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.
- ▌ Dxaudit · agentik-osForensic developer experience audit v1 (Gestalt-Popper). 21-phase deep analysis of every DX surface: README quality (can a new dev start in <10min), Setup complexity (steps to run locally), Error message quality (actionable vs cryptic — owns HELPFULNESS; /copyaudit owns CLARITY; /debugaudit owns ACCURACY), TypeScript strictness, Code documentation (JSDoc on public APIs), Testing infrastructure, CI/CD pipeline quality, PR template/process, Dependency management, Monorepo structure, Dev tooling (linting, formatting, pre-commit hooks), Environment parity (dev/staging/prod), Debug tooling, Migration guides, Changelog maintenance, Contribution guide, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Score /320. Preamble v1.0 compliant. Primary audit for CLI/library projects (replaces /uiuxaudit + /flowaudit + /motionaudit which ABORT on non-UI). Audit -> Plan -> Fix -> Re-audit. Use when user says "/dxaudit", "dx audit", "developer experience", "onboarding audit", "can a new dev start",
- ▌ Brand Identity · agentik-os bundleOmegaOS-shipped Complete Brand Identity System v2.1. From discovery to a deployed interactive brand book: Kapferer Brand Identity Prism, 2-3 switchable variants, typography, colors, voice, logo direction, AI prompts, design tokens, component previews (Next.js brand book on Vercel). Use when user says "/omg-brand-identity", "/brand-identity", "brand book", "brand system", or "visual identity". Step 3 of the OmegaOS new-project pipeline: run /omg-vision then /omg-prd first, follow with /omg-planner then `omega plan-run`.
- ▌ Social Content · agentik-os bundleCreate, schedule, and optimize organic social content for LinkedIn, X/Twitter, Instagram, TikTok, Facebook — posts, threads, carousels, content calendars, and short-form video scripts/hooks. Use when the user says "/omg-social-content", "/social-content", "LinkedIn post", "Twitter thread", "content calendar", "reel", "short-form video", or "what should I post". R-MARKETING: organic distribution, downstream of content-strategy.
- ▌ Artifact Design · agentik-osPublishes deliverable reports (audit, research memo, strategy doc, mission recap, dashboard, brief) as LIVE claude.ai Artifacts via the native Artifact tool; surface 1 of the OmegaOS report router (R-ARTIFACT). Use when the user says "report", "live report", "publish an artifact", "make this a report", "dashboard report", "share a page", or in French "rapport", "rapport live", "publie un artifact", "fais-moi un rapport", "tableau de bord". NOT for explicit PDF asks (omega pdf, R-PDF), plain file-only asks (R-HTML), generating videos or images, or scripted browser E2E.
- ▌ Apiaudit · agentik-osForensic API quality audit v1 (Gestalt-Popper). 23-phase deep analysis of every API surface: Endpoint inventory, REST/GraphQL contract compliance, Authentication (every endpoint — owns STATIC auth correctness; /secaudit owns RUNTIME exploitation), Authorization (role-based access), Input validation (every parameter), Error response format, Status code correctness, Pagination, Rate limiting, Versioning strategy, Documentation accuracy, Response time benchmarks, N+1 detection, Idempotency, Webhook reliability, CORS configuration, Content negotiation, API deprecation handling, plus verdict, fix plan, fix execution, re-audit, and rate-limit safety gate. Reads audits/.dataaudit/verdict.json for schema types when available. Outputs audits/.apiaudit/verdict.json consumed by /secaudit for auth surface exploitation. Score /360. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/apiaudit", "api audit", "api quality check", "endpoint audit", "api security check", "api contract verification".
