Plan and execute entire application builds. Generates phased delivery roadmaps, then executes them autonomously — phase by phase, committing at milestones, deploying, testing, and…
Break the current milestone into slices. Reads M###-ROADMAP.md, asks for slice content until all slices are filled. Creates M###-S##-PLAN.md per slice.
AI-powered spatial epigenomics analysis combining chromatin accessibility, histone modifications, and DNA methylation with spatial coordinates for tissue architecture mapping.
Interactive question-driven discovery skill that transforms vague business problems into structured AI-consumable documents.
Gerencia sprints de desenvolvimento com brainstorm interativo, tracking e tarefas. Use quando precisar criar sprints, planejar iterações, atualizar progresso, ou gerenciar tarefas…
Generate stakeholder-specific communications and presentations for product updates
Generate stakeholder analysis matrices and visualizations including Power-Interest grids and RACI matrices
Stakeholder preference elicitation skill for structured value and weight gathering
Apple-canon design system consultation for SwiftUI projects. Produces DESIGN.md (human source of truth) + a Swift Package starter (DesignSystem.swift + Package.swift + Tests)…
Descobre melhorias visuais e de usabilidade com validação via browser. Use quando precisar analisar interfaces, identificar problemas de UX, ou sugerir melhorias visuais — from…
Value stream mapping skill for current state analysis, waste identification, and future state design with implementation roadmaps
Customer-centric value proposition development using jobs-to-be-done methodology
Use when the user asks to "escribe handoff", "cierra la rama", "prepara /compact", "prepara /clear", or right before the context gate of Fase N+7.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against be — from…
Run axe-core / Pa11y / Lighthouse against changed pages and classify findings by WCAG level (A / AA / AAA)
Validate code against accessibility standards: WCAG 2.1 Level AA, EN 301 549, and the European Accessibility Act (EAA / Directive EU 2019/882).
Use when: writing, rewriting, or auditing acceptance criteria, definition-of-done lists, or user-story AC for quality: testable, observable, single, scoped, and…
Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color c — from…
Prüft Websites und Web-Applikationen (insbesondere React und Angular) auf Barrierefreiheit nach WCAG-Standard.
Use this skill to add planned work discovered during execution to the end of the current milestone in the roadmap.
Mutate a card's status (open / active / blocked / disproved / superseded — everything except `done`).
Maquina de design UI/UX. 67 estilos, 96 paletas, 57 font pairings, 13 stacks. Design system, componentes, landing pages, dashboards. Integra com shadcn, Figma, v0.
Maquina autonoma de teste final. QAT textual, UX-QAT visual, benchmark comparativo, ciclo test-fix-retest, E2E batch — PDCA convergente com scores.
Adversarial review: tenta quebrar o design antes do build. Analisa SPEC/PRD e lista top 5 formas de quebrar, suposicoes implicitas, edge cases nao cobertos.
Avalia qualidade UX de um projeto comparando screenshots reais contra a Design Library (24 solucoes + design system).
Captura tela e controla mouse/teclado em apps nativos macOS via router 3-tier: macos-use (Accessibility tree, semantico — preferido) -> macos-automator (AppleScript/JXA) ->…
[INTERNAL — invocada via ag-4-teste-final] Cria cenarios UX-QAT de alta qualidade. Mapeia telas, seleciona rubrics visuais, define interacoes criticas, captura golden screenshots…
Executa incorporacao de um modulo seguindo o roadmap e task_plan. Implementa ACL, migrations, sync, UI adapters. Um modulo por vez.
Cria roadmap de incorporacao com fases, milestones, feature flags e task_plan. Transforma mapa de integracao em plano executavel.
UX-QAT PDCA Orchestrator — executa Visual Quality Acceptance Testing com ciclo Plan-Do-Check-Act. Captura screenshots por breakpoint/tema, avalia com AI Judge multimodal,…
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance.
Create or update a project roadmap with major milestones. Generates the configured roadmap artifact (default .ai-factory/ROADMAP.md) — a strategic checklist of high-level goals.
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or…
Generate design graph nodes (UserJourney, Flow, Page, Component) from any input: Jira ticket, plain-text description, scenario references, or Figma wireframes.
TOGAF-style architecture gap analysis: traces Baseline (AS IS) and Target (TO BE) architectures, builds a Transition plan via TDD, and produces a Gap Matrix with risks — all…
Archive root-level planning files (`task_plan.md`, `findings.md`, and `progress.md`) into a timestamped `.plannings/` directory for the current feature.
Use when session-end potrzebuje sprawdzić retencję tematów narracyjnych (L2) z articulation bank, lub gdy Jakub prosi "zadaj mi pytania z banku", "sprawdź mnie z X tematów",…
Strategic ASO planning with category-specific templates. 4-phase roadmap, keyword strategy design, metadata roadmap, visual improvement plan.
Hunt for one previously-undocumented defect, derivation gap, doc drift, missing test or wrong concept. Also architectural ugliness, code smells and inconsistencies.
Create or update product briefs through guided or autonomous discovery. Use when the user requests to 'create a product brief', 'help me create a project brief', or 'update my…
Use ONLY when the user explicitly asks to orchestrate parallel external agents (Codex or Claude Code) in tmux sessions via tp (tmux-pilot).
Produces production-ready briefs for app onboarding, App Store preview, and feature-demo videos from supplied UI screenshots.
Designs the in-product interface from a validated map-user-flow — screen inventory, a reusable component system, DESIGN-token application, per-state visual treatments,…
Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts…
Hands-on implementation partner for creating tools, scripts, dashboards, and prototypes. Use when the user wants to build something tangible — apps, scripts, automations, or…
Create or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work.
Create a change management request with impact analysis and rollback plan. Use when proposing a system or process change that needs approval, preparing a change record for CAB…
Analyze and validate forms on web pages. Use when users ask to check form accessibility, verify form labels, audit input fields, check form validation, or analyze form UX.
Analyze and validate images on web pages. Use when users ask to check image alt tags, verify image accessibility, find missing alt attributes, audit image SEO, or check image…
Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation…
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component — from…
Use when brainstorming product names, company names, or brand names. Based on David Placek's Lexicon Branding methodology (Vercel, Swiffer, Sonos, Azure, BlackBerry).
Audit + groom `docs/forsvn/artifacts/` — classify every file (KEEP/STALE/ORPHAN/LEGACY/EPHEMERAL), surface references + risk.
Audit + clean a developer's machine — dotfolders, caches, language toolchains, package globals — with per-target classification, risk surfacing (auth, processes, side effects),…
Clean up git worktrees created by Claude Code background agents. Commits dirty state, merges to target branch, removes worktrees, and purges stale remnant directories from…
Remove stale agent worktree directories and their orphaned branches. Run after parallel agent work or when .claude/worktrees/ accumulates cruft.
Audit any CLI tool for terminal user experience — help text, command structure, error messages, output formatting, discoverability, and accessibility — produces a scored report…
Run the feature-advisor query-time subagent over the full ontology to produce a structured impact assessment for a proposed feature or change.
Run parallel competitor deep-dives and synthesize into positioning strategy and battle cards
Competitive analysis and market positioning partner for Product Managers. Use when the user needs to analyze competitors, map market positioning, identify feature gaps, or prepare…