- ▌ Depaudit · agentik-osForensic dependency & supply-chain audit v1 (Gestalt-Popper). 18-phase deep analysis of everything the project TRUSTS from third parties: dependency CVE exposure (direct + transitive), outdated and abandoned packages, license compliance and contamination, lockfile integrity and reproducible builds, transitive dependency bloat and duplication, typosquatting / dependency-confusion / namespace-takeover risk, postinstall and lifecycle script auditing, pinned vs floating version policy, SBOM generation and completeness, registry trust and provenance, bundle exposure (server deps leaking to client), monorepo workspace hygiene, plus verdict, fix plan, fix execution, re-audit, and build-integrity safety gate. Answers "Is the supply chain SAFE?" Score /360. Preamble v1.0 compliant. Complements /secaudit (which owns RUNTIME exploitation of CVEs) — depaudit owns STATIC supply-chain hygiene, provenance, licensing, and reproducibility. Audit -> Plan -> Fix -> Re-audit. Use when user says "/depaudit", "dependency audit", "
- ▌ Secaudit · agentik-osForensic security audit v1 (Gestalt-Popper). 25-phase deep analysis of everything that is VULNERABLE RIGHT NOW: OWASP Top 10 verification, XSS testing (25+ payload patterns), SQL/NoSQL injection, CORS misconfiguration, CSP headers audit, authentication bypass, session management, JWT security, IDOR detection, SSRF probing, open redirect testing, file upload vulnerabilities, rate limiting verification, brute force protection, secrets scanning (env vars, git history, JS bundles), dependency CVE audit, SSL/TLS configuration, security headers audit, API authentication verification, input validation completeness, plus verdict, fix plan, fix execution, re-audit, and rate-limit safety gate. Score /400. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/secaudit", "security audit", "is it secure", "vulnerability scan", "pentest the code", "find vulnerabilities", "security review", "owasp audit".
- ▌ Seoaudit · agentik-osForensic SEO audit v1 (Gestalt-Popper). 25-phase deep analysis of every search visibility surface: Crawlability (robots.txt, meta robots, canonical), Indexability (sitemap, internal links), Core Web Vitals (LCP, FID, CLS via /perfaudit handoff), Schema.org markup, Meta tags, Heading hierarchy, Image SEO, URL structure, Mobile-friendliness, Page speed, Content quality (E-E-A-T), Internal linking, External links, Hreflang, Pagination, Redirect chains, 404s/broken links, JavaScript rendering, GEO/AEO (AI search optimization), Competitor SERP analysis, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Score /400. Preamble v1.0 compliant. Reads audits/.perfaudit/verdict.json for CWV data when available. Audit -> Plan -> Fix -> Re-audit. Use when user says "/seoaudit", "seo audit", "why am I not ranking", "search optimization", "organic traffic", "indexing issues", "search visibility".
- ▌ Changelog Adopt · agentik-os bundleClaude Changelog Adopt — a daily autonomous self-improvement pass that reads the OFFICIAL Claude Code changelog (the authoritative GitHub CHANGELOG for anthropics/claude-code, with @claudecodelog as a secondary mirror), diffs it against the last version OmegaOS already absorbed, and for each NEW entry decides whether it implies a concrete OmegaOS or system-agent improvement — a new primitive, a doctrine change, an agent-behavior shift, a deprecation to unwind. It classifies each entry (opus), proposes a surgical adoption (what to change, in which file, why — like the manual /loop -> R-LOOP native-loop doctrine move), runs an adversarial anti-fabrication gate (opus, default-reject), writes a self-contained HTML report + Telegram alert for the operator to decide, and — only when ARMED — dispatches each vetted proposal to an oracle behind the full quality gate (In-Review handoff, never auto-Done, never force-push). Auto-adoption is scoped to doctrine (rules.rs), agent identities (agents/*.md), skills, and instal
- ▌ Launch Strategy · agentik-osPlan a product launch, feature announcement, or release go-to-market — build momentum, pick channels (Product Hunt, waitlist, email, social), and convert attention into users. Use when the user says "/omg-launch-strategy", "/launch-strategy", "launch", "Product Hunt", "feature release", "announcement", "go-to-market", "GTM plan", "beta/early access", "waitlist", or "we're about to ship". R-MARKETING: the launch-moment skill, downstream of product-marketing-context and market-research.
- ▌ Market Research · agentik-osResearch market size, trends, competitors, and decision-makers for any industry via the gooseworks data API (natural-language company search, financials, people search). Use when the user says "/omg-market-research", "/market-research", "market analysis", "market size", "TAM", "competitor research", or "industry research". R-MARKETING (research): the most-upstream skill — run before product-marketing-context and launch-strategy. Requires gooseworks credentials.
- ▌ Powerup Library · agentik-osRouter into the private Power-Up skill library (907 specialist Claude skills) that is NOT loaded into the active namespace. Use this the moment a request matches one of its domains, so the right specialist skill is applied instead of a generic answer. Covers: 30 days of content, cold outreach / cold email, sell on Etsy, launch a digital product, launch a podcast, grow on YouTube, faceless channel, start and grow a newsletter, LinkedIn personal brand, build an email funnel, get more leads, write a sales page, write better ads, write like a human, master AI prompting, make AI Instagram videos, create AI product photos, build brand identity, nail pricing, productize a service, find your niche, run webinars, sell with social proof, build a paid community, write a book, course creator, business analyst, automate your business with AI, vibe-code an app; plus bundle categories: Ads & Paid Media, Analytics & Data, Branding & Design, Client & Consulting, Content & Copywriting, Courses & Education, E-commerce & Product
- ▌ Review Governance Os · agentik-os bundleTurn actions, incidents, metrics and decisions into honest learning, controlled change, explicit policy and continuously improved personal and professional systems. Omega Core function that closes learning loops and governs consequential change across all other OSs (approval authority referenced by Revenue OS for boundary/schema/quality-gate changes). Contains 13 specialist agents, 20 skills, 7 protocols and 7 schemas. Use for incident review, postmortems, policy changes, retrospectives, or governance approval of a consequential change. Trigger words: review, governance, incident, postmortem, policy, retrospective, approval; FR: revue, gouvernance, incident, retour d'experience, politique, retrospective, approbation.
- ▌ A11yaudit · agentik-osForensic accessibility audit v1 (Gestalt-Popper). 21-phase deep analysis of every accessibility surface: WCAG 2.1 AA compliance, keyboard navigation (every interactive element), screen reader testing, ARIA labels/roles/states, color contrast (4.5:1 AA, 3:1 large text), focus management, skip navigation, form labels, error announcements, alt text, heading hierarchy, landmark regions, touch targets (44px), motion/animation preferences, cognitive load, reading level, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Score /320. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/a11yaudit", "accessibility audit", "wcag audit", "a11y check", "keyboard navigation test", "screen reader test", "color contrast check".
- ▌ Codeaudit · agentik-os bundleCIA-grade deep code audit v3. 24-phase forensic analysis: phantom detection, dependency dissection, contract interrogation, data flow tracing, state mutation analysis, concurrency autopsy, blast radius mapping, time bomb hunting, supply chain forensics, error propagation tracing, behavioral fingerprinting, configuration drift detection, feature verification, entropy analysis, git criminal profiling, runtime vivisection, observability, test coverage, API contracts, resilience, verdict, fix plan, fix execution, re-audit. Gestalt-Popper doctrine. Preamble v1.0 compliant. Use when user says "/codeaudit", "audit the code", "deep audit", "code review everything".
- ▌ Copyaudit · agentik-osForensic copy and messaging audit v1 (Gestalt-Popper). 19-phase deep analysis of every word on the product: Headline clarity (5-second test), Value proposition accuracy, CTA effectiveness, Claim verification (promises vs reality), Tone consistency, Technical accuracy, Grammar/spelling, Reading level (Flesch-Kincaid), SEO keyword integration, Social proof accuracy, Legal compliance, Microcopy (buttons, errors, empty states), Accessibility of copy, Brand voice adherence, plus verdict, fix plan, fix execution, re-audit, and i18n wrapping detection (owns hardcoded string scanning; /a11yaudit owns rendered-locale verification). Score /280. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/copyaudit", "copy audit", "messaging audit", "check the copy", "review the text", "tone check", "claim verification".
- ▌ Dataaudit · agentik-osForensic data integrity audit v1 (Gestalt-Popper). 21-phase deep analysis of every data surface: Schema validation, Migration status, Orphaned records, Referential integrity, Data consistency, Type safety (runtime vs schema), Null handling, Duplicate detection, Cascade behavior, Backup verification, Query performance, Index coverage, Data lifecycle (TTL, archival), PII detection, Seed data separation, Transaction integrity, plus verdict, fix plan, fix execution, re-audit, and DB backup safety gate (DESTRUCTIVE audit — verifies backup exists before any write operation). Outputs audits/.dataaudit/verdict.json consumed by /apiaudit for schema-to-contract validation. Score /320. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/dataaudit", "data audit", "data integrity check", "schema audit", "database audit", "orphaned records", "data consistency".
- ▌ Flowaudit · agentik-osForensic user flow audit v2. 25-phase deep analysis of every user journey, workflow, state machine, edge case, error recovery, and experience gap. Covers flow mapping, state verification, dead-end detection, permission gaps, data integrity through flows, onboarding completeness, cross-session continuity, error recovery paths, accessibility of journeys, flow performance, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Score /400. Preamble v1.0 compliant. Audit → Plan → Fix → Re-audit. Use when user says "/flowaudit", "audit the flows", "check user journeys", "workflow audit", "flow review".
- ▌ I18naudit · agentik-osForensic internationalization & localization audit v1 (Gestalt-Popper). 18-phase deep analysis of everything that decides whether the product is WORLD-READY: hardcoded user-facing string detection (JSX text, alt/title/aria/placeholder attributes, toast/error/email/notification copy), i18n framework wiring integrity (key existence, namespace structure, interpolation contract), locale routing & detection (path/subdomain/cookie/Accept-Language, persistence across navigation), pluralization rules (CLDR plural categories: zero/one/two/few/many/other), gender/grammatical agreement, date/time formatting (Intl.DateTimeFormat, timezone), number/percent/unit formatting, currency formatting (ISO 4217, symbol placement, minor-unit precision), RTL support (dir attribute, logical CSS properties, bidi-safe interpolation, mirrored icons), translation completeness + fallback chains, character encoding (UTF-8 end to end, normalization, mojibake), locale-aware sorting & collation (Intl.Collator), and untranslated-UI leakage at
- ▌ Perfaudit · agentik-osForensic performance audit v1 (Gestalt-Popper). 23-phase deep analysis of everything that is SLOW RIGHT NOW: Core Web Vitals, bundle size bloat, render performance, JavaScript execution, image optimization, font loading, caching strategy, CDN configuration, SSR/SSG analysis, lazy loading, code splitting, API response times, N+1 query detection, database query performance, memory leaks, connection pooling, resource hints, third-party script impact, plus verdict, fix plan, fix execution, re-audit, and integration smoke gate. Score /360. Preamble v1.0 compliant. Audit -> Plan -> Fix -> Re-audit. Use when user says "/perfaudit", "performance audit", "why is it slow", "speed audit", "optimize performance", "core web vitals", "bundle analysis".
- ▌ Uiuxaudit · agentik-osArt Director-grade UI/UX forensic audit. Pixel-level design coherence, cross-page consistency, typography hierarchy, color system integrity, spacing rhythm, component anatomy, interaction patterns, motion design, responsive fidelity, accessibility. Thinks like Dieter Rams meets Jony Ive meets the Linear design team. Use when user says "/uiuxaudit", "audit the design", "design review", "check UI consistency", or needs systematic design quality verification.
- ▌ Caio Master · agentik-os bundleUse to orchestrate the ENTIRE CAIO engagement — accompanying a classic company end-to-end to become AI-native — as ONE gap-checked, self-correcting pass that routes every phase to its owner skill and never rebuilds them. It walks the journey law (readiness/go-no-go → offer/sell → discovery → diagnose+architect+roadmap → build → enable+transfer → run+optimize), gap-checks each handoff (is the prior phase's real deliverable present AND sufficient before advancing?), adversarially verifies (≥2-of-3), and ships ONE CAIO Engagement Plan + a live phase tracker the operator drives. EN triggers caio master, run the full CAIO engagement, end-to-end AI transformation, make this company AI-native, orchestrate the CAIO journey, AI-native roadmap end to end, gap-check the transformation, CAIO program plan, where are we in the AI engagement. FR triggers caio master, pilote toute la transformation IA, rendre l'entreprise AI-native de bout en bout, orchestrer le parcours CAIO, plan d'accompagnement IA complet, gap-check de l
- ▌ Content Strategy · agentik-os bundleDecide what content to create — topic clusters, content pillars, editorial calendar — content that is searchable, shareable, or both. Use when the user says "/omg-content-strategy", "/content-strategy", "content plan", "what should I write about", "topic clusters", "content pillars", "editorial calendar", or "blog strategy". R-MARKETING: upstream of social-content and ad-creative.
- ▌ Strategy Portfolio Os · agentik-os bundleConvert ambition, evidence and constraints into a coherent strategy, explicit choices, a ranked portfolio of bets and disciplined allocation of time, attention, people and capital. Omega Core function that selects goals, bets, projects and resource allocation before execution begins. Contains 12 specialist agents, 20 skills, 6 protocols and 7 schemas. Use for strategy formulation, bet ranking, portfolio prioritization, or resource allocation decisions across projects. Trigger words: strategy, portfolio, bets, resource allocation, prioritization, strategic choice; FR: strategie, portefeuille, paris strategiques, allocation de ressources, priorisation, choix strategique.